mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 9 Feb 2025

169 papers

  1. MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture RecognitionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  2. Injecting Universal Jailbreak Backdoors into LLMs in MinutesLLM safety and security → Jailbreaking
  3. Jailbreaking to JailbreakLLM safety and security → Jailbreaking
  4. Few-shot LLM Synthetic Data with Distribution MatchingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  5. Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary ResolutionDiffusion models → Flow matching, time series and science
  6. PyPotteryInk: One-Step Diffusion Model for Sketch to Publication-ready Archaeological DrawingsDiffusion models → Image generation, text-to-image and editing
  7. Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  8. Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch PipelineMixture-of-experts → Efficient MoE training and inference systems
  9. Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein RegularizationDiffusion models → Diffusion and flow policies for robotics +1
  10. Training Language Models for Social Deduction with Multi-Agent Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Towards a Sharp Analysis of Offline Policy Learning for f-Divergence-Regularized Contextual BanditsOffline RL and imitation learning from data → Offline RL algorithms +1
  12. Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT ModelsLLM reasoning → Reasoning for agents, planning and code
  13. Investigating Compositional Reasoning in Time Series Foundation ModelsLLM reasoning → Time series reasoning
  14. Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with GuidanceDiffusion models → Flow matching, time series and science
  15. Dual Caption Preference Optimization for Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  16. Noise is an Efficient Learner for Zero-Shot Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  17. Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  18. Diffusion Models for Inverse Problems in the Exponential FamilyDiffusion models → Inverse problems and image restoration
  19. HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM AgentsLLM agents and tool use → Medical and scientific domain agents
  20. VFX Creator: Animated Visual Effect Generation with Controllable Diffusion TransformerDiffusion models → Video generation
  21. AutoAgent: A Fully-Automated and Zero-Code Framework for LLM AgentsLLM agents and tool use → Software engineering coding agents
  22. Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  23. Multi-granular Training Strategies for Robust Multi-hop Reasoning Over Noisy and Heterogeneous Knowledge SourcesLLM reasoning → Knowledge- and tool-augmented reasoning
  24. Continual Adaptation for Autonomous Driving with the Mixture of Progressive Experts NetworkEnd-to-end autonomous driving → Reinforcement learning for driving
  25. Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity AnalysisLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  26. GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination MitigationLLM safety and security → Safety alignment, refusal and guardrails
  27. Inverse Problem Sampling in Latent Space Using Sequential Monte CarloDiffusion models → Inverse problems and image restoration
  28. EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon TasksWorld models → World models for language agents +1
  29. Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language ModelsLLM reasoning → Clinical and biomedical applications
  30. Retrieval-augmented Large Language Models for Financial Time Series ForecastingRetrieval-augmented generation → Legal and financial RAG
  31. Self-Training Large Language Models for Tool-Use Without DemonstrationsLLM reasoning → Reasoning benchmarks and evaluation +2
  32. Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble DistillationKnowledge distillation → Graph neural network distillation
  33. EgoAgent: A Joint Predictive Agent Model in Egocentric WorldsWorld models → Embodied and robot world models
  34. DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot ControlMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  35. From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic ReasoningLLM reasoning → Multimodal reasoning
  36. Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech ModelsKnowledge distillation → Speech and audio distillation
  37. Contrastive Representation Distillation via Multi-Scale Feature DecouplingKnowledge distillation → General knowledge distillation methods
  38. Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  39. Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow ModelsDiffusion models → Diffusion foundations and sampling
  40. Quality Assurance for LLM-RAG Systems: Empirical Insights from Tourism Application TestingRetrieval-augmented generation → RAG pipeline design and evaluation
  41. PIPA: Preference Alignment as Prior-Informed Statistical EstimationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  42. Effective Black-Box Multi-Faceted Attacks Breach Vision Large Language Model GuardrailsLLM safety and security → Vision-language and text-to-image safety
  43. Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation ModelsKnowledge distillation → Speech and audio distillation
  44. Target Speaker Lipreading by Audio-Visual Self-Distillation Pretraining and Speaker AdaptationKnowledge distillation → Speech and audio distillation
  45. Understanding Representation Dynamics of Diffusion Models via Low-Dimensional ModelingDiffusion models → Diffusion foundations and sampling
  46. Mitigating Sensitive Information Leakage in LLMs4Code through Machine UnlearningLLM safety and security → Machine unlearning
  47. Impact of Data Poisoning Attacks on Feasibility and Optimality of Neural Power System OptimizersLLM safety and security → Backdoor and data poisoning attacks
  48. The Application of MATEC (Multi-AI Agent Team Care) Framework in Sepsis Care
  49. Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
  50. NutriTransform: Estimating Nutritional Information From Online Food Posts
  51. Modeling Churn in Recommender Systems with Aggregated Preferences
  52. MixLLM: Dynamic Routing in Mixed Large Language Models
  53. Survey on Recent Progress of AI for Chemistry: Methods, Applications, and Opportunities
  54. CacheMamba: Popularity Prediction for Mobile Edge Caching Networks via Selective State Spaces
  55. Crypto Miner Attack: GPU Remote Code Execution Attacks
  56. MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs
  57. RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition
  58. Agency in Artificial Intelligence Systems
  59. Neural Genetic Search in Discrete Spaces
  60. Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness
  61. Reading between the Lines: Can LLMs Identify Cross-Cultural Communication Gaps?
  62. CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking
  63. A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models
  64. Knowledge-data fusion dominated vehicle platoon dynamics modeling and analysis: A physics-encoded deep learning approach
  65. Temporal Model On Quantum Logic
  66. Decoding Complexity: Intelligent Pattern Exploration with CHPDA (Context Aware Hybrid Pattern Detection Algorithm)
  67. Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
  68. Enabling Autoregressive Models to Fill In Masked Tokens
  69. Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
  70. A Sociotechnical Approach for Knowledge Management (KM)
  71. Large Language Models for In-File Vulnerability Localization Can Be "Lost in the End"
  72. A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation
  73. AI-Driven HSI: Multimodality, Fusion, Challenges, and the Deep Learning Revolution
  74. A New Hybrid Intelligent Approach for Multimodal Detection of Suspected Disinformation on TikTok
  75. ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization
  76. LLMs for Drug-Drug Interaction Prediction: A Comprehensive Comparison
  77. Secure Visual Data Processing via Federated Learning
  78. Gradient Based Method for the Fusion of Lattice Quantizers
  79. Deconstructing Depression Stigma: Integrating AI-driven Data Collection and Analysis with Causal Knowledge Graphs
  80. Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
  81. Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Association
  82. Benchmarking Prompt Sensitivity in Large Language Models
  83. Multi-modal Data Fusion and Deep Ensemble Learning for Accurate Crop Yield Prediction
  84. LM2: Large Memory Models
  85. Neural Shortest Path for Surface Reconstruction from Point Clouds
  86. Differentially Private Hyperparameter Tuning using Local Bayesian Optimization
  87. Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
  88. Provably Overwhelming Transformer Models with Designed Inputs
  89. Traveling Waves Integrate Spatial Information Through Time
  90. A Conditional Tabular GAN-Enhanced Intrusion Detection System for Rare Attacks in IoT Networks
  91. DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
  92. A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptions
  93. Nested subspace learning with flags
  94. Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
  95. Kolmogorov-Arnold Fourier Networks
  96. Uncertainty Quantification and Causal Considerations for Off-Policy Decision Making
  97. Transformers versus the EM Algorithm in Multi-class Clustering
  98. Analysis of LLM as a grammatical feature tagger for African American English
  99. Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AI
  100. A Comprehensive Survey on Image Signal Processing Approaches for Low-Illumination Image Enhancement
All 169
  1. SNAT-YOLO: Efficient Cross-Layer Aggregation Network for Edge-Oriented Gangue Detection
  2. Preventing Rogue Agents Improves Multi-Agent Collaboration
  3. Speech to Speech Translation with Translatotron: A State of the Art Review
  4. Decision Making in Hybrid Environments: A Model Aggregation Approach
  5. Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules
  6. Asymptotic FDR Control with Model-X Knockoffs: Is Moments Matching Sufficient?
  7. μnit Scaling: Simple and Scalable FP8 LLM Training
  8. Detection of Physiological Data Tampering Attacks with Quantum Machine Learning
  9. Revisiting Gradient-based Uncertainty for Monocular Depth Estimation
  10. Redefining Robot Generalization Through Interactive Intelligence
  11. Cyri: A Conversational AI-based Assistant for Supporting the Human User in Detecting and Responding to Phishing Attacks
  12. Survival Concept-Based Learning Models
  13. Verifying Proportionality in Temporal Voting
  14. Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
  15. A Semi-Supervised Text Generation Framework Combining a Deep Transformer and a GAN
  16. Learning to Substitute Words with Model-based Score Ranking
  17. Skill Expansion and Composition in Parameter Space
  18. Protecting Intellectual Property of EEG-based Neural Networks with Watermarking
  19. ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images
  20. A Generative Framework for Bidirectional Image-Report Understanding in Chest Radiography
  21. Sign-Symmetry Learning Rules are Robust Fine-Tuners
  22. Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search
  23. ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification
  24. QP-SNN: Quantized and Pruned Spiking Neural Networks
  25. Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
  26. Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation
  27. A Distributional Perspective on Word Learning in Neural Language Models
  28. MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents
  29. NeuralPrefix: A Zero-shot Sensory Data Imputation Plugin
  30. MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation
  31. HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition
  32. Norm Augmented Graph AutoEncoders for Link Prediction
  33. Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education
  34. SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
  35. MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration
  36. Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases
  37. LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification
  38. Compressing Model with Few Class-Imbalance Samples: An Out-of-Distribution Expedition
  39. HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction
  40. MindCraft: Revolutionizing Education through AI-Powered Personalized Learning and Mentorship for Rural India
  41. Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models
  42. Image-Based Alzheimer's Disease Detection Using Pretrained Convolutional Neural Network Models
  43. Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue
  44. MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
  45. The Curse of Depth in Large Language Models
  46. Structural Perturbation in Large Language Model Representations through Recursive Symbolic Regeneration
  47. On Reference (In-)Determinacy in Natural Language Inference
  48. Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
  49. EPBC-YOLOv8: An efficient and accurate improved YOLOv8 underwater detector based on an attention mechanism
  50. Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
  51. WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch
  52. GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
  53. A 3D Multimodal Feature for Infrastructure Anomaly Detection
  54. Predictive Crash Analytics for Traffic Safety using Deep Learning
  55. Dynamic Pricing in the Linear Valuation Model using Shape Constraints
  56. Digital Twin Buildings: 3D Modeling, GIS Integration, and Visual Descriptions Using Gaussian Splatting, ChatGPT/Deepseek, and Google Maps Platform
  57. Privacy-Preserving Dataset Combination
  58. 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly
  59. Reinforced Lifelong Editing for Language Models
  60. Exploring Visual Embedding Spaces Induced by Vision Transformers for Online Auto Parts Marketplaces
  61. Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning
  62. PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map
  63. UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
  64. Linear Attention Modeling for Learned Image Compression
  65. RECOVER: Designing a Large Language Model-based Remote Patient Monitoring System for Postoperative Gastrointestinal Cancer Care
  66. Performance Analysis of Traditional VQA Models Under Limited Computational Resources
  67. Towards Autonomous Experimentation: Bayesian Optimization over Problem Formulation Space for Accelerated Alloy Development
  68. Attainability of Two-Point Testing Rates for Finite-Sample Location Estimation
  69. BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting