{"work":{"id":"1910796d-9b52-4683-bf5c-de9632c1028b","openalex_id":null,"doi":null,"arxiv_id":"1412.6980","raw_key":null,"title":"Adam: A Method for Stochastic Optimization","authors":null,"authors_text":"Diederik P. Kingma, Jimmy Ba","year":2014,"venue":"cs.LG","abstract":"We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.","external_url":"https://arxiv.org/abs/1412.6980","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-30T09:44:37.421041+00:00","pith_arxiv_id":"1412.6980","created_at":"2026-05-08T16:50:03.275361+00:00","updated_at":"2026-06-30T09:44:37.421041+00:00","title_quality_ok":true,"display_title":"Adam: A Method for Stochastic Optimization","render_title":"Adam: A Method for Stochastic Optimization"},"hub":{"state":{"work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","tier":"mega_hub","tier_reason":"1,000+ Pith inbound or 100,000+ external citations","pith_inbound_count":1671,"external_cited_by_count":null,"distinct_field_count":83,"first_pith_cited_at":"2014-10-30T19:44:20+00:00","last_pith_cited_at":"2026-06-29T17:57:50+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"needed","recognition_status":"needed","updated_at":"2026-06-30T09:59:36.170459+00:00","tier_text":"mega_hub"},"tier":"mega_hub","role_counts":[{"context_role":"method","n":117},{"context_role":"background","n":96},{"context_role":"other","n":9},{"context_role":"baseline","n":8},{"context_role":"dataset","n":2}],"polarity_counts":[{"context_polarity":"use_method","n":117},{"context_polarity":"background","n":85},{"context_polarity":"unclear","n":20},{"context_polarity":"baseline","n":8},{"context_polarity":"use_dataset","n":2}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Adam: A Method for Stochastic Optimization","claims":[{"claim_text":"We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Adam: A Method for Stochastic Optimization because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T17:43:32.784621+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"32a2eaed-ca10-4d2b-9f12-e342896ac90b","orcid":null,"display_name":"Diederik P. Kingma"},{"id":"3651b710-1f6d-4de6-9dd2-f9e8628b782a","orcid":null,"display_name":"Jimmy Ba"}]},"error":null,"updated_at":"2026-05-13T17:24:03.069221+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T17:43:32.777616+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":61},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":36},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":31},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":30},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":29},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":25},{"title":"Gaussian Error Linear Units (GELUs)","work_id":"0466fd22-03a1-4a61-af0a-a900e77bb023","shared_citers":24},{"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","shared_citers":24},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":22},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":21},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":21},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":20},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":20},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":20},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":19},{"title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","work_id":"1c4b4409-c14b-488b-a086-c57a5aab8a29","shared_citers":18},{"title":"Attention Is All You Need","work_id":"baafb5a2-5272-43bc-932f-09fa9ffe5316","shared_citers":17},{"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","shared_citers":17},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":17},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":16},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":16},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":15},{"title":"PennyLane: Automatic differentiation of hybrid quantum-classical computations","work_id":"83078d0b-6c02-4fc5-822d-4da4204fd057","shared_citers":15},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":14}],"time_series":[{"n":2,"year":2015},{"n":3,"year":2016},{"n":3,"year":2017},{"n":4,"year":2018},{"n":5,"year":2019},{"n":3,"year":2020},{"n":7,"year":2021},{"n":7,"year":2022},{"n":6,"year":2023},{"n":5,"year":2024},{"n":7,"year":2025},{"n":585,"year":2026}]},"error":null,"updated_at":"2026-05-13T17:25:54.003532+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T17:43:32.033922+00:00"},"reader_index":{"job_type":"reader_index","status":"succeeded","result":{"note":"annotated reader requires full-text/OA fetch; shell is wired for mega hubs","status":"reader queued"},"error":null,"updated_at":"2026-05-19T19:11:37.805565+00:00"},"recognition_alignment":{"job_type":"recognition_alignment","status":"succeeded","result":{"modules":["IndisputableMonolith.Gravity.PropagationSpeed","IndisputableMonolith.Foundation.PreTemporalForcingOrder","IndisputableMonolith.Physics.LightConeCausalityFromRS","IndisputableMonolith.Cosmology.EtaBPrefactorDerivation","IndisputableMonolith.Physics.MaxwellEquationsFromRS","IndisputableMonolith.Gravity.BlackHoleEntropyFromLedger","IndisputableMonolith.Thermodynamics.FermiDirac","IndisputableMonolith.Gravity.BlackHoleHorizonStates"],"query_chars":1152},"error":null,"updated_at":"2026-05-19T19:11:48.476296+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Adam: A Method for Stochastic Optimization","claims":[{"claim_text":"We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Adam: A Method for Stochastic Optimization because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T17:43:32.781309+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Adam: A Method for Stochastic Optimization","claims":[{"claim_text":"We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Adam: A Method for Stochastic Optimization because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T17:25:52.707031+00:00"}},"summary":{"title":"Adam: A Method for Stochastic Optimization","claims":[{"claim_text":"We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Adam: A Method for Stochastic Optimization because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":61},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":36},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":31},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":30},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":29},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":25},{"title":"Gaussian Error Linear Units (GELUs)","work_id":"0466fd22-03a1-4a61-af0a-a900e77bb023","shared_citers":24},{"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","shared_citers":24},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":22},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":21},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":21},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":20},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":20},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":20},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":19},{"title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","work_id":"1c4b4409-c14b-488b-a086-c57a5aab8a29","shared_citers":18},{"title":"Attention Is All You Need","work_id":"baafb5a2-5272-43bc-932f-09fa9ffe5316","shared_citers":17},{"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","shared_citers":17},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":17},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":16},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":16},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":15},{"title":"PennyLane: Automatic differentiation of hybrid quantum-classical computations","work_id":"83078d0b-6c02-4fc5-822d-4da4204fd057","shared_citers":15},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":14}],"time_series":[{"n":2,"year":2015},{"n":3,"year":2016},{"n":3,"year":2017},{"n":4,"year":2018},{"n":5,"year":2019},{"n":3,"year":2020},{"n":7,"year":2021},{"n":7,"year":2022},{"n":6,"year":2023},{"n":5,"year":2024},{"n":7,"year":2025},{"n":585,"year":2026}]},"authors":[{"id":"32a2eaed-ca10-4d2b-9f12-e342896ac90b","orcid":null,"display_name":"Diederik P. Kingma","source":"manual","import_confidence":0.72},{"id":"3651b710-1f6d-4de6-9dd2-f9e8628b782a","orcid":null,"display_name":"Jimmy Ba","source":"manual","import_confidence":0.72}]},"citers":{"total":1671,"items":[{"citing_arxiv_id":"2606.30634","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining","primary_cat":"cs.LG","submitted_at":"2026-06-29T17:57:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"One-step gradient delay is optimizer-dependent rather than intrinsically unstable, with Muon and error-feedback correction enabling async pipeline parallelism to match synchronous performance on models up to 10B parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30464","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"NQS-Agent: Health-Aware Agentic Hyperparameter Optimization for Neural-Network Quantum States","primary_cat":"cond-mat.str-el","submitted_at":"2026-06-29T15:28:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"NQS-Agent introduces health-aware agentic hyperparameter optimization for neural-network quantum states, demonstrating improved results over human-tuned baselines on the square-lattice J1-J2 Heisenberg model by incorporating optimization trajectory stability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30398","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ENC-ODE: Event-level Neurodegenerative Modeling in Continuous Time with Neural ODEs","primary_cat":"cs.AI","submitted_at":"2026-06-29T14:47:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"ENC-ODE applies diagnosis-conditioned neural ODEs and target-conditioned attention to predict irregular biomarker trajectories in Alzheimer's, claiming better performance than sequence models on ADNI data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30286","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Streak detection in the VST/OmegaCAM archive using deep learning","primary_cat":"astro-ph.IM","submitted_at":"2026-06-29T13:27:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A two-stage deep learning pipeline (HT-LCNN detector + VGG6 classifier) trained on augmented real and simulated data detects streaks in OmegaCAM frames with F1 > 0.95 on test sets and 0.99 precision on real 2023 data, uncovering 25,335 streaks including >20% uncatalogued objects across 1.2 million f","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30267","ref_index":90,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Pathway variability, coat stiffening and mechanical adaptation during clathrin-mediated endocytosis","primary_cat":"q-bio.SC","submitted_at":"2026-06-29T13:15:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Hybrid simulation and non-Euclidean elasticity theory demonstrate that clathrin coats develop adaptive rigidity and memory during growth, producing flat, stalled, or closed outcomes through two energy-landscape gates and matching experiments without fitted parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30244","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation","primary_cat":"cs.CV","submitted_at":"2026-06-29T12:54:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"S4ECA achieves state-of-the-art performance on RRSIS-D and RefSegRS datasets for referring remote sensing image segmentation by updating 2.4% of parameters via textual and visual adapters with language-guided selection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30226","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization","primary_cat":"cs.LG","submitted_at":"2026-06-29T12:39:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hessian eigenvector displacement and inverse participation ratio metrics show SGD stabilizing leading curvature directions while Adam causes more reorganization and parameter localization in MLP training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29854","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Nonperturbative Leakage Elimination Operator-Based Quantum Control Pulse Design Beyond the High Frequency Driving Regime","primary_cat":"quant-ph","submitted_at":"2026-06-29T06:47:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Recasts LEO quantum control in nonperturbative Floquet-Magnus framework to derive low-frequency pulse conditions, proves equivalence to prior zero-order results, and validates on spin-chain state transfer and two-level adiabatic speedup.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29845","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding","primary_cat":"cs.CV","submitted_at":"2026-06-29T06:35:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents Bricker dataset and BRACE multi-frame model using frequency priors and cross-attention for flicker-banding removal in RAW screen captures, with new SFC metric.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29791","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics","primary_cat":"cs.LG","submitted_at":"2026-06-29T05:09:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Theoretical characterization of the inlier-memorization effect in simple autoencoders, deriving its emergence, strength, and persistence from data distribution and initialization, plus guidelines achieving SOTA on ADBench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29528","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Supervised Hebbian learning in Deep Counterstream Associative Networks","primary_cat":"cs.NE","submitted_at":"2026-06-28T17:44:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Supervised counterstream Hebbian learning in deep associative networks reaches high accuracy on binarized MNIST by propagating opposing activity waves linked via local rules.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29521","ref_index":43,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization","primary_cat":"cs.LG","submitted_at":"2026-06-28T17:31:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PCD is a new gradient-based optimizer for hierarchical multi-objective problems that prioritizes primary descent with minimal controlled distortion for secondary objectives via a single tau parameter.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29496","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios","primary_cat":"cs.CV","submitted_at":"2026-06-28T16:51:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RefineSplat applies entropy-aware adaptive masking and density control to 3DGS to remove color- or semantically ambiguous distractors, validated on a new 18-scene Ambiguous wild dataset with claimed SOTA results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29450","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"VeRe-Flow: Guiding Flow Matching toward Clean Speech via Velocity Contrastive Regularization and Representation Alignment for Noise-Robust Bandwidth Expansion","primary_cat":"eess.AS","submitted_at":"2026-06-28T15:15:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VeRe-Flow guides flow matching for noise-robust bandwidth expansion via velocity contrastive regularization at the velocity level and representation alignment with clean SSL features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29184","ref_index":50,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","primary_cat":"cs.LG","submitted_at":"2026-06-28T04:08:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"BaRA adds Bayesian adaptive rank allocation to LoRA fine-tuning by activating sparse instance-specific latent factors, with a generalization bound depending on learned joint effective rank rather than fixed maximum rank.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29167","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data","primary_cat":"cs.CV","submitted_at":"2026-06-28T03:05:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ATM is a zero-shot articulate-then-match framework that uses pretrained vision models and parametric priors to map diverse 3D inputs to a canonical space for robust dense correspondences without correspondence-specific training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29106","ref_index":110,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Deep Multiscale Neural Network for Accurate Neurological Disorder Detection from MRI Scans and Real-Time Web Deployment","primary_cat":"cs.CV","submitted_at":"2026-06-27T23:07:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"End-Net, a multiscale CNN with inception modules, claims superior accuracy on four-class neurological disorder MRI classification and includes online deployment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29105","ref_index":59,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data","primary_cat":"stat.ME","submitted_at":"2026-06-27T23:05:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29064","ref_index":47,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Fairness Attacks on Recommender Systems","primary_cat":"cs.IR","submitted_at":"2026-06-27T19:50:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A structure-aware RL fairness attack with joint item and gender selection policies is introduced and shown effective on four recommender models across two datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28984","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Compositional Dynamics in Learning and Mechanics","primary_cat":"math.CT","submitted_at":"2026-06-27T15:39:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An operad Arr supplies a single compositional syntax whose two functorial semantics in polynomial coalgebras recover both gradient-based learning and Hamiltonian-style mechanics on wired systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28953","ref_index":53,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System","primary_cat":"cs.SD","submitted_at":"2026-06-27T14:51:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Clustering DINO representations via K-means and LDA filters poisoned speech samples, reducing attack success rate from 99.75% to 0.25% at 10% poisoning level.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28947","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Machine-learnable Sets","primary_cat":"cs.LG","submitted_at":"2026-06-27T14:39:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces machine-learnability for sets of binary strings via bounded Boolean autoencoders and shows it holds for Rorschach patterns and evolved wild sets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28158","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Recovering Sharp Conductivity Features in the Finite-Data Calder\\'on Problem with Physics-Informed Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:54:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A PINN framework with separate networks for conductivity and potentials, multiscale wavelet excitations, and FFE recovers dominant conductivity structures from finite DtN data with 3-12% relative error on synthetic tests, with FFE aiding sharp features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28039","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Mind the Gap: Quantifying the Domain Gap in Cross-Sensor Diffusion Super-Resolution","primary_cat":"cs.CV","submitted_at":"2026-06-26T12:43:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Empirical study finds synthetic-to-real domain gap sharply degrades diffusion SR models on real cross-sensor satellite pairs while real-data training faces optimization and adaptation problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28026","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EMOSH: Expressive Motion and Shape Disentanglement for Human Animation","primary_cat":"cs.CV","submitted_at":"2026-06-26T12:30:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shape leakage.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27978","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:27:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27821","ref_index":41,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting","primary_cat":"quant-ph","submitted_at":"2026-06-26T08:02:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Gated QKAN fast-weight programmer achieves lowest pooled RMSE on Abilene TM forecasting while using 22.4% of a larger LSTM's parameters and outperforming classical G-FWP.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27760","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","primary_cat":"cs.CV","submitted_at":"2026-06-26T06:39:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27751","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From General-Purpose Audio Tagging to Spatially Grounded Sound Event Localization and Detection","primary_cat":"cs.SD","submitted_at":"2026-06-26T06:12:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AT2SELD extends pretrained audio tagging backbones to SELD via FOA descriptors, track-wise processing, permutation-aware supervision, and staged NAS on multiple datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26716","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution","primary_cat":"eess.IV","submitted_at":"2026-06-25T07:53:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DP-NSL achieves measurement-consistent arbitrary slice super-resolution in CT and MRI by confining learned details to the null space via orthogonal projection and using content-aware B-spline mixtures for continuity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26260","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A multi-task spatiotemporal deep neural network for predicting penetration depth and morphology in laser welding","primary_cat":"cs.CV","submitted_at":"2026-06-24T18:02:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A CNN-plus-state-space-model multi-task network predicts laser weld penetration state (99.35% accuracy), depth (1.79 mm error), and cross-section morphology (95.65% accuracy) from top-view weld-pool images and welding parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26078","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding","primary_cat":"cs.CV","submitted_at":"2026-06-24T17:52:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Unsupervised domain adaptation with GSDE achieves ~80% accuracy in cross-process TIG-laser weld penetration prediction, improving supervised baselines by over 43%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24851","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment","primary_cat":"cs.LG","submitted_at":"2026-06-23T17:29:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HNO matches or exceeds FNO performance on elliptic PDEs whose Green's functions are real and symmetric but lags on time-dependent PDEs whose operators carry phase, yielding a predictive rule that matches spectral basis to operator symmetry.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23478","ref_index":48,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ffortissimo: A Freeform Forward-Modeling Pipeline for High-Contrast Images of Circumstellar Disks Based on Automatic Differentiation","primary_cat":"astro-ph.IM","submitted_at":"2026-06-22T15:25:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ffortissimo is a JAX-based freeform forward-modeling pipeline that fits complex dust distributions and infers scattering properties in KLIP-reduced images of circumstellar disks such as HR 4796A.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23155","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Neural Parameter Calibration for Finite-State Mean Field Games","primary_cat":"cs.GT","submitted_at":"2026-06-22T11:00:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A differentiable neural framework for learning state- and time-dependent parameters of finite-state mean field games from population trajectories via implicit differentiation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21196","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Atomistic Mechanisms of Hard Carbon Formation from Polyvinylidene Chloride","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-19T08:07:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Machine-learned potential simulations show hard carbon from PVDC forms via radical-mediated dehydrochlorination and sp2 cross-linking, with non-hexagonal rings inducing curvature that prevents graphitic order.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19876","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence","primary_cat":"cs.LG","submitted_at":"2026-06-18T07:34:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proves global GD convergence on reverse Fisher divergence for GMM score matching to single-Gaussian targets from arbitrary init and to separated GMM targets under random init.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19850","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Neural Additive and Basis Models with Feature Selection and Interactions","primary_cat":"cs.LG","submitted_at":"2026-06-18T06:58:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Adds a trainable feature selection layer to NAM and NBM to cut computational cost, enable two-input interaction networks in high dimensions, and match or exceed state-of-the-art GAM performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19302","ref_index":248,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Optimal scenario design for climate emulation","primary_cat":"physics.ao-ph","submitted_at":"2026-06-17T17:26:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Optimizing training data via a differentiable SCM yields climate emulators that outperform those trained on six standard ScenarioMIP pathways while using less data and isolating distinct forcing responses.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19118","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Analysing drivers and interdependencies in European electricity markets using XAI","primary_cat":"cs.AI","submitted_at":"2026-06-17T14:32:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DNNs plus SHAP/SSHAP applied to 39 European bidding zones identify solar and gas as key price drivers and simulate a single-price EU market.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18499","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Solution of the Newtonian plane Couette flow with dynamic wall slip using machine-learning methods","primary_cat":"physics.flu-dyn","submitted_at":"2026-06-16T21:17:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PINNs and DeepONets solve Newtonian plane Couette flow with dynamic wall slip; DeepONet achieves 0.36% mean relative error on unseen cases and 540X speedup over numerical methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13562","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Contrast-Informed Augmentation and Domain-Adversarial Training for Adult-to-Neonatal MR Reconstruction Generalization","primary_cat":"cs.CV","submitted_at":"2026-06-11T16:47:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Mixed training with contrast-informed augmentation and domain-adversarial training improves E2E-VarNet performance on neonatal T2-weighted brain MR reconstruction at R=4 and R=8 compared to adult-only training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11657","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics","primary_cat":"cs.LG","submitted_at":"2026-06-10T04:38:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Case study applies SAE probing with enstrophy triage to a continuum-dynamics foundation model and reports intermittent feature consistency that does not align with standard physics while linking some output discrepancies to specific feature changes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11415","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings","primary_cat":"q-bio.NC","submitted_at":"2026-06-09T20:05:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SMR applied to EEG and iEEG data shows strong reconstruction persists after excluding local neighbors, indicating that electrode signals contain both local redundancy and broader distributed structure.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11140","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques","primary_cat":"physics.geo-ph","submitted_at":"2026-06-09T17:29:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Latent diffusion model parameterization allows MCMC and SMC to outperform latent-space ESMDA in data mismatch and uncertainty reduction for 3D subsurface DA, while model-space ESMDA produces unrealistic posteriors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10038","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning the Universe with the 2nd Generation of CAMELS: Varying 35 parameters of the IllustrisTNG model in (50Mpc/h)^3 boxes","primary_cat":"astro-ph.CO","submitted_at":"2026-06-08T18:12:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"New CAMELS simulations in larger (50 Mpc/h)^3 boxes with 35 varied parameters produce tighter neural-network constraints on model parameters than prior smaller-volume runs, with public data release.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10027","ref_index":237,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning the Universe: The Structure of Dust Attenuation Curves in Galaxy Simulations","primary_cat":"astro-ph.GA","submitted_at":"2026-06-08T18:08:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Four parameters suffice to describe dust attenuation curve diversity in TNG simulations, yielding a new symbolic-regression model that recovers curves and fluxes better than existing parameterizations while linking parameters to SFR surface density, metallicity, and geometry.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08986","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Discovering Misconceptions and Misunderstandings From Administrations of Research-Designed Multiple Choice Instruments","primary_cat":"physics.ed-ph","submitted_at":"2026-06-08T03:31:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Multidimensional IRT analysis of 34k FCI administrations identifies 22 robust misconception dimensions and computes student/class scores revealing varied post-instruction remediation patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08574","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","primary_cat":"cs.LG","submitted_at":"2026-06-07T11:11:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"OrderDP is a plug-and-play data pruning method that selects a random subset then top-q samples to guarantee unbiased surrogate-loss training with convergence analysis and over 40% training cost reduction on CIFAR and ImageNet.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08448","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multiscale Fourier Neural Operator for Inverse Wave Scattering in Highly Oscillatory Media","primary_cat":"math.NA","submitted_at":"2026-06-07T04:36:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MscaleFNO learns mappings from oscillatory media to wavefields for Helmholtz inverse problems and pairs it with diffusion regularization for partial-aperture 2D reconstructions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06322","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions","primary_cat":"cs.AI","submitted_at":"2026-06-04T15:57:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DragOn provides a new drag-grounding benchmark and training dataset for GUI agents, with evaluations suggesting potential improvements on computer-use tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06314","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DAS-PINNs for high-dimensional partial differential equations: extending deep adaptive sampling to spacetime domains","primary_cat":"math.NA","submitted_at":"2026-06-04T15:54:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DAS-PINNs uses normalizing flows to adaptively sample collocation points based on PDE residuals in unified spacetime domains for high-dimensional time-dependent PDEs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05103","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Identifying Gems from Roman RAPIDly","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:06:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Machine learning models RuBR_comb, RuBR_loc, and RuBR_DA for real-bogus classification of transients using combined simulated data and domain adaptation for the Roman RAPID pipeline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05045","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Control-Affine Reduced-Order Models via Autoencoders","primary_cat":"math.DS","submitted_at":"2026-06-03T16:05:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Framework learns control-affine reduced-order models via jointly trained autoencoders on high-dimensional data, extended to sequence-based models and assessed on numerical examples for prediction and feedback linearization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04735","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-06-03T11:19:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Eligibility traces in deep RL create a peak bias by amplifying distal TD errors into gradient shocks that fixed-step SGD cannot normalize, leading to overestimation of peak-reward trajectories and a mechanistic account of the peak-end rule.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06517","ref_index":60,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Odd-parity perturbations of trace-quadratic $f(R,T)$ black holes with anisotropic matter: admissible branches, axial ringdown, and a coupled-PINN benchmark","primary_cat":"gr-qc","submitted_at":"2026-06-02T12:32:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Admissible negative-w_r branches of trace-quadratic f(R,T) black holes support axial ringdown spectra governed by a single master equation equivalent to Einstein gravity plus frozen anisotropic fluid, differing from Schwarzschild by ~22% with no resolved α dependence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03393","ref_index":41,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection","primary_cat":"cs.LG","submitted_at":"2026-06-02T09:36:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Flicker-DDPM accelerates DDPM sampling by injecting 1/f colored noise matched to image spectra, achieving similar quality with 3.33 times fewer steps on CIFAR-10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02961","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AtlasGS: Brain MRI Spatial Resolution Harmonization With Shared Gaussian Geometry","primary_cat":"eess.IV","submitted_at":"2026-06-01T23:41:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AtlasGS uses shared subject-specific Gaussian geometry learned from isotropic scans to achieve through-plane super-resolution and multi-modal harmonization in brain MRI with reported state-of-the-art fidelity on UK Biobank, GBM, and ABCD datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04033","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture","primary_cat":"cs.LG","submitted_at":"2026-06-01T21:19:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A U-Net surrogate with multigroup attention pooling is trained on OpenMC sensitivity data and combined with gradient optimization to generate grid-based critical experiment geometries that achieve c_k values up to 0.97757 for HALEU fuel validation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02474","ref_index":157,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Approximating Hartree-Fock theory via an efficiently local reformulation","primary_cat":"physics.chem-ph","submitted_at":"2026-06-01T16:46:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A reorganized Hartree-Fock framework imposes tunable orbital locality by pairing local degrees of freedom with local solution conditions, maintaining efficient SCF optimization and competitive reaction-energy accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02385","ref_index":53,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","primary_cat":"q-bio.NC","submitted_at":"2026-06-01T15:34:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Derives optimality constraints for nonnegative joint dictionary learning that explain observed SAE behaviors such as feature splitting, absorption, and dense antipodal features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01293","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ResNet-34 with Lightweight Decoder for Accurate and Efficient Segmentation of Fetal Brain MRI","primary_cat":"eess.IV","submitted_at":"2026-05-31T15:25:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"ResNet-34 encoder with MLP-based lightweight decoder reports 90.33% mean DSC and 97.37% accuracy on FeTA 2021 fetal brain MRI segmentation, outperforming UNet variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02643","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Inference Cost Attacks for Retrieval-Augmented Large Language Models","primary_cat":"cs.CR","submitted_at":"2026-05-31T15:11:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Poisoning external knowledge bases with LLM-agent-crafted documents can increase RAG inference token consumption by up to 13.12 times at over 90% success rate while preserving answer quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00944","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA","primary_cat":"cs.LG","submitted_at":"2026-05-31T01:19:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PRISM is a gauge-invariant DP mechanism for LoRA that avoids bilinear noise amplification via tangent-space sampling, supplies a closed-form noise characterization on Z, and includes a DP-aware adaptive update rule.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00752","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A multimodal dataset of photoplethysmography and continuous behavioral responses to ASMR and nature videos","primary_cat":"cs.LG","submitted_at":"2026-05-30T14:36:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Introduces REST-ASMR multimodal dataset of PPG, stimuli, and continuous annotations for ASMR research, validated with 97% responder rate, significant agreement, PPG deceleration, and BiLSTM achieving 75.51% frame-level accuracy under strict subject-video independent 4-fold CV.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00520","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise","primary_cat":"math.OC","submitted_at":"2026-05-30T04:27:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"New in-expectation convergence guarantees for SMD, ASMD (convex) and SGD, SGDM (nonconvex) under heavy-tailed noise without bounded-domain restrictions or algorithmic modifications.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00442","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Exploiting weight-space symmetries for approximating curvature","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:17:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A framework that builds tractable structured Hessian approximations by averaging over user-chosen weight-space symmetry groups, recovering Shampoo-like estimates for one choice of group.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00419","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Parameter-Free and Group Conditional Online Conformal Prediction","primary_cat":"stat.ML","submitted_at":"2026-05-29T23:15:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A parameter-free algorithm for group-conditional online conformal prediction that achieves optimal coverage guarantees without learning-rate tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31547","ref_index":76,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling","primary_cat":"cs.LG","submitted_at":"2026-05-29T17:04:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Exposes a dynamic-probabilistic consistency gap in chaotic dynamical systems reconstruction and introduces the KAFFEE differentiable extended Kalman filter training framework to address it.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31371","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:41:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SoftSignum replaces hard sign with soft-sign in optimizers via temperature control and quantile scheduling, extends to SoftMuon, provides a convergence proof for stochastic non-convex settings, and reports better performance than sign-based methods and AdamW on deep learning tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31231","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A holomorphic neural network framework for 3D boundary value problems governed by harmonic potentials","primary_cat":"math.NA","submitted_at":"2026-05-29T12:35:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Holomorphic neural networks enforce exact satisfaction of harmonic PDEs for 3D Laplace and elasticity problems using Whittaker representations and boundary-only training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31027","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs","primary_cat":"cs.LG","submitted_at":"2026-05-29T08:58:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MS-SFNN builds PDE solutions from element-wise products of outputs from d independent fixed-random-weight subnetworks with tunable scaling and cosine activations, then solves coefficients by least squares, claiming superior accuracy on high-frequency problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07599","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression","primary_cat":"cs.LG","submitted_at":"2026-05-29T07:38:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DiffOR reformulates ordinal regression as continuous generative modeling using diffusion models with dual-decoupling to capture soft semantic transitions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00147","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:06:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RAFT improves domain accuracy by 23.2% over standard SFT while recovering 18.2% and 10.2% relative performance on MS-Bench and IFEval through refined supervision and trajectory-preserving distillation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30677","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents","primary_cat":"cs.CR","submitted_at":"2026-05-29T00:13:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"This work examines prompt injection vulnerabilities in agentic software reverse engineering AI systems and tests detection, obfuscation, and defense techniques.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30664","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Structure-Induced Information for Rerooting Levin Tree Search","primary_cat":"cs.AI","submitted_at":"2026-05-28T23:51:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Three rerooter designs (clustering-based, heuristic-based, hybrid) for √LTS enable scalable search in complex single-agent environments where explicit subgoal methods fail and achieve SOTA online training efficiency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30486","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting","primary_cat":"cs.LG","submitted_at":"2026-05-28T19:05:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GC-MoE improves MAE on four traffic forecasting benchmarks by routing nodes to combinations of frozen spatio-temporal GNN experts via a graph-conditioned lightweight router, training only ~17K parameters atop 1.5M frozen weights.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30272","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"IGA-ODIL: Optimizing DIscretre robust Loss with Isogeometric Analysis to solve forward and inverse problems faster using machine learning tools","primary_cat":"math.NA","submitted_at":"2026-05-28T17:30:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"IGA-ODIL replaces neural-network parameterizations in PINNs with B-spline bases to obtain sparse Jacobians and fast Gauss-Newton optimization of robust residual losses for PDEs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30220","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TriSearch: Learning to Optimize Triangulations via Bistellar Flips","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:54:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TriSearch is an RL framework that optimizes triangulations of polytopes using bistellar flips with a circuit-supported subtriangulation action representation, generalizing zero-shot to larger instances and outperforming prior samplers in 3D and 4D.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30126","ref_index":56,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:57:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PARCEL is a new visual tokenization architecture combining pool-anchored resampling with conditioned elastic queries to enhance performance-efficiency tradeoffs in LVLMs over prior matryoshka methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30112","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Striding Across Reynolds Numbers: Representation Geometry in Neural PDE Generalisation","primary_cat":"cs.LG","submitted_at":"2026-05-28T15:49:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ConvAE-Relay retrieval via source-trained autoencoder latent matching achieves 38.34+/-0.07% relative L2 error on 10x Re shift using only source database, with U-Net at 34.72% and matching quality identified as dominant factor.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29952","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:58:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A multi-horizon graph neural network emulator jointly predicts state increments for ice thickness and velocities at several lead times and shows higher long-range accuracy and stability than autoregressive or direct baselines on Pine Island Glacier simulations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29849","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BuilDyn: Excitation-Driven Data Generation for Building Thermal Dynamics Modeling and Control","primary_cat":"eess.SY","submitted_at":"2026-05-28T12:30:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"BuilDyn supplies customizable excitation strategies and sampling tools to produce control-oriented datasets for machine learning models of building thermal dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29812","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language","primary_cat":"cs.CV","submitted_at":"2026-05-28T11:57:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"OpenVMR uses normalizing flow to detect out-of-distribution queries and performs moment retrieval only on in-distribution queries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29739","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Inverse generalised spin models of answers to questionnaires","primary_cat":"physics.data-an","submitted_at":"2026-05-28T10:33:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Generalized spin models are fitted to ordinal questionnaire responses; the BEG model outperforms others at reproducing distance-to-mean distributions and partially captures multi-modality linked to phase coexistence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29731","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EMAG: Differentiable 4D Gaussian Mixture Splatting for EEG Spatial Super-Resolution","primary_cat":"cs.LG","submitted_at":"2026-05-28T10:26:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EMAG is a differentiable framework representing brain sources as 4D anisotropic Gaussian mixtures to achieve spatial super-resolution of EEG signals from sparse electrodes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29688","ref_index":64,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations","primary_cat":"cs.LG","submitted_at":"2026-05-28T09:51:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TPNet constructs multi-dimensional basis functions via tensor products of subnetwork outputs and solves for coefficients with least-squares to solve PDEs more efficiently than PINNs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29583","ref_index":55,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:28:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BitC-3DGS uses bit-compressed tokenization with a dual-branch decoder to support 128-bit watermark messages in 3DGS while maintaining recovery accuracy and rendering quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29304","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On subspace-constrained preconditioning for randomized iterative methods","primary_cat":"math.NA","submitted_at":"2026-05-28T03:36:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Refines subspace preconditioning for randomized linear solvers via QR-like factorization, enabling implicit use and proving expected linear convergence while reducing to a smaller system with good singular values.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29273","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Theoretical and Experimental Study of a Novel Adaptive Learning Algorithm","primary_cat":"cs.LG","submitted_at":"2026-05-28T02:48:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Introduces C-Adam optimizer variant with claimed convergence proof and real-life numerical experiments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29232","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On the Practice of Scaling Search Conversion Rate Prediction","primary_cat":"cs.IR","submitted_at":"2026-05-28T01:48:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Empirical scaling of backbone, embeddings, and data shows largely independent additive gains, enabling a deployed model with 2.5x data and 8x compute that delivers +2.6% CVR improvement with minimal latency change.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29144","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning and Adaptation in Wire Arc Additive Manufacturing Bead Geometry Control","primary_cat":"cs.RO","submitted_at":"2026-05-27T22:15:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"RNN predictive control with layer-wise adaptation improves bead height and width consistency in WAAM experiments over constant-input and static-model baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29109","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"First steps towards gauge-independent vortex identification through machine learning","primary_cat":"hep-lat","submitted_at":"2026-05-27T21:17:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A neural network trained on 2D SU(2) lattices with inserted thin Z2 vortices, after random gauge transformations, noise, and cooling, can locate center vortices at moderate visibility levels and scales via tiling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29013","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Local Observability and Moving Horizon Estimation-based Training of Feedforward Neural Networks","primary_cat":"eess.SY","submitted_at":"2026-05-27T19:10:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Develops MHE-based training for ReLU FNNs via local observability of the weight dynamics and persistently exciting input design, with convergence guarantees for two-layer cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28812","ref_index":47,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation","primary_cat":"cs.RO","submitted_at":"2026-05-27T17:59:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoP tactile representation with differentiable calibration enables zero-shot sim-to-real transfer and outperforms binary and raw-taxel baselines on peg-in-hole insertion and ball balancing with a multi-fingered hand.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28767","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:23:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Develops H-consistent surrogate losses for generalized metrics in multi-label classification that decompose exactly in O(l) time and introduces the MMO family of algorithms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28762","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples","primary_cat":"math.ST","submitted_at":"2026-05-27T17:21:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DNN-assisted doubly robust estimators for finite population means from combined probability and nonprobability samples, with claimed consistency under regularity conditions and simulation validation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28757","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Approximate Solutions to Multiparametric Generalized Nash Equilibrium Problems","primary_cat":"math.OC","submitted_at":"2026-05-27T17:18:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A learning approach trains neural networks to approximate solutions of multiparametric GNEPs using NI gap loss with value surrogates, achieving large speedups and providing new existence conditions for continuous selections.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28594","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method","primary_cat":"cond-mat.stat-mech","submitted_at":"2026-05-27T15:13:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An improved PULSE generative model samples and evaluates the partition function to reproduce thermodynamic averages on the 2D Ising model more efficiently than standard Monte Carlo.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28531","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Stabilizing distribution-free probabilistic forecasts","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:25:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Neural network-parameterized regression splines enable joint optimization of forecast quality and stability in distribution-free probabilistic time series models by penalizing dissimilarities from forecast updates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":100,"offset":0}}