mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 1 Feb 2026

307 papers

  1. MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question AnsweringRetrieval-augmented generation → Multimodal RAG
  2. FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  3. LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task LearningMixture-of-experts → Mixture of LoRA experts
  4. Autonomous AI Agents for Option Hedging: Enhancing Financial Stability through Shortfall Aware Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  5. XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  6. GOPO: Policy Optimization using Ranked RewardsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  7. Decoding Ambiguous Emotions with Test-Time Scaling in Audio-Language ModelsLLM reasoning → Audio-language model reasoning
  8. Position: 3D Gaussian Splatting Watermarking Should Be Scenario-Driven and Threat-Model ExplicitLLM safety and security → Watermarking generated content and models
  9. Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  10. RAP: KV-Cache Compression via RoPE-Aligned PruningEfficient LLM inference and serving → KV cache optimization
  11. Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM SocietiesLLM agents and tool use → Social simulation and multi-agent debate
  12. ContextEvolve: Multi-Agent Context Compression for Systems Code OptimizationLLM agents and tool use → Software engineering coding agents +1
  13. To Defend Against Cyber Attacks, We Must Teach AI Agents to HackLLM safety and security → Prompt injection and agent security
  14. Predicting and improving test-time scaling laws via reward tail-guided searchLLM reasoning → Test-time compute and efficient thinking +1
  15. ConPress: Learning Efficient Reasoning from Multi-Question Contextual PressureLLM reasoning → Test-time compute and efficient thinking
  16. P-EAGLE: Parallel-Drafting EAGLE with Scalable TrainingLLM reasoning → Test-time compute and efficient thinking +1
  17. A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of ExpertsMixture-of-experts → Expert routing strategies
  18. Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating FunctionLLM reasoning → Test-time compute and efficient thinking +1
  19. Agyn: A Multi-Agent System for Team-Based Autonomous Software EngineeringLLM agents and tool use → Software engineering coding agents
  20. Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient EstimatorDeep reinforcement learning methods → RL theory and sample complexity
  21. SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-CommerceLLM agents and tool use → Social simulation and multi-agent debate
  22. Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in TransformersMechanistic interpretability → Circuits and mechanistic analysis
  23. TQL: Scaling Q-Functions with Transformers by Preventing Attention CollapseDeep reinforcement learning methods → Deep RL algorithms and representations
  24. Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language ModelsEfficient LLM inference and serving → Speculative decoding +1
  25. One Probe Won't Catch Them All: Towards Targeted Deception DetectionMechanistic interpretability → Probing deception, bias and beliefs
  26. Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM AgentsLLM agents and tool use → Educational agents and math problem solving
  27. Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  28. From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level SynthesisLLM agents and tool use → Software engineering coding agents
  29. Rethinking Selective Knowledge DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  30. Evaluation of Electricity Market Clearing Mechanisms via Reinforcement Learning: Prices, Remuneration and Competitive DynamicsDeep reinforcement learning methods → RL for energy, networks and operations
  31. The Enhanced Physics-Informed Kolmogorov-Arnold Networks: Applications of Newton's Laws in Financial Deep Reinforcement Learning (RL) AlgorithmsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  32. PromptRL: Prompt Matters in RL for Flow-Based Image GenerationDiffusion models → Diffusion and flow policies for robotics +1
  33. On the Power of (Approximate) Reward Models for Inference-Time ScalingLLM reasoning → Test-time compute and efficient thinking +1
  34. PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator EnsemblesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  35. Exposing and Defending the Achilles' Heel of Video Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
  36. When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for ReasoningLLM reasoning → Reinforcement learning for reasoning
  37. Balancing Understanding and Generation in Discrete Diffusion ModelsDiffusion models → Discrete and text diffusion
  38. Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation LearningSynthetic data and self-improvement for LLMs → Self-play RL for reasoning +1
  39. Aggregation Queries over Unstructured Text: Benchmark and Agentic MethodLLM agents and tool use → Web, search, and research agents
  40. T2M Mamba: Motion Periodicity-Saliency Coupling Approach for Stable Text-Driven Motion GenerationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  41. Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  42. Model Specific Task Similarity for Vision Language Model Selection via Layer ConductanceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  43. Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy AnalysisEfficient LLM inference and serving → Fast autoregressive visual generation
  44. MTC-VAE: Multi-Level Temporal Compression with Content AwarenessDiffusion models → Diffusion foundations and sampling
  45. High-accuracy sampling for diffusion models and log-concave distributionsDiffusion models → Diffusion foundations and sampling
  46. Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic ReasoningLLM agents and tool use → Multimodal and embodied agents
  47. What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-ZoomMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  48. A-MapReduce: Executing Wide Search via Agentic MapReduceLLM agents and tool use → Web, search, and research agents
  49. FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow MatchingDiffusion models → Flow matching, time series and science
  50. DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size CanvasDiffusion models → Discrete and text diffusion
  51. PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial DecodingMechanistic interpretability → Sparse autoencoder training and evaluation
  52. StoryState: Agent-Based State Control for Consistent and Editable StorybooksLLM agents and tool use → Multimodal and embodied agents
  53. Interaction-Consistent Object Removal via MLLM-Based ReasoningLLM reasoning → Multimodal reasoning
  54. RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical DiagnosisLLM reasoning → Clinical and biomedical applications
  55. Gradient-Aligned Calibration for Post-Training Quantization of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  56. EDIS: Diagnosing LLM Reasoning via Entropy DynamicsLLM reasoning → Test-time compute and efficient thinking
  57. PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive LengthEfficient LLM inference and serving → Speculative decoding
  58. Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  59. From Intents to Actions: Agentic AI in Autonomous NetworksLLM agents and tool use → Agentic AI for wireless networks
  60. Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent DynamicsWorld models → Latent dynamics models and model-based RL +1
  61. Reinforcement Learning for Active Perception in Autonomous NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  62. BicKD: Bilateral Contrastive Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  63. Sample Efficient Active Algorithms for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  64. Mechanistic Interpretability of Brain-to-Speech Models Across Speech ModesMechanistic interpretability → Knowledge and representations inside LLMs
  65. PARSE: An Open-Domain Reasoning Question Answering Benchmark for PersianLLM reasoning → Reasoning benchmarks and evaluation
  66. Large-Scale Terminal Agentic Trajectory Generation from Dockerized EnvironmentsLLM agents and tool use → Software engineering coding agents
  67. Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  68. FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge DistillationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  69. Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast WeightsMixture-of-experts → Expert routing strategies
  70. Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  71. Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning AlignmentLLM reasoning → Reinforcement learning for reasoning +1
  72. ASTER: Agentic Scaling with Tool-integrated Extended ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  73. Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head CollapseMixture-of-experts → MoE large language models
  74. Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow ConstructionLLM agents and tool use → Software engineering coding agents
  75. Med3D-R1: Incentivizing Clinical Reasoning in 3D Medical Vision-Language Models for Abnormality DiagnosisLLM reasoning → Clinical and biomedical applications +1
  76. A State-Transition Framework for Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  77. Unraveling the Hidden Dynamical Structure in Recurrent Neural PoliciesDeep reinforcement learning methods → Deep RL algorithms and representations
  78. Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion PerspectiveDiffusion models → Flow matching, time series and science
  79. Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  80. Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  81. A Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site SelectionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  82. DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent DiffusionDiffusion models → Robustness, privacy and adversarial aspects
  83. Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual InputsVision-language-action models → Safety and adversarial attacks
  84. PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  85. Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in VehiclesLLM agents and tool use → Software engineering coding agents
  86. SMI: Statistical Membership Inference for Reliable Unlearned Model AuditingLLM safety and security → Machine unlearning
  87. Capabilities and Fundamental Limits of Latent Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  88. Self-Generative Adversarial Fine-Tuning for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  89. Lyapunov Stability-Aware Stackelberg Game for Low-Altitude Economy: A Control-Oriented Pruning-Based DRL ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
  90. SMCP: Secure Model Context ProtocolLLM agents and tool use → Agent threats, guardrails and governance
  91. Tangent Space Fine-Tuning for Directional Preference Alignment in Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  92. Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant AnalysisMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  93. MarkovScale: Towards Optimal Sequential Scaling at Inference TimeLLM reasoning → Test-time compute and efficient thinking
  94. KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKVDiffusion models → Diffusion and flow policies for robotics
  95. Probing RLVR training instability through the lens of objective-level hackingLLM reasoning → Reinforcement learning for reasoning +1
  96. Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching ModelsDiffusion models → Robustness, privacy and adversarial aspects
  97. MedAD-R1: Eliciting Consistent Reasoning in Interpretible Medical Anomaly Detection via Consistency-Reinforced Policy OptimizationLLM reasoning → Clinical and biomedical applications +1
  98. AutoHealth: An Uncertainty-Aware Multi-Agent System for Autonomous Health Data ModelingLLM agents and tool use → Medical and scientific domain agents
  99. PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion TransformersDiffusion models → Video generation
  100. Vortex Stretching in the Navier-Stokes Equations and Information Dissipation in Diffusion Models: A Reformulation from a Partial Differential Equation ViewpointDiffusion models → Flow matching, time series and science
All 307
  1. What If We Allocate Test-Time Compute Adaptively?LLM reasoning → Test-time compute and efficient thinking
  2. From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  3. A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot ManipulationVision-language-action models → Human-video and latent-action pretraining +1
  4. Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMsKnowledge distillation → Knowledge distillation for LLMs
  5. Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  6. SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  7. TLDiffGAN: A Latent Diffusion-GAN Framework with Temporal Information Fusion for Anomalous Sound DetectionDiffusion models → Audio, speech and music
  8. Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  9. LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM AgentsLLM agents and tool use → Software engineering coding agents +1
  10. Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual GuidanceMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Superposition unifies power-law training dynamicsMechanistic interpretability → Sparse autoencoder training and evaluation +1
  12. VEQ: Modality-Adaptive Quantization for MoE Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  13. Discovering Process-Outcome Credit in Multi-Step LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  14. Toward Universal and Transferable Jailbreak Attacks on Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  15. Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective AlignmentRetrieval-augmented generation → Generation and context integration
  16. Offline Discovery of Interpretable Skills from Multi-Task TrajectoriesOffline RL and imitation learning from data → Robot manipulation imitation learning
  17. How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic ExperimentsLLM reasoning → Prompting and chain-of-thought reasoning
  18. Large Language Models as Students Who Think Aloud: Overly Coherent, Verbose, and ConfidentLLM reasoning → Reasoning benchmarks and evaluation
  19. Multi-Agent Teams Hold Experts BackLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. Distilling Token-Trained Models into Byte-Level ModelsKnowledge distillation → Knowledge distillation for LLMs
  21. SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware LearningLLM reasoning → Chain-of-thought reasoning for driving +1
  22. ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-TuningLLM reasoning → Reinforcement learning for reasoning
  23. How RLHF Amplifies SycophancyLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  24. Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  25. Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled TuningLLM reasoning → Reasoning for agents, planning and code +1
  26. HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  27. Sparse Reward Subsystem in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  28. DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  29. GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading AgentsLLM agents and tool use → Educational agents and math problem solving
  30. Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion ReasoningLLM reasoning → Audio-language model reasoning +1
  31. Symphony-Coord: Adaptive Routing for Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge ExtractionLLM agents and tool use → Web, search, and research agents
  33. Small-Margin Preferences Still Matter-If You Train Them RightLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker DiscoveryLLM agents and tool use → Medical and scientific domain agents
  35. MindGuard: Guardrail Classifiers for Multi-Turn Mental Health SupportLLM safety and security → Safety alignment, refusal and guardrails
  36. FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy EvolutionLLM agents and tool use → Financial trading and forecasting agents
  37. ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  38. Multimodal Claim Extraction for Fact-Checking
  39. Task-Aware LoRA Adapter Composition via Similarity Retrieval in Vector Databases
  40. Asymptotic Semantic Collapse in Hierarchical Optimization
  41. Global AI Bias Audit for Technical Governance
  42. Adaptive traffic signal control optimization using a novel road partition and multi-channel state representation method
  43. Deep Learning Based Multi-Level Classification for Aviation Safety
  44. Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
  45. Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
  46. Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting
  47. CaST: Causal Discovery via Spatio-Temporal Graphs in Disaster Tweets
  48. Fubini Study geometry of representation drift in high dimensional data
  49. Effective Frontiers: A Unification of Neural Scaling Laws
  50. Learnable Koopman-Enhanced Transformer-Based Time Series Forecasting with Spectral Control
  51. VividVoice: A Unified Framework for Scene-Aware Visually-Driven Speech Synthesis
  52. PeerRank: Autonomous LLM Evaluation Through Web-Grounded, Bias-Controlled Peer Review
  53. Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
  54. Causal Preference Elicitation
  55. Community-Level Modeling of Gyral Folding Patterns for Robust and Anatomically Informed Individualized Brain Mapping
  56. Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability
  57. Ebisu: Benchmarking Large Language Models in Japanese Finance
  58. Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning
  59. Learning to Guide Local Search for MPE Inference in Probabilistic Graphical Models
  60. Legal Infrastructure for Transformative AI Governance
  61. Understanding vision transformer robustness through the lens of out-of-distribution detection
  62. Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
  63. Modeling Topological Impact on Node Attribute Distributions in Attributed Graphs
  64. The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
  65. Cross-Paradigm Evaluation of Gaze-Based Semantic Object Identification for Intelligent Vehicles
  66. Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language
  67. Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics
  68. SentiFuse: Deep Multi-model Fusion Framework for Robust Sentiment Extraction
  69. A Meta-Knowledge-Augmented LLM Framework for Hyperparameter Optimization in Time-Series Forecasting
  70. A texture-based framework for foundational ultrasound models
  71. CIPHER: Cryptographic Insecurity Profiling via Hybrid Evaluation of Responses
  72. Theoretical Analysis of Measure Consistency Regularization for Partially Observed Data
  73. BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images
  74. Phase Transitions for Feature Learning in Neural Networks
  75. DCD: Decomposition-based Causal Discovery from Autocorrelated and Non-Stationary Temporal Data
  76. Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
  77. Semi-supervised CAPP Transformer Learning via Pseudo-labeling
  78. Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
  79. Importance Weighted Variational Inference without the Reparameterization Trick
  80. SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training
  81. Online Social Welfare Function-based Resource Allocation
  82. An Odd Estimator for Shapley Values
  83. Nonlinear model reduction for transport-dominated problems
  84. SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling
  85. Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics
  86. Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters
  87. "If You're Very Clever, No One Knows You've Used It": The Social Dynamics of Developing Generative AI Literacy in the Workplace
  88. WAKESET: A Large-Scale, High-Reynolds Number Flow Dataset for Machine Learning of Turbulent Wake Dynamics
  89. Context Dependence and Reliability in Autoregressive Language Models
  90. Robust Sublinear Convergence Rates for Iterative Bregman Projections
  91. Deep Variational Contrastive Learning for Joint Risk Stratification and Time-to-Event Estimation
  92. Causally Disentangled Contrastive Learning for Multilingual Speaker Embeddings
  93. PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
  94. Towards knowledge-based workflows: a semantic approach to atomistic simulations for mechanical and thermodynamic properties
  95. Adaptive Quantum-Safe Cryptography for 6G Vehicular Networks via Context-Aware Optimization
  96. Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
  97. TxRay: Agentic Postmortem of Live Blockchain Attacks
  98. Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
  99. Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution
  100. Dispelling the Curse of Singularities in Neural Network Optimizations
  101. DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling
  102. ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation
  103. Interacted Planes Reveal 3D Line Mapping
  104. Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
  105. Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses
  106. Seeing, Hearing, and Knowing Together: Multimodal Strategies in Deepfake Videos Detection
  107. Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
  108. Richer Bayesian Last Layers with Subsampled NTK Features
  109. DSFC-Net: A Dual-Encoder Spatial and Frequency Co-Awareness Network for Rural Road Extraction
  110. TF-Lane: Traffic Flow Module for Robust Lane Perception
  111. LLM-Driven Ontology Construction for Enterprise Knowledge Graphs
  112. OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth
  113. Diving into Kronecker Adapters: Component Design Matters
  114. Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment
  115. Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
  116. Inferential Question Answering
  117. Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching
  118. Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
  119. Learning from Anonymized and Incomplete Tabular Data
  120. AI Meets Plasticity: A Comprehensive Survey
  121. SimpleGPT: Improving GPT via A Simple Normalization Strategy
  122. Addressing Explainability of Generative AI using SMILE (Statistical Model-agnostic Interpretability with Local Explanations)
  123. EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting
  124. Bridging Lexical Ambiguity and Vision: A Mini Review on Visual Word Sense Disambiguation
  125. Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
  126. The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics
  127. FedBGS: A Blockchain Approach to Segment Gossip Learning in Decentralized Systems
  128. Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion
  129. Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
  130. Privacy Implies Stability: Information-Theoretic Generalization Bounds for Quantum Learning
  131. Multi-Fidelity Physics-Informed Neural Networks with Bayesian Uncertainty Quantification and Adaptive Residual Learning for Efficient Solution of Parametric Partial Differential Equations
  132. EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment
  133. ASP-Bench: From Natural Language to Logic Programs
  134. EmoAra: Emotion-Preserving English Speech Transcription and Cross-Lingual Translation with Arabic Text-to-Speech
  135. PedagoSense: A Pedology Grounded LLM System for Pedagogical Strategy Detection and Contextual Response Generation in Learning Dialogues
  136. Typologically-Informed Candidate Reranking for LLM-based Translation into Low-Resource Languages
  137. The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models
  138. Deep Time-Series Models Meet Volatility: Multi-Horizon Electricity Price Forecasting in the Australian National Electricity Market
  139. A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
  140. PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
  141. Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization
  142. Key Principles of Graph Machine Learning: Representation, Robustness, and Generalization
  143. A Unified Matrix-Spectral Framework for Stability and Interpretability in Deep Learning
  144. Your Autoregressive Model Already Reveals the Causal Graph
  145. Don't Judge a Book by its Cover: Testing LLMs' Robustness Under Logical Obfuscation
  146. WinFLoRA: Incentivizing Client-Adaptive Aggregation in Federated LoRA under Privacy Heterogeneity
  147. Long-range Modeling and Processing of Multimodal Event Sequences
  148. ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs
  149. Tendem: A Hybrid AI+Human Platform
  150. LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions
  151. Logic-Oriented Retriever Enhancement via Contrastive Learning
  152. Single-Edge Node Injection Threats to GNN-Based Security Monitoring in Industrial Graph Systems
  153. Transforming Vehicle Diagnostics: A Multimodal Approach to Error Patterns Prediction
  154. SPELL: Synthesis of Programmatic Edits using LLMs
  155. OLion: Approaching the Hadamard Ideal by Intersecting Spectral and ℓ∞ Implicit Biases
  156. Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning
  157. PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space
  158. Hard Constraints Meet Soft Generation: Guaranteed Feasibility for LLM-based Combinatorial Optimization
  159. MedBeads: An AI-Native Clinical Context Graph Built from Immutable Beads and Reconstructable Clinical Links
  160. On the Expressive Power of Permutation-Equivariant Weight-Space Networks
  161. EvoOpt-LLM: Evolving industrial optimization models with large language models
  162. ConvexBench: Can LLMs Recognize Convex Functions?
  163. PDE-Constrained Optimization for Neural Image Segmentation with Physics Priors
  164. DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification
  165. Radioactive 3D Gaussian Ray Tracing for Tomographic Reconstruction
  166. Baseline Method of the Foundation Model Challenge for Ultrasound Image Analysis
  167. The Quantum Learning Menagerie (A survey on Quantum learning for Classical concepts)
  168. SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes
  169. ReLayout: Versatile and Structure-Preserving Design Layout Editing via Relation-Aware Design Reconstruction
  170. Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection
  171. From Videos to Conversations: Egocentric Instructions for Task Assistance
  172. FUSE-Flow: Scalable Real-Time Multi-View Point Cloud Reconstruction Using Confidence
  173. GMAC: Global Multi-View Constraint for Automatic Multi-Camera Extrinsic Calibration
  174. HierCon: Hierarchical Contrastive Attention for Audio Deepfake Detection
  175. HalluHard: A Hard Multi-Turn Hallucination Benchmark
  176. Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations
  177. SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models
  178. The Stacked Autoencoder Evolution Hypothesis
  179. Calibrating Behavioral Parameters with Large Language Models
  180. Effectiveness of Automatically Curated Dataset in Thyroid Nodules Classification Algorithms Using Deep Learning
  181. Inter- and Intra-Subject Variability in EEG: A Systematic Survey
  182. LocalScore: Local Density-Aware Similarity Scoring for Biometrics
  183. LASS-ODE: Scaling ODE Computations to Connect Foundation Models with Dynamical Physical Systems
  184. Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
  185. Predicting Anemia Among Under-Five Children in Nepal Using Machine Learning and Deep Learning
  186. CortiNet: A Physics-Perception Hybrid Cortical-Inspired Dual-Stream Network for Gallbladder Disease Diagnosis from Ultrasound
  187. Error Taxonomy-Guided Prompt Optimization
  188. DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
  189. VAMOS-OCTA: Vessel-Aware Multi-Axis Orthogonal Supervision for Inpainting Motion-Corrupted OCT Angiography Volumes
  190. Optimal Decision-Making Based on Prediction Sets
  191. Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees
  192. Navigating Simply, Aligning Deeply: Winning Solutions for Mouse vs. AI 2025
  193. MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA
  194. Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
  195. Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
  196. Verification Required: The Impact of Information Credibility on AI Persuasion
  197. On the Spectral Flattening of Quantized Embeddings
  198. Multimodal Scientific Learning Beyond Diffusions and Flows
  199. From drift to adaptation to the failed ml model: Transfer Learning in Industrial MLOps
  200. Hybrid Topological and Deep Feature Fusion for Accurate MRI-Based Alzheimer's Disease Severity Classification
  201. Optimal Budgeted Adaptation of Large Language Models
  202. R-HTN: Rebellious Online HTN Planning for Safety and Game AI
  203. Data Augmentation for High-Fidelity Generation of CAR-T/NK Immunological Synapse Images
  204. The Keyhole Effect: Why Chat Interfaces Fail at Data Analysis
  205. Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
  206. Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems
  207. SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference