mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 16 Feb 2025

204 papers

  1. Deep Reinforcement Learning-Based Bidding Strategies for Prosumers Trading in Double Auction-Based Transactive Energy MarketDeep reinforcement learning methods → RL for energy, networks and operations
  2. Learning to Reason from Feedback at Test-TimeLLM reasoning → Test-time compute and efficient thinking
  3. Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. Vision-Enhanced Time Series Forecasting via Latent Diffusion ModelsDiffusion models → Flow matching, time series and science
  5. ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMsLLM safety and security → Jailbreaking
  6. Attention Mechanism for LLM-based Agents Dynamic Diffusion under Information AsymmetryLLM agents and tool use → Social simulation and multi-agent debate
  7. To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  8. Maximize Your Diffusion: A Study into Reward Maximization and Alignment for Diffusion-based ControlLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  9. AI Generations: From AI 1.0 to AI 4.0LLM agents and tool use → General LLM agent frameworks and benchmarks
  10. Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  11. CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?LLM reasoning → Multimodal reasoning +1
  12. Dialogue-based Explanations for Logical Reasoning using Structured ArgumentationLLM reasoning → Reasoning benchmarks and evaluation
  13. Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based FinetuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  14. OctoTools: An Agentic Framework with Extensible Tools for Complex ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  15. Improved Unbiased Watermark for Large Language ModelsLLM safety and security → Watermarking generated content and models
  16. Scalable Multi-Agent Offline Reinforcement Learning and the Role of InformationOffline RL and imitation learning from data → Offline multi-agent RL
  17. Uncertainty-Aware Step-wise Verification with Generative Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  18. Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  19. LLMs and Childhood Safety: Identifying Risks and Proposing a Protection Framework for Safe Child-LLM InteractionLLM safety and security → Safety alignment, refusal and guardrails
  20. Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  21. A Survey of LLM-based Agents in Medicine: How far are we from Baymax?LLM agents and tool use → Medical and scientific domain agents
  22. CSP: A Simulator For Multi-Agent Ranking CompetitionsLLM agents and tool use → Web, search, and research agents
  23. Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM TrainingKnowledge distillation → Knowledge distillation for LLMs
  24. ReLearn: Unlearning via Learning for Large Language ModelsLLM safety and security → Machine unlearning
  25. Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  26. Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration PitfallsLLM reasoning → Test-time compute and efficient thinking
  27. RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformerState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  28. DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  29. LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  30. Investigating Language Preference of Multilingual RAG SystemsRetrieval-augmented generation → Generation and context integration
  31. CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language ModelLLM reasoning → Mathematical reasoning
  32. Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance AnalysisLLM reasoning → Reasoning benchmarks and evaluation
  33. AI Sees Your Location, But With A Bias Toward The Wealthy WorldMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. Dyve: Thinking Fast and Slow for Dynamic Process VerificationLLM reasoning → Test-time compute and efficient thinking
  35. Robust Search with Uncertainty-Aware Value Models for Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
  36. RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  37. NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLMRetrieval-augmented generation → Multimodal RAG
  38. Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven OptimizationLLM reasoning → Multimodal reasoning
  39. Safety Evaluation of DeepSeek Models in Chinese ContextsLLM reasoning → Reasoning for agents, planning and code
  40. Solving Online Resource-Constrained Scheduling for Follow-Up Observation in Astronomy: a Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
  41. MasRouter: Learning to Route LLMs for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow MatchingDiffusion models → Audio, speech and music
  43. G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  44. DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming CapabilitiesState-space sequence models (S4, Mamba) → Speech and audio SSMs
  45. Gumbel Reranking: Differentiable End-to-End Reranker OptimizationRetrieval-augmented generation → Generation and context integration
  46. Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot ApplicationsRetrieval-augmented generation → Medical and biomedical RAG
  47. Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingKnowledge distillation → Knowledge distillation for LLMs
  48. OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization ModelingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  49. CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  50. Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  51. Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference TimeLLM reasoning → Test-time compute and efficient thinking +1
  52. SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak AttacksLLM safety and security → Jailbreaking
  53. Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness InstructionLLM safety and security → Jailbreaking
  54. Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based TasksRetrieval-augmented generation → Agentic RAG, agents and memory
  55. Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable DecisionsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  56. ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language ModelsMixture-of-experts → MoE for time series and graphs
  57. Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  58. MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  59. RLHF in an SFT Way: From Optimal Solution to Reward-Weighted AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  60. GRIFFIN: Effective Token Alignment for Faster Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  61. Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal SystemsDiffusion models → Flow matching, time series and science
  62. CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language ModelsLLM reasoning → Causal reasoning in LLMs
  63. Prompt Inject Detection with Generative Explanation as an Investigative ToolLLM safety and security → Prompt injection and agent security
  64. ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font AnnotationsDiffusion models → Image generation, text-to-image and editing
  65. RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference OptimizationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  66. Agentic LLM Framework for Adaptive Decision DiscourseLLM agents and tool use → Social simulation and multi-agent debate
  67. QuOTE: Question-Oriented Text EmbeddingsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  68. Skillful Nowcasting of Convective Clouds With a Cascade Diffusion ModelDiffusion models → Flow matching, time series and science
  69. Learning to Stop Overthinking at Test TimeLLM reasoning → Test-time compute and efficient thinking
  70. PEA: Enhancing LLM Performance on Computational-Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
  71. SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human InterventionLLM agents and tool use → Social simulation and multi-agent debate
  72. IterQR: An Iterative Framework for LLM-based Query Rewrite in e-Commercial Search System
  73. Conversational Explanations: Discussing Explainable AI with Non-AI Experts
  74. Practical Topics in Optimization
  75. The Butterfly Effect of Technology: How Various Factors accelerate or hinder the Arrival of Technological Singularity
  76. Generating Millions Of Lean Theorems With Proofs By Exploring State Transition Graphs
  77. ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis
  78. JExplore: Design Space Exploration Tool for Nvidia Jetson Boards
  79. Rashomon perspective for measuring uncertainty in the survival predictive maintenance models
  80. Performance Review on LLM for solving leetcode problems
  81. WeedVision: Multi-Stage Growth and Classification of Weeds using DETR and RetinaNet for Precision Agriculture
  82. Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
  83. Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review
  84. Noumenal Labs White Paper: How To Build A Brain
  85. PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN
  86. Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
  87. Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration
  88. An Interpretable Automated Mechanism Design Framework with Large Language Models
  89. Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
  90. Generalized Factor Neural Network Model for High-dimensional Regression
  91. ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
  92. Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection
  93. Non-Uniform Memory Sampling in Experience Replay
  94. Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring
  95. Integrating Language Models for Enhanced Network State Monitoring in DRL-Based SFC Provisioning
  96. Game-Of-Goals: Using adversarial games to achieve strategic resilience
  97. MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring
  98. Neural Operators for Stochastic Modeling of Nonlinear Structural System Response to Natural Hazards
  99. The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval
  100. Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
All 204
  1. FairFare: A Tool for Crowdsourcing Rideshare Data to Empower Labor Organizers
  2. Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations
  3. Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent
  4. The Shrinking Landscape of Linguistic Diversity in the Age of Large Language Models
  5. Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model
  6. Generating Skyline Datasets for Data Science Models
  7. Exploiting network optimization stability for enhanced PET image denoising using deep image prior
  8. Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification
  9. Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View
  10. Explaining Necessary Truths
  11. MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
  12. Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
  13. Towards identifying possible fault-tolerant advantage of quantum linear system algorithms in terms of space, time and energy
  14. Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL
  15. MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
  16. Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
  17. METAFOR: A Hybrid Metaheuristics Software Framework for Single-Objective Continuous Optimization Problems
  18. Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation
  19. PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
  20. Stochastic Optimization of Inventory at Large-scale Supply Chains
  21. Deep Contrastive Learning for Feature Alignment: Insights from Housing-Household Relationship Inference
  22. Multiscale autonomous forecasting of plasma systems' dynamics using neural networks
  23. Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation
  24. ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition
  25. How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
  26. From Deception to Perception: The Surprising Benefits of Deepfakes for Detecting, Measuring, and Mitigating Bias
  27. Large Language Models Penetration in Scholarly Writing and Peer Review
  28. TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
  29. Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation
  30. The Mirage of Model Editing: Revisiting Evaluation in the Wild
  31. Evaluating the Potential of Quantum Machine Learning in Cybersecurity: A Case-Study on PCA-based Intrusion Detection Systems
  32. Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
  33. SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
  34. Logarithmic Width Suffices for Robust Memorization
  35. BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation
  36. AnyRefill: A Unified, Data-Efficient Framework for Left-Prompt-Guided Vision Tasks
  37. Physics-Informed Support Vector Kernels via Green-Function Analogies and Jackson-Chebyshev Spectral Design
  38. Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks
  39. Eye Tracking Based Cognitive Evaluation of Automatic Readability Assessment Methods
  40. Large Language-Geometry Model: When LLM meets Equivariance
  41. Cognitive Neural Architecture Search Reveals Hierarchical Entailment
  42. Machine Learning-Based Intrusion Detection and Prevention System for IIoT Smart Metering Networks: Challenges and Solutions
  43. UNITE-FND: Reframing Multimodal Fake News Detection through Unimodal Scene Translation
  44. Improving Similar Case Retrieval Ranking Performance By Revisiting RankSVM
  45. AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
  46. Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time
  47. Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability
  48. Beyond Pairwise: Global Zero-shot Temporal Graph Generation
  49. Valuable Hallucinations: Realizable Non-realistic Propositions
  50. Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
  51. Graceful forgetting: Memory as a process
  52. Towards Achieving Concept Completeness for Textual Concept Bottleneck Models
  53. A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
  54. SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer
  55. Text-Promptable Propagation for Referring Medical Image Sequence Segmentation
  56. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
  57. On the Importance of Pretraining Data Alignment for Atomic Property Prediction
  58. Phantom: Subject-consistent video generation via cross-modal alignment
  59. DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling
  60. Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models
  61. Generalization of the Gibbs algorithm with high probability at low temperatures
  62. A Survey on Vulnerability Prioritization: Taxonomy, Metrics, and Research Challenges
  63. MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
  64. A Survey on Active Feature Acquisition Strategies
  65. CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
  66. Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
  67. D'ej`a Vu? Decoding Repeated Reading from Eye Movements
  68. A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
  69. Faces of Fairness: Examining Bias in Facial Expression Recognition Datasets and Models
  70. Detecting Cadastral Boundary from Satellite Images Using U-Net model
  71. Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
  72. AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping
  73. Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
  74. A Critical Review of Predominant Bias in Neural Networks
  75. Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
  76. On the Effect of Sampling Diversity in Scaling LLM Inference
  77. TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules
  78. DT4ECG: A Dual-Task Learning Framework for ECG-Based Human Identity Recognition and Human Activity Detection
  79. MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translation
  80. Leveraging Uncertainty Estimation for Efficient LLM Routing
  81. TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages
  82. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
  83. Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations
  84. FeaKM: Robust Collaborative Perception under Noisy Pose Conditions
  85. Adjust Your Focus: Defocus Deblurring From Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation
  86. CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening
  87. Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy
  88. RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
  89. Evaluating Large language models on Understanding Korean indirect Speech acts
  90. SSVEP-BiMA: Bifocal Masking Attention Leveraging Native and Symmetric-Antisymmetric Components for Robust SSVEP Decoding
  91. FinMTEB: Finance Massive Text Embedding Benchmark
  92. OMG: Opacity Matters in Material Modeling with Gaussian Splatting
  93. Is Elo Rating Reliable? A Study Under Model Misspecification
  94. TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction
  95. GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting
  96. Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues
  97. Neural Networks Remember More: The Power of Parameter Isolation and Combination
  98. Graders should cheat: privileged information enables expert-level automated evaluations
  99. A recurrent vision transformer shows signatures of primate visual attention
  100. Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System
  101. Learning the Exact Time Integration Algorithm for Initial Value Problems by Randomized Neural Networks
  102. The Relationship between No-Regret Learning and Online Conformal Prediction
  103. Exploring Contextual Flux in Large Language Models: A Novel Approach to Self-Modulating Semantic Networks
  104. CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation