{"total":17,"items":[{"citing_arxiv_id":"2607.01372","ref_index":83,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AI-enabled gravitational-waves searches for binary neutron stars at optimal sensitivity","primary_cat":"astro-ph.HE","submitted_at":"2026-07-01T18:34:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Aframe neural network achieves matched-filter sensitivity for binary neutron star GW searches at lower computational cost using heterodyning and a single GPU.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17045","ref_index":52,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Compact Spin-Charge Separated Neural Quantum States for Valence-Bond States","primary_cat":"cond-mat.str-el","submitted_at":"2026-06-15T17:57:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A compact NQS architecture for VBS and doped sVBS states reaches high fidelity with fewer parameters than standard baselines by using solvable-point-guided designs and explicit spin-hole sector separation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10669","ref_index":43,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"In Defense of Information Leakage in Concept-based Models","primary_cat":"cs.LG","submitted_at":"2026-06-09T10:19:41+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29547","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:00:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"S-Adam modulates updates via an LGI-based damping term and proves almost-sure convergence to Clarke stationary points at O(1/sqrt(T)) while reporting accuracy gains on CIFAR-100 and TinyImageNet.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20250","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Physics-informed convolutional neural networks for fluid flow through porous media","primary_cat":"cs.LG","submitted_at":"2026-05-18T08:02:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A physics-informed CNN predicts pore-scale velocity fields from geometry and serves as a warm-start to accelerate Lattice-Boltzmann solvers in over 90% of tested cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09022","ref_index":52,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Inferring identified hadron production in $pp$ collisions with physics-informed machine learning at the LHC","primary_cat":"hep-ph","submitted_at":"2026-05-09T16:02:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A physics-informed neural network infers pT spectra of pi, K, p, Lambda, and Ks in unmeasured rapidity regions from PYTHIA8 pp collisions at 13.6 TeV, achieving 1.5-5.83% yield uncertainties while reproducing yield ratios and freeze-out parameters.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[48] S. Acharyaet al.(ALICE Collaboration), Phys. Rev. C 99, 024906 (2019). [49] B. B. Abelevet al.(ALICE Collaboration), Phys. Lett. B727, 371 (2013). [50] P. Braun-Munzinger, J. Stachel, J. P. Wessels and N. Xu, Phys. Lett. B344, 43 (1995). [51] P. Huovinen, P. F. Kolb, U. W. Heinz, P. V. Ruuskanen and S. A. Voloshin, Phys. Lett. B503, 58 (2001). [52] S. Acharyaet al.(ALICE Collaboration), Eur. Phys. J. C84, 813 (2024). [53] A. Ortiz, G. Pai' c and E. Cuautle, Nucl. Phys. A941, 78 (2015). [54] I. C. Arseneet al.(BRAHMS Collaboration), Phys. Rev. C94, 014907 (2016). [55] Z. Tang, L. Yi, L. Ruan, M. Shao, H. Chen, C. Li, B. Mo- hanty, P. Sorensen, A. Tang and Z. Xu, Chin. Phys. Lett. 30, 031201 (2013)."},{"citing_arxiv_id":"2605.06678","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","primary_cat":"cs.LG","submitted_at":"2026-04-22T08:30:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A conditional Wasserstein GAN generates plausible future SWI drought trajectories for French insurance risk management under climate change.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19625","ref_index":155,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Coherent-State Propagation: A Computational Framework for Simulating Bosonic Quantum Systems","primary_cat":"quant-ph","submitted_at":"2026-04-21T16:13:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Coherent-state propagation enables quasi-polynomial classical simulation of bosonic circuits with logarithmically many Kerr gates at exponentially small trace-distance error, with polynomial runtime in the weak-nonlinearity regime.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08661","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States","primary_cat":"quant-ph","submitted_at":"2026-04-09T18:00:04+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dilated RNN wave functions induce power-law correlations for the critical 1D transverse-field Ising model and the Cluster state, unlike the exponential decay of conventional RNN ansatze.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and two-point correlation functions, which are presented and discussed in the following subsections. More details about our hyperparameters are found in Appendix A. A. 1D T ransverse-Field Ising Model To demonstrate the advantage of the dilated architec- ture, we use the 1D Transverse-field Ferromagnetic Ising Model (TFIM) as a testbed for probing long-range cor- relations at the critical point [45, 46]. Its Hamiltonian is 5 100 101 r 10−3 10−2 10−1 C(r) (a) l = 1 l = 2 l = 3 l = 4 l = 5 l = 6 l = 7 1 2 3 4 5 6 7 l 0.3 0.4 0.5 0.6 0.7 η (b) η = 0.25 η R2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 R2 Figure 3. (a) A plot of the connected two-point correlation functionC(r) as a function of distancercomputed by dilated RNNs for different numbers of layers using the 1D periodic"},{"citing_arxiv_id":"2604.16334","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Preventing overfitting in deep learning using differential privacy","primary_cat":"cs.LG","submitted_at":"2026-03-12T22:40:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Differential privacy techniques can help prevent overfitting and improve generalization in deep neural networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2404.03099","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks","primary_cat":"cs.LG","submitted_at":"2024-04-03T22:42:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NEON provides uncertainty-aware operator learning for composite Bayesian optimization in function spaces using a single network, achieving claimed SOTA with orders of magnitude fewer parameters than ensembles.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2204.02311","ref_index":108,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PaLM: Scaling Language Modeling with Pathways","primary_cat":"cs.CL","submitted_at":"2022-04-05T16:11:45+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PaLM 540B demonstrates continued scaling benefits by setting new few-shot SOTA results on hundreds of benchmarks and outperforming humans on BIG-bench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2003.00295","ref_index":192,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Adaptive Federated Optimization","primary_cat":"cs.LG","submitted_at":"2020-02-29T16:37:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.06286","ref_index":208,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Autoencoding sensory substitution","primary_cat":"q-bio.NC","submitted_at":"2019-07-14T21:58:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Deep recurrent autoencoders convert images to shortened audio signals that incorporate hearing models, enabling above-chance hand posture discrimination and object reaching after a few hours of training instead of months.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.02908","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On Inductive Biases in Deep Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2019-07-05T16:14:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Adaptive replacements for domain-specific components in deep RL agents can yield better learning on new tasks without additional tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.10198","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multimodal and Multi-view Models for Emotion Recognition","primary_cat":"cs.CL","submitted_at":"2019-06-24T19:47:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Multimodal training with attention and contrastive multi-view learning improves both combined and acoustic-only emotion recognition on IEMOCAP over prior acoustic baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1609.08144","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:59:55+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GNMT deploys 8-layer LSTMs with attention, wordpieces, low-precision inference, and coverage-penalized beam search to match state-of-the-art on WMT'14 En-Fr and En-De while cutting translation errors by 60% in human evaluations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"where AttentionFunction in our implementation is a feed forward network with one hidden layer. 3.1 Residual Connections As mentioned above, deep stacked LSTMs often give better accuracy over shallower models. However, simply stacking more layers of LSTM works only to a certain number of layers, beyond which the network becomes 4 too slow and difficult to train, likely due to exploding and vanishing gradient problems [33, 22]. In our experience with large-scale translation tasks, simple stacked LSTM layers work well up to 4 layers, barely with 6 layers, and very poorly beyond 8 layers. Figure 2: The difference between normal stacked LSTM and our stacked LSTM with residual connections. On the left: simple stacked LSTM layers [41]. On the right: our implementation of stacked LSTM layers"}],"limit":50,"offset":0}