mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 27 Sep 2025

320 papers

  1. MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AILLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  2. Your Dense Retriever is Secretly an Expeditious ReasonerLLM reasoning → Knowledge- and tool-augmented reasoning
  3. CoDA: Coding LM via Diffusion AdaptationDiffusion models → Discrete and text diffusion
  4. General Exploratory Bonus for Optimistic Exploration in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  5. Language, Culture, and Ideology: Personalizing Offensiveness Detection in Political Tweets with Reasoning LLMsLLM reasoning → Reasoning benchmarks and evaluation
  6. Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured CompressionMixture-of-experts → MoE large language models
  7. CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language ModelsLLM safety and security → Watermarking generated content and models
  8. DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  9. Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model ExplanationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  11. Culture In a Frame: C3B as a Comic-Based Benchmark for Multimodal Culturally AwarenessMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  13. Knowledge distillation through geometry-aware representational alignmentKnowledge distillation → General knowledge distillation methods
  14. BEV-VLM: Trajectory Planning via Unified BEV AbstractionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  15. BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source SoftwareLLM agents and tool use → Software engineering coding agents
  16. Protocode: Prototype-Driven Interpretability for Code Generation in LLMsMechanistic interpretability → Knowledge and representations inside LLMs
  17. ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-SearchRetrieval-augmented generation → Privacy and security of RAG
  18. Evaluating point-light biological motion in multimodal large language modelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  19. Ask, Reason, Assist: Robot Collaboration via Natural Language and Temporal LogicLLM reasoning → Spatial and embodied reasoning
  20. RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature DistillationDiffusion models → Inverse problems and image restoration +1
  21. Solve Smart, Not Often: Policy Learning for Costly MILP Re-solvingDeep reinforcement learning methods → RL theory and sample complexity
  22. ViTSP: A Vision Language Models Guided Framework for Solving Large-Scale Traveling Salesman ProblemsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  24. From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database AgentsLLM agents and tool use → Medical and scientific domain agents
  25. Planner Aware Path Learning in Diffusion Language Models TrainingDiffusion models → Discrete and text diffusion
  26. WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics
  27. Your Models Have Thought Enough: Training Large Reasoning Models to Stop OverthinkingLLM reasoning → Test-time compute and efficient thinking
  28. Flow Matching Calibration for Simulation-Based Inference under Model MisspecificationDiffusion models → Flow matching, time series and science
  29. A Predictive and Synergistic Two-Layer Scheduling Framework for LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  30. Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFTLLM safety and security → Safety alignment, refusal and guardrails
  31. CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  32. CasPoinTr: Point Cloud Completion with Cascaded Networks and Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  33. Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. GRAPE: Let GRPO Supervise Query Rewriting by Ranking for RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  35. MedCritical: Enhancing Medical Reasoning in Small Language Models via Self-Collaborative CorrectionLLM reasoning → Clinical and biomedical applications +2
  36. Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  37. Dual-Space Smoothness for Robust and Balanced LLM UnlearningLLM safety and security → Machine unlearning
  38. Landing with the Score: Riemannian Optimization through DenoisingDiffusion models → Diffusion foundations and sampling
  39. Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured SamplingDiffusion models → Diffusion and flow policies for robotics
  40. Entering the Era of Discrete Diffusion Models: A Benchmark for Schr"odinger Bridges and Entropic Optimal TransportDiffusion models → Diffusion foundations and sampling
  41. DentVLM: A Multimodal Vision-Language Model for Comprehensive Dental Diagnosis and Enhanced Clinical PracticeMultimodal LLMs / vision-language models → Medical vision-language models
  42. Enhancing Blind Face Restoration through Online Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  43. Structured In-context Environment Scaling for Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  44. "Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online DiscussionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. Scaling LLM Test-Time Compute with Mobile NPU on SmartphonesLLM reasoning → Test-time compute and efficient thinking
  46. LLM Interpretability with Identifiable Temporal-Instantaneous RepresentationMechanistic interpretability → SAE features and their applications
  47. Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic FrameworkLLM reasoning → Multimodal reasoning +2
  48. Two-Scale Latent Dynamics for Recurrent-Depth TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  49. Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural MeaningLLM reasoning → Multimodal reasoning +1
  50. Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing ClassificationDiffusion models → Inverse problems and image restoration
  51. Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated ReasoningLLM reasoning → Mathematical reasoning +1
  52. Scaling Policy Compliance Assessment in Language Models with Policy Reasoning TracesLLM reasoning → Reasoning for agents, planning and code
  53. A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  54. Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference LearningLLM reasoning → Reasoning for agents, planning and code +3
  55. Preventing Robotic Jailbreaking via Multimodal Domain AdaptationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  56. Continuous-Time Reinforcement Learning for Asset-Liability ManagementDeep reinforcement learning methods → Adversarial robustness and RL in finance
  57. CREPE: Controlling Diffusion with Replica ExchangeDiffusion models → Diffusion foundations and sampling
  58. GUI-PRA: Process Reward Agent for GUI TasksLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  59. The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software EvolutionLLM agents and tool use → Software engineering coding agents
  60. NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  61. Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons LearnedLLM reasoning → Multimodal reasoning +1
  62. Resource-Aware LLM Reasoning for Mobile Edge General IntelligenceLLM reasoning → Reasoning for agents, planning and code +1
  63. More Data or Better Algorithms: Latent Diffusion Augmentation for Deep Imbalanced RegressionDiffusion models → Diffusion foundations and sampling
  64. Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-ReflectionLLM reasoning → Hallucination detection and mitigation +1
  65. Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  66. SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative RolloutsLLM reasoning → Reinforcement learning for reasoning +1
  67. Leave No Observation Behind: Real-time Correction for VLA Action ChunksVision-language-action models → Efficient VLA inference and adaptation
  68. GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch TrackingOffline RL and imitation learning from data → Robot manipulation imitation learning
  69. WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  70. Context Value Informed In-Context Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  71. A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated TasksMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  72. PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress AwarenessLLM agents and tool use → Reinforcement learning for LLM agents
  73. From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMsLLM reasoning → Reinforcement learning for reasoning
  74. Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction ConflictsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  75. PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous SpaceLLM reasoning → Test-time compute and efficient thinking
  76. ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without CollapseLLM reasoning → Reinforcement learning for reasoning
  77. LaGEA: Language Guided Embodied Agents for Robotic ManipulationLLM agents and tool use → Multimodal and embodied agents
  78. Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained VerifiersLLM reasoning → Test-time compute and efficient thinking
  79. Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  80. MathBode: Measuring the Stability of LLM Reasoning using Frequency ResponseLLM reasoning → Mathematical reasoning
  81. Earth-Agent: Unlocking the Full Landscape of Earth Observation with AgentsLLM agents and tool use → Multimodal and embodied agents
  82. Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  83. Trust Region Reward Optimization and Proximal Inverse Reward Optimization AlgorithmOffline RL and imitation learning from data → Inverse reinforcement learning +1
  84. C2GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware ReasoningLLM reasoning → Reinforcement learning for reasoning
  85. Impute-MACFM: Imputation based on Mask-Aware Flow MatchingDiffusion models → Flow matching, time series and science
  86. Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and ChallengesVision-language-action models → Generalist VLA models and benchmarks
  87. RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human MobilityLLM reasoning → Spatial and embodied reasoning
  88. FTACT: Force Torque aware Action Chunking Transformer for Pick-and-Reorient Bottle TaskOffline RL and imitation learning from data → Robot manipulation imitation learning
  89. Liaohe-CobotMagic-PnP: an Imitation Learning Dataset of Intelligent Robot for Industrial ApplicationsOffline RL and imitation learning from data → Robot manipulation imitation learning
  90. Towards Comprehensive Interactive Change Understanding in Remote Sensing: A Large-scale Dataset and Dual-granularity Enhanced VLMMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  91. Multiplayer Nash Preference OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  92. d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive CachingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  93. Sensitivity Analysis for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  94. Unleashing Flow Policies with Distributional CriticsOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  95. Follow-Your-Preference: Towards Preference-Aligned Image InpaintingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  96. CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable SystemsKnowledge distillation → Distillation for medical imaging
  97. From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents DevelopmentLLM reasoning → Knowledge- and tool-augmented reasoning +2
  98. Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended TasksSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  99. Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent DebateLLM agents and tool use → Social simulation and multi-agent debate
  100. Understanding Language Prior of LVLMs by Contrasting Chain-of-EmbeddingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
All 320
  1. Kimi-Dev: Agentless Training as Skill Prior for SWE-AgentsLLM agents and tool use → Software engineering coding agents
  2. Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  3. Look Back to Reason Forward: Revisitable Memory for Long-Context LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  4. GuardNet: Graph-Attention Filtering for Jailbreak Defense in Large Language ModelsLLM safety and security → Jailbreaking
  5. Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential PrivacyDiffusion models → Robustness, privacy and adversarial aspects
  6. LLM Watermark Evasion via Bias InversionLLM safety and security → Watermarking generated content and models
  7. Planning with Unified Multimodal ModelsLLM reasoning → Spatial and embodied reasoning +1
  8. MoE-PHDS: One MoE checkpoint for flexible runtime sparsityMixture-of-experts → Efficient MoE training and inference systems
  9. ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single ViewWorld models → Video-generation world models and simulators +1
  10. BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart
  11. Conversational Collective Intelligence (CCI) using Hyperchat AI in a Real-world Forecasting Task
  12. Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation
  13. Modeling Bias Evolution in Fashion Recommender Systems: A System Dynamics Approach
  14. Single-Snapshot Gridless 2D-DoA Estimation for UCAs: A Joint Optimization Approach
  15. From Noise to Laws: Regularized Time-Series Forecasting via Denoised Dynamic Graphs
  16. Cross-Domain Multi-Person Human Activity Recognition via Near-Field Wi-Fi Sensing
  17. VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
  18. Trainable Reference-Based Evaluation Metric for Identifying Quality of English-Gujarati Machine Translation System
  19. SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size
  20. Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
  21. Learning without Global Backpropagation via Synergistic Information Distillation
  22. Where to Add PDE Diffusion in Transformers
  23. Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary
  24. Decipher the Modality Gap in Multimodal Contrastive Learning: From Convergent Representations to Pairwise Alignment
  25. PT2-LLM: Post-Training Ternarization for Large Language Models
  26. Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
  27. An Encoder-Decoder Network for Beamforming over Sparse Large-Scale MIMO Channels
  28. Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness
  29. An Senegalese Legal Texts Structuration Using LLM-augmented Knowledge Graph
  30. Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations
  31. LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL
  32. An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
  33. mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations
  34. Small Language Models for Curriculum-based Guidance
  35. textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Training
  36. Object-AVEdit: An Object-level Audio-Visual Editing Model
  37. AI-Based Stroke Rehabilitation Domiciliary Assessment System with ST_GCN Attention
  38. Deep Learning Approaches with Explainable AI for Differentiating Alzheimer Disease and Mild Cognitive Impairment
  39. Beyond the Prompt: Gender Bias in Text-to-Image Models, with a Case Study on Hospital Professions
  40. Linear Regression in p-adic metric spaces
  41. Artificial Intelligence-Powered Assessment Framework for Skill-Oriented Engineering Lab Education
  42. RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
  43. Operationalising AI Regulatory Sandboxes: Activities, Requirements, and Technical Assessment under the EU AI Act
  44. Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration
  45. Memory Management and Contextual Consistency for Long-Running Low-Code Agents
  46. Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis
  47. DOoM: Difficult Olympiads of Math
  48. Learning single index model with gradient descent: spectral initialization and precise asymptotics
  49. Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts
  50. Network-Optimised Spiking Neural Network for Event-Driven Networking
  51. From Human Annotation to Automation: LLM-in-the-Loop Active Learning for Arabic Sentiment Analysis
  52. Model Consistency as a Cheap yet Predictive Proxy for LLM Elo Scores
  53. AraS2P: Arabic Speech-to-Phonemes System
  54. Enhancing Polyp Segmentation via Encoder Attention and Dynamic Kernel Update
  55. The Impact of Role Design in In-Context Learning for Large Language Models
  56. Beyond Outliers: A Study of Optimizers Under Quantization
  57. Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional
  58. Dynamic Trust Calibration Using Contextual Bandits
  59. Revisiting Multivariate Time Series Forecasting with Missing Values
  60. Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
  61. Mapping Overlaps in Benchmarks through Perplexity in the Wild
  62. Temporal Generalization: A Reality Check
  63. Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
  64. Accurate Predictions in Education with Discrete Variational Inference
  65. GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models
  66. Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation
  67. Statistical Learning Guarantees for Group-Invariant Barron Functions
  68. Memory-Efficient Fine-Tuning via Low-Rank Activation Compression
  69. Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases
  70. Multi-Modal Manipulation via Multi-Modal Policy Consensus
  71. Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
  72. Data-Efficient Training by Evolved Sampling
  73. MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
  74. No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
  75. 3DPCNet: Pose Canonicalization for Robust Viewpoint-Invariant 3D Kinematic Analysis from Monocular RGB cameras
  76. AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
  77. PHASE: Physics-Integrated, Heterogeneity-Aware Surrogates for Scientific Simulations
  78. FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing
  79. Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity
  80. Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
  81. S3F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network
  82. Optimal Diagonal Preconditioning Beyond Worst-Case Conditioning: Theory and Practice of Omega Scaling
  83. FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality
  84. Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions
  85. LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport
  86. AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
  87. NeuroBridge: Using Generative AI to Bridge Cross-neurotype Communication Differences through Neurotypical Perspective-taking
  88. SPIKE-RL: Video-LLMs meet Bayesian Surprise
  89. ToolUniverse: An open platform for democratizing AI scientists
  90. Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimization
  91. Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models
  92. FracDetNet: Advanced Fracture Detection via Dual-Focus Attention and Multi-scale Calibration in Medical X-ray Imaging
  93. URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
  94. Comparison of Scoring Rationales Between Large Language Models and Human Raters
  95. Hybrid Graph Embeddings and Louvain Algorithm for Unsupervised Community Detection
  96. PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
  97. Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks
  98. Enhanced Fracture Diagnosis Based on Critical Regional and Scale Aware in YOLO
  99. Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation
  100. Generative Modeling of Shape-Dependent Self-Contact Human Poses
  101. Optimizing the Network Topology of a Linear Reservoir Computer
  102. No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
  103. Train Once, Answer All: Many Pretraining Experiments for the Cost of One
  104. UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation
  105. An Accelerated Newton-GMRES Method for Multilinear PageRank
  106. Graph Your Own Prompt
  107. Splines-Based Feature Importance in Kolmogorov-Arnold Networks: A Framework for Supervised Tabular Data Dimensionality Reduction
  108. AI-Assisted Music Production: A User Study on Text-to-Music Models
  109. AI Education in Higher Education: A Taxonomy for Curriculum Reform and the Mission of Knowledge
  110. Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
  111. ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following
  112. CrediBench: Building Web-Scale Network Datasets for Information Integrity
  113. PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
  114. DiffTex: Differentiable Texturing for Architectural Proxy Models
  115. DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP
  116. Targeted perturbations reveal brain-like local coding axes in robustified, but not standard, ANN-based brain models
  117. C-Evolve: Consensus-based Evolution for Prompt Groups
  118. Space Robotics Bench: Robot Learning Beyond Earth
  119. Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
  120. Spatial-Spectral Binarized Neural Network for Panchromatic and Multi-spectral Images Fusion
  121. Multifractal features of multimodal cardiac signals: Nonlinear dynamics of exercise recovery
  122. C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection
  123. MELCOT: A Hybrid Learning Architecture with Marginal Preservation for Matrix-Valued Regression
  124. ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
  125. A Neural ODE Approach to Aircraft Flight Dynamics Modelling
  126. Seeing the Unseen in Low-light Spike Streams
  127. Seeing Through the Blur: Unlocking Defocus Maps for Deepfake Detection
  128. Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
  129. SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction
  130. Socio-Economic Model of AI Agents
  131. Transfer Learning and Machine Learning for Training Five Year Survival Prognostic Models in Early Breast Cancer
  132. Learning Regional Monsoon Patterns with a Multimodal Attention U-Net
  133. Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin
  134. OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
  135. LiDAR-based Human Activity Recognition through Laplacian Spectral Analysis
  136. ABConformer: Physics-inspired Sliding Attention for Antibody-Antigen Interface Prediction
  137. Deep Learning for Subspace Regression
  138. Explicit modelling of subject dependency in BCI decoding
  139. Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
  140. Online Dynamic Goal Recognition in Gym Environments
  141. Increasing the Diversity in RGB-to-Thermal Image Translation for Automotive Applications
  142. TATTOO: Training-free AesTheTic-aware Outfit recOmmendation
  143. Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
  144. p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
  145. A Generative Model for Controllable Feature Heterophily in Graphs
  146. UltraUNet: Real-Time Ultrasound Tongue Segmentation for Diverse Linguistic and Imaging Conditions
  147. One-Shot Multi-Label Causal Discovery in High-Dimensional Event Sequences
  148. Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2
  149. Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
  150. Real-World Transferable Adversarial Attack on Face-Recognition Systems
  151. Global Beats, Local Tongue: Studying Code Switching in K-pop Hits on Billboard Charts
  152. Structure leads and dominates comprehension in naturalistic reading
  153. Unsupervised Online 3D Instance Segmentation with Synthetic Sequences and Dynamic Loss
  154. CoSIFL: Collaborative Secure and Incentivized Federated Learning with Differential Privacy
  155. AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
  156. Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction
  157. Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
  158. Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
  159. WARBERT: A Hierarchical BERT-based Model for Web API Recommendation
  160. F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
  161. TRAX: TRacking Axles for Accurate Axle Count Estimation
  162. Sparse2Dense: A Keypoint-driven Generative Framework for Human Video Compression and Vertex Prediction
  163. Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs
  164. Dense associative memory for Gaussian distributions
  165. ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
  166. Deep Learning-Based Detection of Cognitive Impairment from Passive Smartphone Sensing with Routine-Aware Augmentation and Demographic Personalization
  167. Grouped Satisficing Paths in Pure Strategy Games: a Topological Perspective
  168. CrystalGym: A New Benchmark for Materials Discovery Using Reinforcement Learning
  169. AI-Enhanced Distributed Channel Access for Collision Avoidance in Future Wi-Fi 8
  170. WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning
  171. TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
  172. Coordination Requires Simplification: Thermodynamic Bounds on Multi-Objective Compromise in Natural and Artificial Intelligence
  173. Beyond Heuristics: Globally Optimal Configuration of Implicit Neural Representations
  174. Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT
  175. SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems
  176. Conditional Risk Minimization with Side Information: A Tractable, Universal Optimal Transport Framework
  177. Statistical Inference for Gradient Boosting Regression
  178. Impact of Environmental Factors on LoRa 2.4 GHz Time of Flight Ranging Outdoors
  179. Non-Collaborative User Simulators for Tool Agents
  180. Stochastic Interpolants via Conditional Dependent Coupling
  181. EKF-Based Fusion of Wi-Fi/LiDAR/IMU for Indoor Localization and Navigation
  182. Exploring LLM-based Frameworks for Fault Diagnosis
  183. AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors
  184. Artificial Phantasia: Emergent Mental Imagery in Large Language Models
  185. Open-Vocabulary Spatio-Temporal Scene Graph for Robot Perception and Teleoperation Planning
  186. Effective Quantization of Muon Optimizer States
  187. HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
  188. Towards Quantum-Ready Blockchain Fraud Detection via Ensemble Graph Neural Networks
  189. Deep Learning for Oral Health: Benchmarking ViT, DeiT, BEiT, ConvNeXt, and Swin Transformer
  190. How to Make Large Language Models Generate 100% Valid Molecules?
  191. Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
  192. Streamline pathology foundation model by cross-magnification distillation
  193. Causally-Enhanced Reinforcement Policy Optimization
  194. FedBit: Accelerating Privacy-Preserving Federated Learning via Bit-Interleaved Packing and Cross-Layer Co-Design
  195. Demystifying Network Foundation Models
  196. The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
  197. Beyond Gaussian Initializations: Signal Preserving Weight Initialization for Odd-Sigmoid Activations
  198. Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
  199. Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
  200. Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification
  201. Risk Profiling and Modulation for LLMs
  202. FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection
  203. Mask What Matters: Controllable Text-Guided Masking for Self-Supervised Medical Image Analysis
  204. Optimization as a Dynamical System: Generative Schedules from Latent ODEs
  205. Activation Matching for Explanation Generation
  206. Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
  207. MMeViT: Multi-Modal ensemble ViT for Post-Stroke Rehabilitation Action Recognition
  208. IsingFormer: Augmenting Parallel Tempering With Learned Proposals
  209. GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularization
  210. Sensor-Adaptive Flood Mapping with Pre-trained Multi-Modal Transformers across SAR and Multispectral Modalities
  211. DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence
  212. Understanding Catastrophic Interference: On the Identifibility of Latent Representations
  213. Perceptual Influence: Improving the Perceptual Loss Design for Low-Dose CT Enhancement
  214. Tracing the Representation Geometry of Language Models from Pretraining to Post-training
  215. Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
  216. UniPrototype: Humn-Robot Skill Learning with Uniform Prototypes
  217. On the Sheafification of Higher-Order Message Passing
  218. Geometry-Aware Losses for Structure-Preserving Text-to-Sign Language Generation
  219. Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Training
  220. Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition