mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 26 Jan 2025

161 papers

  1. SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  2. TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMsLLM reasoning → Test-time compute and efficient thinking
  3. HardML: A Benchmark For Evaluating Data Science And Machine Learning knowledge and reasoning in AILLM reasoning → Mathematical reasoning
  4. Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct ReasoningLLM reasoning → Test-time compute and efficient thinking
  5. Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology ImagesDiffusion models → Medical imaging and segmentation
  6. SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science DomainLLM reasoning → Mathematical reasoning
  7. Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive FrameworkLLM reasoning → Mathematical reasoning
  8. An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Medical vision-language models
  9. Cross-Cultural Fashion Design via Interactive Large Language Models and Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  10. ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from TransformerLLM safety and security → Machine unlearning
  11. Diffusion-Based Planning for Autonomous Driving with Flexible GuidanceEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  12. PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT EnvironmentsLLM safety and security → Backdoor and data poisoning attacks
  13. CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word VocabularyDiffusion models → Robustness, privacy and adversarial aspects
  14. Ocean-OCR: Towards General OCR Application via a Vision-Language ModelMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  15. Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion ModelDiffusion models → Diffusion recommenders
  16. UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  17. RLER-TTE: An Efficient and Effective Framework for En Route Travel Time Estimation with Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  18. CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with PlanningMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +2
  19. Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State SpaceState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  20. CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  21. Data-adaptive Safety Rules for Training Reward ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  22. SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal SparsityDiffusion models → Diffusion foundations and sampling
  23. StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary SpacesDiffusion models → 3D, point cloud and scene generation
  24. Episodic Novelty Through Temporal DistanceDeep reinforcement learning methods → Deep RL algorithms and representations
  25. Safe Learning Control with Optimality and Stability GuaranteesDeep reinforcement learning methods → Safe and constrained RL
  26. Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models +1
  27. Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual ReflectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  28. Factors That Influence the Adoption of AI-enabled Conversational Agents (AICAs) as an Augmenting Therapeutic Tool by Frontline Healthcare Workers: From Technology Acceptance Model 3 (TAM3) Lens -- A Systematic Mapping Review
  29. Feature-Aware Task-to-Core Allocation in Embedded Multi-core Platforms via Statistical Learning
  30. Regulating Multifunctionality
  31. Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach
  32. Physics-Trained Neural Network as Inverse Problem Solver for Potential Fields: An Example of Downward Continuation between Arbitrary Surfaces
  33. Physics-Driven Self-Supervised Deep Learning for Free-Surface Multiple Elimination
  34. An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising
  35. The Spectral Barycentre of a Set of Graphs with Community Structure
  36. Spontaneous emergence of linguistic statistical laws in images via artificial neural networks
  37. Letters, Colors, and Words: Constructing the Ideal Building Blocks Set
  38. Visualizing Uncertainty in Translation Tasks: An Evaluation of LLM Performance and Confidence Metrics
  39. Complete Chess Games Enable LLM Become A Chess Master
  40. Transformer^-1: Input-Adaptive Computation for Resource-Constrained Deployment
  41. Improving Network Threat Detection by Knowledge Graph, Large Language Model, and Imbalanced Learning
  42. HMCGeo: IP Region Prediction Based on Hierarchical Multi-label Classification
  43. Inductive-Associative Meta-learning Pipeline with Human Cognitive Patterns for Unseen Drug-Target Interaction Prediction
  44. Bridging the Sim2Real Gap: Vision Encoder Pre-Training for Visuomotor Policy Transfer
  45. Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributions
  46. Adapting Biomedical Abstracts into Plain language using Large Language Models
  47. Random Walk Guided Hyperbolic Graph Distillation
  48. Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination
  49. A Statistical Learning Approach to Mediterranean Cyclones
  50. Beyond Benchmarks: On The False Promise of AI Regulation
  51. Refined climatologies of future precipitation over High Mountain Asia using probabilistic ensemble learning
  52. Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts
  53. Blissful (A)Ignorance: People form overly positive impressions of others based on their written messages, despite wide-scale adoption of Generative AI
  54. Exploring the Feasibility of Deep Learning Models for Long-term Disease Prediction: A Case Study for Wheat Yellow Rust in England
  55. MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation
  56. StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel
  57. Constrained Hybrid Metaheuristic Algorithm for Probabilistic Neural Networks Learning
  58. Marker Track: Accurate Fiducial Marker Tracking for Evaluation of Residual Motions During Breath-Hold Radiotherapy
  59. AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability
  60. Classifying Deepfakes Using Swin Transformers
  61. A Machine Learning Approach to Automatic Fall Detection of Soldiers
  62. People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
  63. A Privacy Enhancing Technique to Evade Detection by Street Video Cameras Without Using Adversarial Accessories
  64. Can Pose Transfer Models Generate Realistic Human Motion?
  65. Mathematical analysis of the gradients in deep learning
  66. IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting
  67. A Comprehensive Survey on Self-Interpretable Neural Networks
  68. Be Intentional About Fairness!: Fairness, Size, and Multiplicity in the Rashomon Set
  69. BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation
  70. Quantum-Enhanced Attention Mechanism in NLP: A Hybrid Classical-Quantum Approach
  71. Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets
  72. GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting
  73. Your Learned Constraint is Secretly a Backward Reachable Tube
  74. I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers
  75. IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter
  76. Deterministic Reservoir Computing for Chaotic Time Series Prediction
  77. Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning
  78. Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction
  79. Advancing TDFN: Precise Fixation Point Generation Using Reconstruction Differences
  80. SedarEval: Automated Evaluation using Self-Adaptive Rubrics
  81. Information Consistent Pruning: How to Efficiently Search for Sparse Networks?
  82. Assessing and Predicting Air Pollution in Asia: A Regional and Temporal Study (2018-2023)
  83. Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge
  84. Twin Transition or Competing Interests? Validation of the Artificial Intelligence and Sustainability Perceptions Inventory (AISPI)
  85. Instruction Tuning for Story Understanding and Generation with Weak Supervision
  86. Approximate Message Passing for Bayesian Neural Networks
  87. Comparative clinical evaluation of "memory-efficient" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest
  88. A Unified Information-Theoretic Framework for Meta-Learning Generalization
  89. Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
  90. BoTier: Multi-Objective Bayesian Optimization with Tiered Composite Objectives
  91. Optimal Transport on Categorical Data for Counterfactuals using Compositional Data and Dirichlet Transport
  92. Building Efficient Lightweight CNN Models
  93. Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Internet of Electric Vehicles
  94. Estimating the Optimal Number of Clusters in Categorical Data Clustering by Silhouette Coefficient
  95. Estimating Committor Functions via Deep Adaptive Sampling on Rare Transition Paths
  96. Efficient Self-Supervised Grading of Prostate Cancer Pathology
  97. Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition
  98. TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler
  99. Universal Image Restoration Pre-training via Degradation Classification
  100. FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
All 161
  1. Unveiling the Potential of iMarkers: Invisible Fiducial Markers for Advanced Robotics
  2. Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification
  3. One Model to Forecast Them All and in Entity Distributions Bind Them
  4. Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
  5. Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
  6. AI in Oncology: Transforming Cancer Detection through Machine Learning and Deep Learning Applications
  7. Multilevel Browsing of Folksonomy-Based Digital Collections
  8. FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment
  9. Differentiable Low-computation Global Correlation Loss for Monotonicity Evaluation in Quality Assessment
  10. Query-based versus resource-based cache strategies in tag-based browsing systems
  11. LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
  12. CISOL: An Open and Extensible Dataset for Table Structure Recognition in the Construction Industry
  13. TractoGPT: A GPT architecture for White Matter Segmentation
  14. Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
  15. Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From Simulated Nonparametric Functions
  16. On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning
  17. Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
  18. STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection
  19. FlatTrack: Eye-tracking with ultra-thin lensless cameras
  20. Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection
  21. NP-Hard Lower Bound Complexity for Semantic Self-Verification
  22. InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
  23. Overview of the Amphion Toolkit (v0.2)
  24. Dfilled: Repurposing Edge-Enhancing Diffusion for Guided DSM Void Filling
  25. Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection
  26. Making Sense Of Distributed Representations With Activation Spectroscopy
  27. Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
  28. Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
  29. Evaluating Simple Debiasing Techniques in RoBERTa-based Hate Speech Detection Models
  30. OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
  31. Stroke Lesion Segmentation using Multi-Stage Cross-Scale Attention
  32. Visual Generation Without Guidance
  33. AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement
  34. OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery
  35. The Potential of Large Language Models in Supply Chain Management: Advancing Decision-Making, Efficiency, and Innovation
  36. TdAttenMix: Top-Down Attention Guided Mixup
  37. Turn That Frown Upside Down: FaceID Customization via Cross-Training Data
  38. Semantic Layered Embedding Diffusion in Large Language Models for Multi-Contextual Consistency
  39. A Neurosymbolic Framework for Geometric Reduction of Binary Forms
  40. Scaling of hardware-compatible perturbative training algorithms
  41. How Green are Neural Language Models? Analyzing Energy Consumption in Text Summarization Fine-tuning
  42. Foundations of a Knee Joint Digital Twin from qMRI Biomarkers for Osteoarthritis and Knee Replacement
  43. Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perception
  44. Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completion
  45. Faster Configuration Performance Bug Testing with Neural Dual-level Prioritization
  46. CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation
  47. Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion Theory
  48. DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation
  49. MetaOcc: Spatio-Temporal Fusion of Surround-View 4D Radar and Camera for 3D Occupancy Prediction with Dual Training Strategies
  50. Qwen2.5-1M Technical Report
  51. Diffusion Augmented Retrieval: A Training-Free Approach to Interactive Text-to-Image Retrieval
  52. How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
  53. Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
  54. Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models
  55. Acquiring Submillimeter-Accurate Multi-Task Vision Datasets for Computer-Assisted Orthopedic Surgery
  56. iFormer: Integrating ConvNet and Transformer for Mobile Application
  57. Baichuan-Omni-1.5 Technical Report
  58. A Transfer Learning Framework for Anomaly Detection in Multivariate IoT Traffic Data
  59. AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach
  60. Decentralized Low-Rank Fine-Tuning of Large Language Models
  61. Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting