| 1 | Communication-Efficient Distributed Learning with Differential Privacy | ArXiv ML (cs.LG) | |
| 2 | ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models | ArXiv ML (cs.LG) | |
| 3 | VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation | ArXiv ML (cs.LG) | |
| 4 | WGFINNs: Weak formulation-based GENERIC formalism informed neural networks’ | ArXiv ML (cs.LG) | |
| 5 | Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens | ArXiv ML (cs.LG) | |
| 6 | Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems | ArXiv ML (cs.LG) | |
| 7 | Analytic Drift Resister for Non-Exemplar Continual Graph Learning | ArXiv ML (cs.LG) | |
| 8 | AXELRAM: Quantize Once, Never Dequantize | ArXiv ML (cs.LG) | |
| 9 | Conditional Sampling via Wasserstein Autoencoders and Triangular Transport | ArXiv ML (cs.LG) | |
| 10 | Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training | ArXiv ML (cs.LG) | |
| 11 | Generalization Limits of Reinforcement Learning Alignment | ArXiv ML (cs.LG) | |
| 12 | Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability | ArXiv ML (cs.LG) | |
| 13 | Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration | ArXiv ML (cs.LG) | |
| 14 | A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation | ArXiv ML (cs.LG) | |
| 15 | Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network | ArXiv ML (cs.LG) | |
| 16 | Finding Belief Geometries with Sparse Autoencoders | ArXiv ML (cs.LG) | |
| 17 | Beyond Semantic Manipulation: Token-Space Attacks on Reward Models | ArXiv ML (cs.LG) | |
| 18 | Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism | ArXiv ML (cs.LG) | |
| 19 | LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks | ArXiv ML (cs.LG) | |
| 20 | FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving | ArXiv ML (cs.LG) | |
| 21 | Generative Frontiers: Why Evaluation Matters for Diffusion Language Models | ArXiv ML (cs.LG) | |
| 22 | Understanding Latent Diffusability via Fisher Geometry | ArXiv ML (cs.LG) | |
| 23 | STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation | ArXiv ML (cs.LG) | |
| 24 | Towards Realistic Class-Incremental Learning with Free-Flow Increments | ArXiv ML (cs.LG) | |
| 25 | Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs | ArXiv ML (cs.LG) | |
| 26 | Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guarantees | ArXiv ML (cs.LG) | |
| 27 | Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting | ArXiv ML (cs.LG) | |
| 28 | Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation | ArXiv ML (cs.LG) | |
| 29 | Efficient Logistic Regression with Mixture of Sigmoids | ArXiv ML (cs.LG) | |
| 30 | Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms | ArXiv ML (cs.LG) | |
| 31 | Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in Female Mouse White Adipose Tissue After 37 Days of Microgravity: First AI/ML Analysis of NASA OSD-970 | ArXiv ML (cs.LG) | |
| 32 | Mitigating Reward Hacking in RLHF via Advantage Sign Robustness | ArXiv ML (cs.LG) | |
| 33 | FedSQ: Optimized Weight Averaging via Fixed Gating | ArXiv ML (cs.LG) | |
| 34 | Generating DDPM-based Samples from Tilted Distributions | ArXiv ML (cs.LG) | |
| 35 | Co-Evolution of Policy and Internal Reward for Language Agents | ArXiv ML (cs.LG) | |
| 36 | Self-Distilled RLVR | ArXiv ML (cs.LG) | |
| 37 | HyperFitS — Hypernetwork Fitting Spectra for metabolic quantification of 1H MR spectroscopic imaging | ArXiv ML (cs.LG) | |
| 38 | DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation | ArXiv ML (cs.LG) | |
| 39 | Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models | ArXiv ML (cs.LG) | |
| 40 | PRISM: LLM-Guided Semantic Clustering for High-Precision Topics | ArXiv ML (cs.LG) | |
| 41 | Reflective Context Learning: Studying the Optimization Primitives of Context Space | ArXiv ML (cs.LG) | |
| 42 | Gradient Boosting within a Single Attention Layer | ArXiv ML (cs.LG) | |
| 43 | Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis | ArXiv ML (cs.LG) | |
| 44 | Hierarchical Planning with Latent World Models | ArXiv ML (cs.LG) | |
| 45 | Enhancing Robustness of Federated Learning via Server Learning | ArXiv ML (cs.LG) | |
| 46 | MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites | ArXiv ML (cs.LG) | |
| 47 | Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations | ArXiv ML (cs.LG) | |
| 48 | TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning | ArXiv ML (cs.LG) | |
| 49 | Backdoor Attacks on Decentralised Post-Training | ArXiv ML (cs.LG) | |
| 50 | Photonic convolutional neural network with pre-trained in-situ training | ArXiv ML (cs.LG) | |
| 51 | PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction | ArXiv ML (cs.LG) | |
| 52 | Guideline2Graph: Profile-Aware Multimodal Parsing for Executable Clinical Decision Graphs | ArXiv ML (cs.LG) | |
| 53 | Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models | ArXiv ML (cs.LG) | |
| 54 | Optimal Projection-Free Adaptive SGD for Matrix Optimization | ArXiv ML (cs.LG) | |
| 55 | Reinforcement Learning from Human Feedback: A Statistical Perspective | ArXiv ML (cs.LG) | |
| 56 | Neural posterior estimation for scalable and accurate inverse parameter inference in Li-ion batteries | ArXiv ML (cs.LG) | |
| 57 | AQVolt26: High-Temperature r2SCAN Halide Dataset for Universal ML Potentials and Solid-State Batteries | ArXiv ML (cs.LG) | |
| 58 | Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization | ArXiv ML (cs.LG) | |
| 59 | Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions? | ArXiv ML (cs.LG) | |
| 60 | Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization | ArXiv ML (cs.LG) | |
| 61 | Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation | ArXiv ML (cs.LG) | |
| 62 | Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding | ArXiv ML (cs.LG) | |
| 63 | Financial Anomaly Detection for the Canadian Market | ArXiv ML (cs.LG) | |
| 64 | Robust Learning with Optimal Error | ArXiv ML (cs.LG) | |
| 65 | WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models | ArXiv ML (cs.LG) | |
| 66 | Understanding the Effects of Safety Unalignment on Large Language Models | ArXiv ML (cs.LG) | |
| 67 | Learning interacting particle systems from unlabeled data | ArXiv ML (cs.LG) | |
| 68 | Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transport | ArXiv ML (cs.LG) | |
| 69 | AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models | ArXiv ML (cs.LG) | |
| 70 | Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge | ArXiv ML (cs.LG) | |
| 71 | Transfer Learning for Meta-analysis Under Covariate Shift | ArXiv ML (cs.LG) | |
| 72 | Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy | ArXiv ML (cs.LG) | |
| 73 | MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications | ArXiv ML (cs.LG) | |
| 74 | State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference | ArXiv ML (cs.LG) | |
| 75 | Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces | ArXiv ML (cs.LG) | |
| 76 | Lipschitz bounds for integral kernels | ArXiv ML (cs.LG) | |
| 77 | Rethinking Forward Processes for Score-Based Data Assimilation in High Dimensions | ArXiv ML (cs.LG) | |
| 78 | Toward an Artificial General Teacher: Procedural Geometry Data Generation and Visual Grounding with Vision-Language Models | ArXiv ML (cs.LG) | |
| 79 | Split and Conquer Partial Deepfake Speech | ArXiv ML (cs.LG) | |
| 80 | Scalable Mean-Variance Portfolio Optimization via Subspace Embeddings and GPU-Friendly Nesterov-Accelerated Projected Gradient | ArXiv ML (cs.LG) | |
| 81 | Learning from Synthetic Data via Provenance-Based Input Gradient Guidance | ArXiv ML (cs.LG) | |
| 82 | Inversion-Free Natural Gradient Descent on Riemannian Manifolds | ArXiv ML (cs.LG) | |
| 83 | A semicontinuous relaxation of Saito’s criterion and freeness as angular minimization | ArXiv ML (cs.LG) | |
| 84 | Learning Contractive Integral Operators with Fredholm Integral Neural Operators | ArXiv ML (cs.LG) | |
| 85 | On Data-Driven Koopman Representations of Nonlinear Delay Differential Equations | ArXiv ML (cs.LG) | |
| 86 | SkillRT: Compiling Skills for Efficient Execution Everywhere | ArXiv ML (cs.LG) | |
| 87 | Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization | ArXiv ML (cs.LG) | |
| 88 | The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling | ArXiv ML (cs.LG) | |
| 89 | Learning the Signature of Memorization in Autoregressive Language Models | ArXiv ML (cs.LG) | |
| 90 | PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction | ArXiv ML (cs.LG) | |
| 91 | A Tsetlin Machine-driven Intrusion Detection System for Next-Generation IoMT Security | ArXiv ML (cs.LG) | |
| 92 | Efficient Causal Graph Discovery Using Large Language Models | ArXiv ML (cs.LG) | |
| 93 | Output-Constrained Decision Trees | ArXiv ML (cs.LG) | |
| 94 | Supplementary Materials to Graph Convolutional Branch and Bound | ArXiv ML (cs.LG) | |
| 95 | Amortized Inference of Causal Models via Conditional Fixed-Point Iterations | ArXiv ML (cs.LG) | |
| 96 | Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models | ArXiv ML (cs.LG) | |
| 97 | Zero-shot Concept Bottleneck Models | ArXiv ML (cs.LG) | |
| 98 | A Unified Approach to Analysis and Design of Denoising Markov Models | ArXiv ML (cs.LG) | |
| 99 | Accelerated Learning with Linear Temporal Logic using Differentiable Simulation | ArXiv ML (cs.LG) | |
| 100 | PVD-ONet: A Multi-scale Neural Operator Method for Singularly Perturbed Boundary Layer Problems | ArXiv ML (cs.LG) | |
| 101 | A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems | ArXiv ML (cs.LG) | |
| 102 | Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring | ArXiv ML (cs.LG) | |
| 103 | ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization | ArXiv ML (cs.LG) | |
| 104 | High-probability Convergence Guarantees of Decentralized SGD | ArXiv ML (cs.LG) | |
| 105 | Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions | ArXiv ML (cs.LG) | |
| 106 | f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness | ArXiv ML (cs.LG) | |
| 107 | Diffusion Models as Dataset Distillation Priors | ArXiv ML (cs.LG) | |
| 108 | Towards best practices in low-dimensional semi-supervised latent Bayesian optimization for the design of antimicrobial peptides | ArXiv ML (cs.LG) | |
| 109 | Steering Autoregressive Music Generation with Recursive Feature Machines | ArXiv ML (cs.LG) | |
| 110 | Fast and Robust Simulation-Based Inference With Optimization Monte Carlo | ArXiv ML (cs.LG) | |
| 111 | Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning | ArXiv ML (cs.LG) | |
| 112 | Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins | ArXiv ML (cs.LG) | |
| 113 | Resting Neurons, Active Insights: Robustify Activation Sparsity for Large Language Models | ArXiv ML (cs.LG) | |
| 114 | Community-Based Early-Stage Chronic Kidney Disease Screening using Explainable Machine Learning for Low-Resource Settings | ArXiv ML (cs.LG) | |
| 115 | Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models | ArXiv ML (cs.LG) | |
| 116 | On the Extreme Variance of Certified Local Robustness Across Model Seeds | ArXiv ML (cs.LG) | |
| 117 | Textual Equilibrium Propagation for Deep Compound AI Systems | ArXiv ML (cs.LG) | |
| 118 | Early Classification of Time Series in Non-Stationary Cost Regimes | ArXiv ML (cs.LG) | |
| 119 | ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs | ArXiv ML (cs.LG) | |
| 120 | When RL Meets Adaptive Speculative Training: A Unified Training-Serving System | ArXiv ML (cs.LG) | |
| 121 | Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions | ArXiv ML (cs.LG) | |
| 122 | Equivariant Evidential Deep Learning for Interatomic Potentials | ArXiv ML (cs.LG) | |
| 123 | Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking | ArXiv ML (cs.LG) | |
| 124 | Early-Warning Signals of Grokking via Loss-Landscape Geometry | ArXiv ML (cs.LG) | |
| 125 | The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure | ArXiv ML (cs.LG) | |
| 126 | CeRA: Overcoming the Linear Ceiling of Low-Rank Adaptation via Capacity Expansion | ArXiv ML (cs.LG) | |
| 127 | Learning Physical Operators using Neural Operators | ArXiv ML (cs.LG) | |
| 128 | SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond | ArXiv ML (cs.LG) | |
| 129 | CRISP: Compressed Reasoning via Iterative Self-Policy Distillation | ArXiv ML (cs.LG) | |
| 130 | Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis | ArXiv ML (cs.LG) | |
| 131 | JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction | ArXiv ML (cs.LG) | |
| 132 | Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows | ArXiv ML (cs.LG) | |
| 133 | λ-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks | ArXiv ML (cs.LG) | |
| 134 | ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models | ArXiv ML (cs.LG) | |
| 135 | Temporal Credit Is Free | ArXiv ML (cs.LG) | |
| 136 | The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training | ArXiv ML (cs.LG) | |
| 137 | Transfer learning for nonparametric Bayesian networks | ArXiv ML (cs.LG) | |
| 138 | Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial | ArXiv ML (cs.LG) | |
| 139 | annbatch unlocks terabyte-scale training of biological data in anndata | ArXiv ML (cs.LG) | |
| 140 | ResidualPlanner+: a scalable matrix mechanism for marginals and beyond | ArXiv ML (cs.LG) | |
| 141 | Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators | ArXiv ML (cs.LG) | |
| 142 | Learn then Decide: A Learning Approach for Designing Data Marketplaces | ArXiv ML (cs.LG) | |
| 143 | gen2seg: Generative Models Enable Generalizable Instance Segmentation | ArXiv ML (cs.LG) | |
| 144 | LMask: Learn to Solve Constrained Routing Problems with Lazy Masking | ArXiv ML (cs.LG) | |
| 145 | Are Statistical Methods Obsolete in the Era of Deep Learning? A Study of ODE Inverse Problems | ArXiv ML (cs.LG) | |
| 146 | AI-informed model-analogs for understanding subseasonal-to-seasonal jet stream and North American temperature predictability | ArXiv ML (cs.LG) | |
| 147 | Decoding RWA Tokenized U.S. Treasuries: Functional Dissection and Address Role Inference | ArXiv ML (cs.LG) | |
| 148 | Constrained free energy minimization for the design of thermal states and stabilizer thermodynamic systems | ArXiv ML (cs.LG) | |
| 149 | DRtool: An Interactive Tool for Analyzing High-Dimensional Clusterings | ArXiv ML (cs.LG) | |
| 150 | LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade | ArXiv ML (cs.LG) | |
| 151 | ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation | ArXiv ML (cs.LG) | |
| 152 | Adaptive randomized pivoting and volume sampling | ArXiv ML (cs.LG) | |
| 153 | Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference | ArXiv ML (cs.LG) | |
| 154 | Fast Best-in-Class Regret for Contextual Bandits | ArXiv ML (cs.LG) | |
| 155 | Stability of the Kim—Milman flow map | ArXiv ML (cs.LG) | |
| 156 | Tensor Computation of Euler Characteristic Functions and Transforms | ArXiv ML (cs.LG) | |
| 157 | Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning | ArXiv ML (cs.LG) | |
| 158 | Investigating Test Overfitting on SWE-bench | ArXiv ML (cs.LG) | |
| 159 | Reward-Forcing: Autoregressive Video Generation with Reward Feedback | ArXiv ML (cs.LG) | |
| 160 | Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification | ArXiv ML (cs.LG) | |
| 161 | Fisher-Geometric Diffusion in Stochastic Gradient Descent: Optimal Rates, Oracle Complexity, and Information-Theoretic Limits | ArXiv ML (cs.LG) | |
| 162 | Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models | ArXiv ML (cs.LG) | |
| 163 | Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks | ArXiv ML (cs.LG) | |
| 164 | Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms | ArXiv ML (cs.LG) | |
| 165 | Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers | ArXiv ML (cs.LG) | |
| 166 | Yau’s Affine Normal Descent: Algorithmic Framework and Convergence Analysis | ArXiv ML (cs.LG) | |
| 167 | Functional Natural Policy Gradients | ArXiv ML (cs.LG) | |
| 168 | Multimodal Language Models Cannot Spot Spatial Inconsistencies | ArXiv ML (cs.LG) | |
| 169 | When AI Gets it Wrong: Reliability and Risk in AI-Assisted Medication Decision Systems | ArXiv ML (cs.LG) | |
| 170 | ProdCodeBench: A Production-Derived Benchmark for Evaluating AI Coding Agents | ArXiv ML (cs.LG) | |
| 171 | Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks | ArXiv ML (cs.LG) | |
| 172 | (PAC-)Learning state machines from data streams: A generic strategy and an improved heuristic (Extended version) | ArXiv ML (cs.LG) | |
| 173 | Copilot is ‘for entertainment purposes only,’ according to Microsoft’s terms of use | TechCrunch AI | |
| 174 | Can orbital data centers help justify a massive valuation for SpaceX? | TechCrunch AI | |
| 175 | In Japan, the robot isn’t coming for your job; it’s filling the one nobody wants | TechCrunch AI | |
| 176 | The New York Times drops freelancer whose AI tool copied from an existing book review | The Decoder | |
| 177 | Study maps developer frustration over “AI slop” as a “tragedy of the commons” in software development | The Decoder | |
| 178 | AI offensive cyber capabilities are doubling every six months, safety researchers find | The Decoder | |
| 179 | AI benchmarks systematically ignore how humans disagree, Google study finds | The Decoder | |
| 180 | AI chatbot traffic grows seven times faster than social media but still trails by a factor of four | The Decoder | |
| 181 | Proxy-Pointer RAG: Achieving Vectorless Accuracy at Vector RAG Scale and Cost | Towards Data Science | |
| 182 | A Data Scientist’s Take on the $599 MacBook Neo | Towards Data Science | |
| 183 | Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis | ArXiv CL (cs.CL) | |
| 184 | CIPHER: Conformer-based Inference of Phonemes from High-density EEG | ArXiv CL (cs.CL) | |
| 185 | SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy | ArXiv CL (cs.CL) | |
| 186 | Skeleton-based Coherence Modeling in Narratives | ArXiv CL (cs.CL) | |
| 187 | Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets | ArXiv CL (cs.CL) | |
| 188 | Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting | ArXiv CL (cs.CL) | |
| 189 | PolyJarvis: LLM Agent for Autonomous Polymer MD Simulations | ArXiv CL (cs.CL) | |
| 190 | Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming | ArXiv CL (cs.CL) | |
| 191 | Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation | ArXiv CL (cs.CL) | |
| 192 | Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models | ArXiv CL (cs.CL) | |
| 193 | An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages | ArXiv CL (cs.CL) | |
| 194 | Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training | ArXiv CL (cs.CL) | |
| 195 | Overcoming the “Impracticality” of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework | ArXiv CL (cs.CL) | |
| 196 | Speaking of Language: Reflections on Metalanguage Research in NLP | ArXiv CL (cs.CL) | |
| 197 | Revealing the Learning Dynamics of Long-Context Continual Pre-training | ArXiv CL (cs.CL) | |
| 198 | SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models | ArXiv CL (cs.CL) | |
| 199 | Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems | ArXiv CL (cs.CL) | |
| 200 | Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments | ArXiv CL (cs.CL) | |
| 201 | Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints | ArXiv CL (cs.CL) | |
| 202 | Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts | ArXiv CL (cs.CL) | |
| 203 | Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models | ArXiv CL (cs.CL) | |
| 204 | When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs | ArXiv CL (cs.CL) | |
| 205 | Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks | ArXiv CL (cs.CL) | |
| 206 | Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection | ArXiv CL (cs.CL) | |
| 207 | GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics | ArXiv CL (cs.CL) | |
| 208 | LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction | ArXiv CL (cs.CL) | |
| 209 | One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging | ArXiv CL (cs.CL) | |
| 210 | BioUNER: A Benchmark Dataset for Clinical Urdu Named Entity Recognition | ArXiv CL (cs.CL) | |
| 211 | Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus | ArXiv CL (cs.CL) | |
| 212 | A Multi-head-based architecture for effective morphological tagging in Russian with open dictionary | ArXiv CL (cs.CL) | |
| 213 | How Annotation Trains Annotators: Competence Development in Social Influence Recognition | ArXiv CL (cs.CL) | |
| 214 | LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation | ArXiv CL (cs.CL) | |
| 215 | NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons | ArXiv CL (cs.CL) | |
| 216 | R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning | ArXiv CL (cs.CL) | |
| 217 | JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency | ArXiv CL (cs.CL) | |
| 218 | Querying Structured Data Through Natural Language Using Language Models | ArXiv CL (cs.CL) | |
| 219 | Verbalizing LLMs’ assumptions to explain and control sycophancy | ArXiv CL (cs.CL) | |
| 220 | Multi-Aspect Knowledge Distillation for Language Model with Low-rank Factorization | ArXiv CL (cs.CL) | |
| 221 | Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts | ArXiv CL (cs.CL) | |
| 222 | StoryScope: Investigating idiosyncrasies in AI fiction | ArXiv CL (cs.CL) | |
| 223 | Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation | ArXiv CL (cs.CL) | |
| 224 | Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control | ArXiv CL (cs.CL) | |
| 225 | Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents | ArXiv CL (cs.CL) | |
| 226 | Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation | ArXiv CL (cs.CL) | |
| 227 | Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization | ArXiv CL (cs.CL) | |
| 228 | BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence | ArXiv CL (cs.CL) | |
| 229 | Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment | ArXiv CL (cs.CL) | |
| 230 | Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation | ArXiv CL (cs.CL) | |
| 231 | Internalized Reasoning for Long-Context Visual Document Understanding | ArXiv CL (cs.CL) | |
| 232 | Measuring What Cannot Be Surveyed: LLMs as Instruments for Latent Cognitive Variables in Labor Economics | ArXiv CL (cs.CL) | |
| 233 | VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors | ArXiv CL (cs.CL) | |
| 234 | High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination | ArXiv CL (cs.CL) | |
| 235 | Mitigating LLM biases toward spurious social contexts using direct preference optimization | ArXiv CL (cs.CL) | |
| 236 | IndustryCode: A Benchmark for Industry Code Generation | ArXiv CL (cs.CL) | |
| 237 | EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors | ArXiv CL (cs.CL) | |
| 238 | Analysis of Optimality of Large Language Models on Planning Problems | ArXiv CL (cs.CL) | |
| 239 | Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA | ArXiv CL (cs.CL) | |
| 240 | FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models | ArXiv CL (cs.CL) | |
| 241 | Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference | ArXiv CL (cs.CL) | |
| 242 | Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR | ArXiv CL (cs.CL) | |
| 243 | Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems | ArXiv CL (cs.CL) | |
| 244 | An Independent Safety Evaluation of Kimi K2.5 | ArXiv CL (cs.CL) | |
| 245 | InCoder-32B-Thinking: Industrial Code World Model for Thinking | ArXiv CL (cs.CL) | |
| 246 | BibTeX Citation Hallucinations in Scientific Publishing Agents: Evaluation and Mitigation | ArXiv CL (cs.CL) | |
| 247 | Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling | ArXiv CL (cs.CL) | |
| 248 | Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen! | ArXiv CL (cs.CL) | |
| 249 | Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents | ArXiv CL (cs.CL) | |
| 250 | AutoPCR: Automated Phenotype Concept Recognition by Prompting | ArXiv CL (cs.CL) | |
| 251 | Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents | ArXiv CL (cs.CL) | |
| 252 | VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents | ArXiv CL (cs.CL) | |
| 253 | SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP | ArXiv CL (cs.CL) | |
| 254 | Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior | ArXiv CL (cs.CL) | |
| 255 | Future Policy Approximation for Offline Reinforcement Learning Improves Mathematical Reasoning | ArXiv CL (cs.CL) | |
| 256 | What Is The Political Content in LLMs’ Pre- and Post-Training Data? | ArXiv CL (cs.CL) | |
| 257 | CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints | ArXiv CL (cs.CL) | |
| 258 | Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding | ArXiv CL (cs.CL) | |
| 259 | IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge | ArXiv CL (cs.CL) | |
| 260 | APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay | ArXiv CL (cs.CL) | |
| 261 | Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation | ArXiv CL (cs.CL) | |
| 262 | Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS | ArXiv CL (cs.CL) | |
| 263 | WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis | ArXiv CL (cs.CL) | |
| 264 | StructEval: Benchmarking LLMs’ Capabilities to Generate Structural Outputs | ArXiv CL (cs.CL) | |
| 265 | AutiHero: Engaging Parents in Creating Personalized, Multi-path Social Narratives for Autistic Children | ArXiv CL (cs.CL) | |
| 266 | Glia: A Human-Inspired AI for Automated Systems Design and Optimization | ArXiv CL (cs.CL) | |
| 267 | CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents | ArXiv CL (cs.CL) | |
| 268 | Machine Translation in the Wild: User Reaction to Xiaohongshu’s Built-In Translation Feature | ArXiv CL (cs.CL) | |
| 269 | The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning | ArXiv CL (cs.CL) | |
| 270 | Borderless Long Speech Synthesis | ArXiv CL (cs.CL) | |
| 271 | Terminal Agents Suffice for Enterprise Automation | ArXiv CL (cs.CL) | |
| 272 | OSCAR: Orchestrated Self-verification and Cross-path Refinement | ArXiv CL (cs.CL) | |
| 273 | Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising | ArXiv CV (cs.CV) | |
| 274 | Environment-Aware Channel Prediction for Vehicular Communications: A Multimodal Visual Feature Fusion Framework | ArXiv CV (cs.CV) | |
| 275 | Variational Encoder—Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition | ArXiv CV (cs.CV) | |
| 276 | LumiVideo: An Intelligent Agentic System for Video Color Grading | ArXiv CV (cs.CV) | |
| 277 | From Elevation Maps To Contour Lines: SVM and Decision Trees to Detect Violin Width Reduction | ArXiv CV (cs.CV) | |
| 278 | Street-Legal Physical-World Adversarial Rim for License Plates | ArXiv CV (cs.CV) | |
| 279 | VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation | ArXiv CV (cs.CV) | |
| 280 | Hierarchical, Interpretable, Label-Free Concept Bottleneck Model | ArXiv CV (cs.CV) | |
| 281 | Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI | ArXiv CV (cs.CV) | |
| 282 | Token-Efficient Multimodal Reasoning via Image Prompt Packaging | ArXiv CV (cs.CV) | |
| 283 | Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph | ArXiv CV (cs.CV) | |
| 284 | An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis | ArXiv CV (cs.CV) | |
| 285 | Rapidly deploying on-device eye tracking by distilling visual foundation models | ArXiv CV (cs.CV) | |
| 286 | FusionBERT: Multi-View Image-3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder | ArXiv CV (cs.CV) | |
| 287 | TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction | ArXiv CV (cs.CV) | |
| 288 | Moondream Segmentation: From Words to Masks | ArXiv CV (cs.CV) | |
| 289 | Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signals | ArXiv CV (cs.CV) | |
| 290 | Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis | ArXiv CV (cs.CV) | |
| 291 | Smart Transfer: Leveraging Vision Foundation Model for Rapid Building Damage Mapping with Post-Earthquake VHR Imagery | ArXiv CV (cs.CV) | |
| 292 | Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles | ArXiv CV (cs.CV) | |
| 293 | Drift-Resilient Temporal Priors for Visual Tracking | ArXiv CV (cs.CV) | |
| 294 | Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs | ArXiv CV (cs.CV) | |
| 295 | Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing | ArXiv CV (cs.CV) | |
| 296 | DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning | ArXiv CV (cs.CV) | |
| 297 | XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis | ArXiv CV (cs.CV) | |
| 298 | VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping | ArXiv CV (cs.CV) | |
| 299 | ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving | ArXiv CV (cs.CV) | |
| 300 | THOM: Generating Physically Plausible Hand-Object Meshes From Text | ArXiv CV (cs.CV) | |
| 301 | Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks | ArXiv CV (cs.CV) | |
| 302 | Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation | ArXiv CV (cs.CV) | |
| 303 | DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection | ArXiv CV (cs.CV) | |
| 304 | InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging | ArXiv CV (cs.CV) | |
| 305 | Generalized Small Object DetectionPoint-Prompted Paradigm and Benchmark | ArXiv CV (cs.CV) | |
| 306 | A Unified Perspective on Adversarial Membership Manipulation in Vision Models | ArXiv CV (cs.CV) | |
| 307 | CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization | ArXiv CV (cs.CV) | |
| 308 | LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers | ArXiv CV (cs.CV) | |
| 309 | UNICA: A Unified Neural Framework for Controllable 3D Avatars | ArXiv CV (cs.CV) | |
| 310 | PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis | ArXiv CV (cs.CV) | |
| 311 | CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification | ArXiv CV (cs.CV) | |
| 312 | QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models | ArXiv CV (cs.CV) | |
| 313 | MMPhysVideo: Scaling Physical Plausibility in Video Generation via Joint Multimodal Modeling | ArXiv CV (cs.CV) | |
| 314 | NavCrafter: Exploring 3D Scenes from a Single Image | ArXiv CV (cs.CV) | |
| 315 | STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation | ArXiv CV (cs.CV) | |
| 316 | Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices | ArXiv CV (cs.CV) | |
| 317 | Deformation-based In-Context Learning for Point Cloud Understanding | ArXiv CV (cs.CV) | |
| 318 | Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations | ArXiv CV (cs.CV) | |
| 319 | HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints | ArXiv CV (cs.CV) | |
| 320 | A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos | ArXiv CV (cs.CV) | |
| 321 | HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits | ArXiv CV (cs.CV) | |
| 322 | Token Warping Helps MLLMs Look from Nearby Viewpoints | ArXiv CV (cs.CV) | |
| 323 | SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detection | ArXiv CV (cs.CV) | |
| 324 | Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework | ArXiv CV (cs.CV) | |
| 325 | InstructTable: Improving Table Structure Recognition Through Instructions | ArXiv CV (cs.CV) | |
| 326 | Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision | ArXiv CV (cs.CV) | |
| 327 | Progressive Video Condensation with MLLM Agent for Long-form Video Understanding | ArXiv CV (cs.CV) | |
| 328 | EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment | ArXiv CV (cs.CV) | |
| 329 | RayMamba: Ray-Aligned Serialization for Long-Range 3D Object Detection | ArXiv CV (cs.CV) | |
| 330 | UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting | ArXiv CV (cs.CV) | |
| 331 | SentiAvatar: Towards Expressive and Interactive Digital Humans | ArXiv CV (cs.CV) | |
| 332 | GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes | ArXiv CV (cs.CV) | |
| 333 | BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving | ArXiv CV (cs.CV) | |
| 334 | PolyReal: A Benchmark for Real-World Polymer Science Workflows | ArXiv CV (cs.CV) | |
| 335 | Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection | ArXiv CV (cs.CV) | |
| 336 | MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion | ArXiv CV (cs.CV) | |
| 337 | CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation | ArXiv CV (cs.CV) | |
| 338 | Collaborative Multi-Mode Pruning for Vision-Language Models | ArXiv CV (cs.CV) | |
| 339 | Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection | ArXiv CV (cs.CV) | |
| 340 | Exploring Motion-Language Alignment for Text-driven Motion Generation | ArXiv CV (cs.CV) | |
| 341 | Effect of Input Resolution on Retinal Vessel Segmentation Performance: An Empirical Study Across Five Datasets | ArXiv CV (cs.CV) | |
| 342 | Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation | ArXiv CV (cs.CV) | |
| 343 | Rendering Multi-Human and Multi-Object with 3D Gaussian Splatting | ArXiv CV (cs.CV) | |
| 344 | Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition | ArXiv CV (cs.CV) | |
| 345 | GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model | ArXiv CV (cs.CV) | |
| 346 | QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection | ArXiv CV (cs.CV) | |
| 347 | STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models | ArXiv CV (cs.CV) | |
| 348 | Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks | ArXiv CV (cs.CV) | |
| 349 | Gram-MMD: A Texture-Aware Metric for Image Realism Assessment | ArXiv CV (cs.CV) | |
| 350 | SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction | ArXiv CV (cs.CV) | |
| 351 | MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs | ArXiv CV (cs.CV) | |
| 352 | A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification | ArXiv CV (cs.CV) | |
| 353 | Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning | ArXiv CV (cs.CV) | |
| 354 | Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models | ArXiv CV (cs.CV) | |
| 355 | Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation | ArXiv CV (cs.CV) | |
| 356 | SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization | ArXiv CV (cs.CV) | |
| 357 | SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation | ArXiv CV (cs.CV) | |
| 358 | CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator | ArXiv CV (cs.CV) | |
| 359 | EffiMiniVLM: A Compact Dual-Encoder Regression Framework | ArXiv CV (cs.CV) | |
| 360 | SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection | ArXiv CV (cs.CV) | |
| 361 | The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report | ArXiv CV (cs.CV) | |
| 362 | ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow | ArXiv CV (cs.CV) | |
| 363 | VOSR: A Vision-Only Generative Model for Image Super-Resolution | ArXiv CV (cs.CV) | |
| 364 | CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning | ArXiv CV (cs.CV) | |
| 365 | Managing Diabetic Retinopathy with Deep Learning: A Data Centric Overview | ArXiv CV (cs.CV) | |
| 366 | Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It | ArXiv CV (cs.CV) | |
| 367 | Wavelength-multiplexed massively parallel diffractive optical information storage and image projection | ArXiv CV (cs.CV) | |
| 368 | A Rapid Instrument Exchange System for Humanoid Robots in Minimally Invasive Surgery | ArXiv CV (cs.CV) | |
| 369 | V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views | ArXiv CV (cs.CV) | |
| 370 | Task-Guided Prompting for Unified Remote Sensing Image Restoration | ArXiv CV (cs.CV) | |
| 371 | Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation | ArXiv CV (cs.CV) | |
| 372 | ARM: Advantage Reward Modeling for Long-Horizon Manipulation | ArXiv CV (cs.CV) | |
| 373 | ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality | ArXiv CV (cs.CV) | |
| 374 | Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model | ArXiv CV (cs.CV) | |
| 375 | HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis | ArXiv CV (cs.CV) | |
| 376 | Motion Capture from Inertial and Vision Sensors | ArXiv CV (cs.CV) | |
| 377 | Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes | ArXiv CV (cs.CV) | |
| 378 | Accuracy Improvement of Cell Image Segmentation Using Feedback Former | ArXiv CV (cs.CV) | |
| 379 | ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization | ArXiv CV (cs.CV) | |
| 380 | FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO | ArXiv CV (cs.CV) | |
| 381 | We’ll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback | ArXiv CV (cs.CV) | |
| 382 | FLEX: A Largescale Multimodal, Multiview Dataset for Learning Structured Representations for Fitness Action Quality Assessment | ArXiv CV (cs.CV) | |
| 383 | TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs | ArXiv CV (cs.CV) | |
| 384 | SmartCLIP: Modular Vision-language Alignment with Identification Guarantees | ArXiv CV (cs.CV) | |
| 385 | PAOLI: Pose-free Articulated Object Learning from Sparse-view Images | ArXiv CV (cs.CV) | |
| 386 | MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging | ArXiv CV (cs.CV) | |
| 387 | Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection | ArXiv CV (cs.CV) | |
| 388 | Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding | ArXiv CV (cs.CV) | |
| 389 | SAGA: Source Attribution of Generative AI Videos | ArXiv CV (cs.CV) | |
| 390 | SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors | ArXiv CV (cs.CV) | |
| 391 | Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions | ArXiv CV (cs.CV) | |
| 392 | The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment | ArXiv CV (cs.CV) | |
| 393 | FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting | ArXiv CV (cs.CV) | |
| 394 | Analysis of Invasive Breast Cancer in Mammograms Using YOLO, Explainability, and Domain Adaptation | ArXiv CV (cs.CV) | |
| 395 | DM3D: Deformable Mamba via Offset-Guided Differentiable Scanning for Point Cloud Understanding | ArXiv CV (cs.CV) | |
| 396 | Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality | ArXiv CV (cs.CV) | |
| 397 | Training Multi-Image Vision Agents via End2End Reinforcement Learning | ArXiv CV (cs.CV) | |
| 398 | GimbalDiffusion: Gravity-Aware Camera Control for Video Generation | ArXiv CV (cs.CV) | |
| 399 | DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass | ArXiv CV (cs.CV) | |
| 400 | FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation | ArXiv CV (cs.CV) | |
| 401 | Unified Thinker: A General Reasoning Modular Core for Image Generation | ArXiv CV (cs.CV) | |
| 402 | EGM: Efficient Visual Grounding Language Models | ArXiv CV (cs.CV) | |
| 403 | ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction | ArXiv CV (cs.CV) | |
| 404 | PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing | ArXiv CV (cs.CV) | |
| 405 | Video Understanding: Through A Temporal Lens | ArXiv CV (cs.CV) | |
| 406 | Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering | ArXiv CV (cs.CV) | |
| 407 | 3DXTalker: Unifying Identity, Lip Sync, Emotion, and Spatial Dynamics in Expressive 3D Talking Avatars | ArXiv CV (cs.CV) | |
| 408 | Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation | ArXiv CV (cs.CV) | |
| 409 | Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval | ArXiv CV (cs.CV) | |
| 410 | DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization | ArXiv CV (cs.CV) | |
| 411 | Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection | ArXiv CV (cs.CV) | |
| 412 | CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models | ArXiv CV (cs.CV) | |
| 413 | When Negation Is a Geometry Problem in Vision-Language Models | ArXiv CV (cs.CV) | |
| 414 | Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection | ArXiv CV (cs.CV) | |
| 415 | Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing | ArXiv CV (cs.CV) | |
| 416 | MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models | ArXiv CV (cs.CV) | |
| 417 | Scene Grounding In the Wild | ArXiv CV (cs.CV) | |
| 418 | Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars | ArXiv CV (cs.CV) | |
| 419 | UniRecGen: Unifying Multi-View 3D Reconstruction and Generation | ArXiv CV (cs.CV) | |
| 420 | Satellite-Free Training for Drone-View Geo-Localization | ArXiv CV (cs.CV) | |
| 421 | Semantic Richness or Geometric Reasoning? The Fragility of VLM’s Visual Invariance | ArXiv CV (cs.CV) | |
| 422 | Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition | ArXiv CV (cs.CV) | |
| 423 | SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions | ArXiv CV (cs.CV) | |
| 424 | Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation | ArXiv CV (cs.CV) | |
| 425 | Neural Field-Based 3D Surface Reconstruction of Microstructures from Multi-Detector Signals in Scanning Electron Microscopy | ArXiv CV (cs.CV) | |
| 426 | Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via U-Net Segmentation | ArXiv CV (cs.CV) | |
| 427 | Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception | ArXiv CV (cs.CV) | |