mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 7 Jun 2025

172 papers

  1. Modeling Earth-Scale Human-Like Societies with One Billion AgentsLLM agents and tool use → Social simulation and multi-agent debate
  2. PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking MechanismRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  3. From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  4. Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric SequencesState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  5. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem ComplexityLLM reasoning → Test-time compute and efficient thinking
  6. How Important are Videos for Training Video LLMs?LLM reasoning → Multimodal reasoning
  7. Boosting LLM Reasoning via Spontaneous Self-CorrectionLLM reasoning → Test-time compute and efficient thinking
  8. Causal Graph based Event Reasoning using Semantic Relation ExpertsLLM reasoning → Causal reasoning in LLMs
  9. Meta-Adaptive Prompt Distillation for Few-Shot Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Robust In-Context Reinforcement Learning Under Reward Poisoning AttacksDeep reinforcement learning methods → Adversarial robustness and RL in finance
  11. Hybrid Vision Transformer-Mamba Framework for Autism Diagnosis via Eye-Tracking AnalysisState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  12. FREE: Fast and Robust Vision Language Models with Early ExitsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  13. KnowCoder-V2: Deep Knowledge AnalysisLLM reasoning → Knowledge- and tool-augmented reasoning
  14. Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math ReasoningLLM reasoning → Mathematical reasoning
  15. FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation EnsemblesMixture-of-experts → Vision mixture-of-experts
  16. Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual ReasoningLLM reasoning → Multimodal reasoning
  17. United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load TheoryLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Harnessing Vision-Language Models for Time Series Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  19. Controllable Coupled Image Generation via Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  20. Deep reinforcement learning-based joint real-time energy scheduling for green buildings with heterogeneous battery energy storage devicesDeep reinforcement learning methods → RL for energy, networks and operations
  21. Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMsLLM reasoning → Audio-language model reasoning
  22. Training-Free Diffusion Framework for Stylized Image Generation with Identity PreservationDiffusion models → Image generation, text-to-image and editing
  23. Minimal Ingredients for Reward Assignment from Expert DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  24. Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information GainDeep reinforcement learning methods → Deep RL algorithms and representations
  25. Continuous Semi-Implicit ModelsDiffusion models → Diffusion foundations and sampling
  26. Mitigating Object Hallucination via Robust Local Perception SearchMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  27. VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMsLLM reasoning → Multimodal reasoning +1
  28. WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-makingWorld models → World models for language agents
  29. Dynamic and Parametric Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  30. Contextual Experience Replay for Self-Improvement of Language AgentsLLM agents and tool use → Agent memory systems +1
  31. Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual LearningMixture-of-experts → MoE for time series and graphs
  32. RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation EvaluationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  33. Flood-DamageSense: Multimodal Mamba with Multitask Learning for Building Flood Damage Assessment using SAR Remote Sensing ImageryState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  34. SafeLawBench: Towards Safe Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  35. Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  36. Transferring Linear Features Across Language Models With Model StitchingMechanistic interpretability → SAE features and their applications
  37. RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware ConstraintsLLM reasoning → Clinical and biomedical applications +1
  38. eXtended Physics Informed Neural Network Method for Fracture Mechanics Problems
  39. Deep Kernel Bayesian Optimisation for Closed-Loop Electrode Microstructure Design with User-Defined Properties based on GANs
  40. Subjective Evaluation Profile Analysis of Science Fiction Short Stories and its Critical-Theoretical Significance
  41. Scalable Offline ASR for Command-Style Dictation in Courtrooms
  42. Recursive Learning-Based Virtual Buffering for Analytical Global Placement
  43. Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations
  44. Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor
  45. Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation
  46. Exploring Image Transforms derived from Eye Gaze Variables for Progressive Autism Diagnosis
  47. What Makes a Good Natural Language Prompt?
  48. Making a Pipeline Production-Ready: Challenges and Lessons Learned in the Healthcare Domain
  49. Conditional Denoising Diffusion for ISAC Enhanced Channel Estimation in Cell-Free 6G
  50. Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
  51. Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP
  52. An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design
  53. Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
  54. DiscoSum: Discourse-aware News Summarization
  55. Hybrid Extractive Abstractive Summarization for Multilingual Sentiment Analysis
  56. Basis Transformers for Multi-Task Tabular Regression
  57. Reading in the Dark with Foveated Event Vision
  58. Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
  59. Graph Neural Networks in Modern AI-aided Drug Discovery
  60. Sleep Stage Classification using Multimodal Embedding Fusion from EOG and PSM
  61. Gaussian Mapping for Evolving Scenes
  62. Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
  63. KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search
  64. Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example
  65. NSD-Imagery: A benchmark dataset for extending fMRI vision decoding methods to mental imagery
  66. Scalable Gaussian Processes with Latent Kronecker Structure
  67. SPC to 3D: Novel View Synthesis from Binary SPC via I2I translation
  68. Automatic Speech Recognition of African American English: Lexical and Contextual Effects
  69. Mixture of Small and Large Models for Chinese Spelling Check
  70. LLM-D12: A Dual-Dimensional Scale of Instrumental and Relational Dependencies on Large Language Models
  71. Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
  72. Recursive Semantic Anchoring in ISO 639:2023: A Structural Extension to ISO/TC 37 Frameworks
  73. Incorporating Failure of Machine Learning in Dynamic Probabilistic Safety Assurance
  74. SAFE: Finding Sparse and Flat Minima to Improve Pruning
  75. Face recognition on point cloud with cgan-top for denoising
  76. Multimodal Spatial Language Maps for Robot Navigation and Manipulation
  77. Differentially Private Sparse Linear Regression with Heavy-tailed Responses
  78. DONUT: A Decoder-Only Model for Trajectory Prediction
  79. Curvature Enhanced Data Augmentation for Regression
  80. Position Prediction Self-Supervised Learning for Multimodal Satellite Imagery Semantic Segmentation
  81. Deep Inertial Pose: A deep learning approach for human pose estimation
  82. Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles
  83. Linear Discriminant Analysis with Gradient Optimization
  84. Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
  85. PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation
  86. A Statistical Framework for Model Selection in LSTM Networks
  87. AI-Generated Compromises for Coalition Formation
  88. Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures
  89. EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery
  90. The Currents of Conflict: Decomposing Conflict Trends with Gaussian Processes
  91. Exploring Visual Prompting: Robustness Inheritance and Beyond
  92. Hi-LSplat: Hierarchical 3D Language Gaussian Splatting
  93. Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems
  94. Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
  95. ASPO: Constraint-Aware Bayesian Optimization for FPGA-based Soft Processors
  96. How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language
  97. Path Integral Optimiser: Global Optimisation via Neural Schr"odinger-F"ollmer Diffusion
  98. BTPD: A Multilingual Hand-curated Dataset of Bengali Transnational Political Discourse Across Online Communities
  99. Advancing Question Generation with Joint Narrative and Difficulty Control
  100. IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder
All 172
  1. Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events
  2. Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
  3. On the Adaptive Psychological Persuasion of Large Language Models
  4. FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networks
  5. Extending dependencies to the taggedPBC: Word order in transitive clauses
  6. Caterpillar GNN: Replacing Message Passing with Efficient Aggregation
  7. Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
  8. Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
  9. They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse
  10. Taming Wild Branches: Overcoming Hard-to-Predict Branches using the Bullseye Predictor
  11. LoopDB: A Loop Closure Dataset for Large Scale Simultaneous Localization and Mapping
  12. The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing
  13. LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security
  14. SAR2Struct: Extracting 3D Semantic Structural Representation of Aircraft Targets from Single-View SAR Image
  15. Depth-Optimal Quantum Layout Synthesis as SAT
  16. Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
  17. Accuracy-Efficiency Trade-Offs in Spiking Neural Networks: A Lempel-Ziv Complexity Perspective on Learning Rules
  18. THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation
  19. AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Method
  20. Honey, I shrunk the hypothesis space (through logical preprocessing)
  21. C-PATH: Conversational Patient Assistance and Triage in Healthcare System
  22. Ai-Driven Vulnerability Analysis in Smart Contracts: Trends, Challenges and Future Directions
  23. RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
  24. Neural Spectral Band Generation for Audio Coding
  25. Fuse and Federate: Enhancing EV Charging Station Security with Multimodal Fusion and Federated Learning
  26. Improving Wildlife Out-of-Distribution Detection: Africas Big Five
  27. IQFM A Wireless Foundational Model for I/Q Streams in AI-Native 6G
  28. A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks
  29. Integrating AI Planning Semantics into SysML System Models for Automated PDDL File Generation
  30. Active Contour Models Driven by Hyperbolic Mean Curvature Flow for Image Segmentation
  31. A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
  32. A Survey of Retentive Network
  33. DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
  34. Do Protein Transformers Have Biological Intelligence?
  35. MarginSel : Max-Margin Demonstration Selection for LLMs
  36. Design and Implementation of a RISC-V SoC with Custom DSP Accelerators for Edge Computing
  37. SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot System
  38. Learning Distribution-Wise Control in Representation Space for Language Models
  39. RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
  40. Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics
  41. Interpretation of Deep Learning Model in Embryo Selection for In Vitro Fertilization (IVF) Treatment
  42. Through the Gaps: Uncovering Tactical Line-Breaking Passes with Clustering
  43. SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
  44. Generalized Trajectory Scoring for End-to-end Multimodal Planning
  45. DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
  46. Self-Improving Loops for Visual Robotic Planning
  47. Quantile Regression with Large Language Models for Price Prediction
  48. Rescaled Influence Functions: Accurate Data Attribution in High Dimension
  49. Explaining Risks: Axiomatic Risk Attributions for Financial Models
  50. SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes
  51. Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling
  52. Spark Transformer: Reactivating Sparsity in FFN and Attention
  53. Dark Channel-Assisted Depth-from-Defocus from a Single Image
  54. Non-Intrusive Load Monitoring Based on Image Load Signatures and Continual Learning
  55. GELD: A Unified Neural Model for Efficiently Solving Traveling Salesman Problems Across Different Scales
  56. Vision-QRWKV: Exploring Quantum-Enhanced RWKV Models for Image Classification
  57. PhysLab: A Benchmark Dataset for Multi-Granularity Visual Parsing of Physics Experiments
  58. Active Test-time Vision-Language Navigation
  59. Psychological Counseling Cannot Be Achieved Overnight: Automated Psychological Counseling Through Multi-Session Conversations
  60. QuantMCP: Grounding Large Language Models in Verifiable Financial Reality
  61. BriefMe: A Legal NLP Benchmark for Assisting with Legal Briefs
  62. Interpretable Depression Detection from Social Media Text Using LLM-Derived Embeddings
  63. Robust Learnability of Sample-Compressible Distributions under Noisy or Adversarial Perturbations
  64. Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
  65. Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓp-Smooth Nonconvex Optimization
  66. MedCite: Can Language Models Generate Verifiable Text for Medicine?
  67. Scoring the Unscorables: Cyber Risk Assessment Beyond Internet Scans
  68. CAtCh: Cognitive Assessment through Cookie Thief
  69. Zero Shot Composed Image Retrieval
  70. Direct Prediction Set Minimization via Bilevel Conformal Classifier Training
  71. EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras
  72. From Model-Based and Adaptive Control to Evolving Fuzzy Control