{"total":2073,"items":[{"citing_arxiv_id":"2607.02486","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:52:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GeoMix achieves new state-of-the-art results in descriptor-free 2D-3D matching by adding directional embeddings, learnable global context nodes, and multi-detector training, cutting rotation and translation errors by up to 90% on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02402","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Show Me Examples: Inferring Visual Concepts from Image Sets","primary_cat":"cs.CV","submitted_at":"2026-07-02T16:35:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces VICIS task and training framework for inferring visual concepts from image sets, with experiments showing better accuracy, diversity, and generalization than standard VLMs on synthetic and ImageNet data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02363","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates","primary_cat":"quant-ph","submitted_at":"2026-07-02T16:06:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces bounded old-state modulation via tanh gate to stabilize self-modulating QFWPs, with evaluations showing reduced divergence and improved robustness on quantum dynamics and SMS tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02292","ref_index":126,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective","primary_cat":"cs.LG","submitted_at":"2026-07-02T15:09:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02219","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Differentiable inverse design of short-range order in high-entropy alloys: from target sro to target property","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-07-02T14:25:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A differentiable pipeline uses continuous atom occupancy and gradient descent plus a neural network to optimize short-range order in multi-element alloys directly for target stiffness properties.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02194","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:03:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DSGNAR optimization framework for PINNs reaches relative L2 errors of 3e-16 in double precision and improves prior results by 5-8 orders of magnitude on Burgers' and high-dimensional Poisson problems while remaining faster.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02034","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","primary_cat":"cs.CV","submitted_at":"2026-07-02T11:01:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ComplexMimic applies a dual-flow imitation and interaction expert strategy plus difficulty-aware distillation to enable HSI mimicry in complex scenes and reports outperformance on three benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02015","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Mirror Illusion Art","primary_cat":"cs.CV","submitted_at":"2026-07-02T10:47:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AutoMIA is an automated pipeline for inverse design of 3D mirror illusion objects that jointly optimizes shape and color using four stabilization mechanisms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01943","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Hybrid quantum-classical neural network for sentiment analysis","primary_cat":"cs.LG","submitted_at":"2026-07-02T09:34:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Hybrid quantum-classical networks match classical accuracy on tweet sentiment analysis and raise spam-class accuracy from 66% to 81% under transfer learning to SMS messages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01918","ref_index":81,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis","primary_cat":"cs.LG","submitted_at":"2026-07-02T09:16:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01721","ref_index":90,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning","primary_cat":"cs.RO","submitted_at":"2026-07-02T05:20:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"CoRe combines VLM-designed formal rewards with VLM-labeled residual rewards to produce preference-aligned policies on robotic manipulation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01698","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-07-02T04:41:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SIG frequency scheduler and sphere-constrained Gaussians enable more efficient and higher-quality 3D Gaussian Splatting for large-scale scenes by synchronizing supervision with representation frequencies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01678","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication","primary_cat":"cs.LG","submitted_at":"2026-07-02T04:10:42+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SCAPE enables 90-99% sparse gradient communication in sharded Adam-style LLM training by deriving masks from first-moment statistics, achieving up to 43.3% faster pre-training on Llama-500M with no loss in validation loss or downstream accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01608","ref_index":88,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Structured Factorization Approaches for Quantum State Tomography","primary_cat":"quant-ph","submitted_at":"2026-07-02T02:23:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A unified structured factorization framework for quantum state tomography that parametrizes the density matrix as FF^dagger, supports multiple priors, provides sample complexity bounds, and introduces projected gradient descent and power-method algorithms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01552","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Symbolic Discovery of Iterative Algorithms: A Continuous Latent Space Bayesian Optimization Framework","primary_cat":"math.OC","submitted_at":"2026-07-02T00:20:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A VAE-plus-Bayesian-optimization framework discovers new symbolic iterative optimization algorithms without assuming update function forms and faster than prior mathematical programming methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01171","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Decision-Aware Training for Sample-Based Generative Models","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:02:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Augments the energy score objective for sample-based generative models with a differentiable decision loss that is itself a proper scoring rule, yielding targeted improvements on cost-sensitive regions in synthetic and real tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01128","ref_index":55,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems","primary_cat":"cs.LG","submitted_at":"2026-07-01T16:14:22+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"GAIA introduces a geometry-adaptive integral autoencoder that unifies forward, boundary-value, and inverse PDE operator learning on arbitrary domains via geometry tokens and cross-attention.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01032","ref_index":213,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Point spread function wavefront recovery from in-focus stellar observations","primary_cat":"astro-ph.IM","submitted_at":"2026-07-01T15:00:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"WaveDiff with wavefront feature projection recovers WFE from noisy undersampled in-focus observations at ~3% error, a tenfold improvement over the prior version.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00987","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:22:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AVSR-Diff uses a decoupled diffusion framework with TGFR and SAFR modules to deliver temporally consistent arbitrary-scale video super-resolution that outperforms fixed-scale and arbitrary-scale baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00733","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data","primary_cat":"cs.LG","submitted_at":"2026-07-01T10:17:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AgentODE uses LLMs to discover ODE structures and infer parameter distributions from aggregate data, recovering consistent structures on benchmarks and RDEB clinical data with 231 observations from 46 patients.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00720","ref_index":49,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning","primary_cat":"cs.LG","submitted_at":"2026-07-01T10:08:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Active learning with masked reconstruction and minimax training raises AUC by 12.39% across 28 test cases on four multivariate datasets and seven unsupervised backbones.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00603","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment","primary_cat":"cs.LG","submitted_at":"2026-07-01T08:29:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A descent-free method recovers the singularity order k of dead directions in neural networks from the directional-Fisher rate, classifies them, and assembles global learning coefficients matching closed forms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00595","ref_index":14,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-07-01T08:18:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"GADA corrects spatial misalignments in warped images for Gaussian Splatting via iterative deformable offsets and confidence-weighted fusion, yielding higher quality and 2.13x faster FPS than prior warping methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00500","ref_index":54,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Closed-loop coupling of personalised and foundation models for real-time treatment guidance with MRI","primary_cat":"physics.med-ph","submitted_at":"2026-07-01T06:32:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Closed-loop coupling of personalised temporal prediction and foundation model segmentation improves anatomical prediction and reduces dosimetric error for 400 ms horizons in MRI-guided radiotherapy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00416","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble","primary_cat":"cs.CV","submitted_at":"2026-07-01T04:17:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"DroneIQA-VLE ensembles SigLIP2 vision encoders and a LoRA-adapted Qwen3.5-9B multimodal LLM to jointly predict global, target, and background quality scores for low-altitude UAV images, placing 2nd in the ICME 2026 Drone-IQA challenge.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00379","ref_index":51,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval","primary_cat":"cs.IR","submitted_at":"2026-07-01T03:23:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"APKH uses prompt-optimized attribute kernel mapping and kernel-smoothed contrastive alignment to improve generalization from seen to unseen categories in data-constrained unsupervised cross-modal hashing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01275","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions","primary_cat":"stat.ML","submitted_at":"2026-06-30T23:05:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"X-VAE uses empirical statistics from a pretrained autoencoder to set a data-adaptive Gaussian prior and introduces a latent scaling factor for controllable generation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00235","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Low-Energy Subspace Overlaps in Many-Body Systems with Measurement-Based and Coherent Quantum Strategies","primary_cat":"quant-ph","submitted_at":"2026-06-30T22:25:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Compares shadow-based CNNs and physics-informed QCNNs for predicting low-energy subspace overlaps in quenched 10-qubit Heisenberg chains, reporting regime-dependent R^2 performance with QCNNs more stable overall.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00228","ref_index":48,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility","primary_cat":"astro-ph.IM","submitted_at":"2026-06-30T22:15:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ORACLE-2 multimodal classifiers raise macro F1 from 0.52-0.66 (light-curve only) to 0.73 on ZTF Bright Transient Survey data and reach 0.88 on simulated ELAsTiCC data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00190","ref_index":50,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Play Like Champions: Counterfactual Feedback Generation in Latent Space","primary_cat":"cs.LG","submitted_at":"2026-06-30T21:15:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A guided VAE trained on pro StarCraft replays enables four latent-space traversal strategies to produce counterfactual improvement trajectories for amateur players.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00090","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition","primary_cat":"cs.CV","submitted_at":"2026-06-30T19:33:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DAPR is a model-agnostic plug-in that rebalances gradient contributions across head and tail classes and applies multi-scale distance search for distributional compactness, improving VPR performance by 18.3% on SF-XL v1 and 6.7% on v2.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31988","ref_index":60,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Joint inference of weak lensing convergence map and cosmology with diffusion models","primary_cat":"astro-ph.CO","submitted_at":"2026-06-30T17:25:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31609","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation","primary_cat":"cs.CV","submitted_at":"2026-06-30T12:57:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-view radar segmentation approach with hypergraphs for structural dependencies and UOT for view alignment reports mIoU gains of 1.7-2.3 points on CARRADA and RADIal benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31517","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing","primary_cat":"cs.IR","submitted_at":"2026-06-30T11:30:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"GNAH transfers semantic structure from vision-language models into compact binary codes using prototype-anchored global alignment and contrastive stochastic neighborhood alignment for data-efficient unsupervised cross-modal hashing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31363","ref_index":57,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","primary_cat":"cs.CV","submitted_at":"2026-06-30T08:57:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LA-SR extracts real LR patches from depth-varying regions in single images and uses vision-language models with linguistic content and quality losses for unpaired super-resolution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31268","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TDGT: A Tabular Data Generation Toolkit supporting adaptive GPU-accelerated Bayesian mixture models, diffusion-based models, and latent-space generative modeling","primary_cat":"cs.LG","submitted_at":"2026-06-30T07:42:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TDGT toolkit introduces ABMS for adaptive synthetic tabular data generation with multi-metric fidelity assessment and a web interface.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31208","ref_index":87,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Probing Memorization of Tabular In-Context Learning","primary_cat":"cs.LG","submitted_at":"2026-06-30T06:40:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31119","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Visualizing High-Dimensional Graph Embeddings via Informed Multi-View Projections","primary_cat":"cs.LG","submitted_at":"2026-06-30T04:28:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"High-dimensional graph embeddings are projected to 2D views optimized for aesthetic metrics using a differentiable edge-crossing surrogate, outperforming standard layouts in tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31088","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","primary_cat":"cs.CV","submitted_at":"2026-06-30T03:27:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"InterTalk is a motion-based real-time framework for flexible multi-round multi-person conversational talking face generation using motion feedback, iterative strategies, and facial component disentanglement, supported by a new dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30935","ref_index":50,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints","primary_cat":"eess.SY","submitted_at":"2026-06-29T21:38:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"ShardNet enforces non-convex polyhedral safety constraints in neural controllers by construction via a differentiable projection layer, achieving 100% verified safety and over 3x larger safe sets than prior methods on double integrator benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30889","ref_index":81,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Dynamic Prediction of Alternating Recurrent Events via Neural Network","primary_cat":"stat.ML","submitted_at":"2026-06-29T20:24:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents a neural network model with IPW pseudo-observations for dynamic prediction of alternating recurrent events, with simulation and medical resident mood application results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30861","ref_index":55,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields","primary_cat":"cs.GR","submitted_at":"2026-06-29T19:47:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proof-of-concept for editable physically-based reflections in raytraced 3D Gaussian radiance fields via diffuse/specular buffer separation, path tracing, and specialized training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30813","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","primary_cat":"cs.LG","submitted_at":"2026-06-29T18:37:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Gradient Smoothing applies depth-wise smoothing to optimizer updates from base methods like Adam, yielding consistent gains in optimization and generalization on language, RL, diffusion, and vision tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30807","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations","primary_cat":"cs.RO","submitted_at":"2026-06-29T18:32:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derail adversarial perturbations hijack the scoring head in generative E2E driving planners, flipping safe to unsafe trajectory selection with 39-80% score drops and up to 50% collision rates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30773","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Diffusion-warm sampling of the XY model enables fast thermalization at scale","primary_cat":"quant-ph","submitted_at":"2026-06-29T18:06:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A temperature-conditioned diffusion model trained on small XY lattices produces accurate larger-lattice samples and cuts MCMC thermalization time by roughly 10x.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"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":"2606.30338","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Sequential Fairness Auditing with Limited Output Access","primary_cat":"cs.AI","submitted_at":"2026-06-29T14:17:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper introduces a sequential generalized likelihood-ratio test framework for auditing Statistical Parity and Equal Opportunity fairness metrics under limited model query access.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30326","ref_index":57,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Construction of Nuclear Covariant Energy Density Functional from A Physics-Guaranteed Neural Network Approach","primary_cat":"nucl-th","submitted_at":"2026-06-29T14:09:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A physics-guaranteed neural network constructs a covariant nuclear energy density functional, improving binding energy accuracy from 644 keV to 86 keV in known regions and achieving ~5 MeV accuracy on extrapolations up to 30 steps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}