mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 5 Jan 2025

114 papers

  1. LatteReview: A Multi-Agent Framework for Systematic Review Automation Using Large Language ModelsLLM agents and tool use → Web, search, and research agents
  2. Strategic Fusion Optimizes Transformer CompressionKnowledge distillation → General knowledge distillation methods
  3. Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  4. DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineeringDiffusion models → Flow matching, time series and science
  6. Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?LLM reasoning → Multimodal reasoning +1
  7. A View of the Certainty-Equivalence Method for PAC RL as an Application of the Trajectory Tree MethodDeep reinforcement learning methods → RL theory and sample complexity
  8. Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack DefenseLLM safety and security → Jailbreaking
  9. Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety FiltersDeep reinforcement learning methods → Safe and constrained RL
  10. Efficient Architectures for High Resolution Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. DepthMaster: Taming Diffusion Models for Monocular Depth EstimationDiffusion models → 3D, point cloud and scene generation
  12. Energy Optimization of Multi-task DNN Inference in MEC-assisted XR Devices: A Lyapunov-Guided Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  13. Decoding fMRI Data into Captions using Prefix Language ModelingDiffusion models → Medical imaging and segmentation
  14. KM-UNet KAN Mamba UNet for medical image segmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  15. Planning Under Observation Mismatch for Traffic Signal Control via Adaptive Modular World ModelsWorld models → World models for autonomous driving
  16. Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGILLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  17. Unified Guidance for Geometry-Conditioned Molecular GenerationDiffusion models → Flow matching, time series and science
  18. Face-MakeUp: Multimodal Facial Prompts for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  19. Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  20. PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost OptimizationEfficient LLM inference and serving → Early exit and edge inference
  21. ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool UseLLM agents and tool use → Tool learning and function calling
  22. A Survey of Test-Time Compute: From Intuitive Inference to Deliberate ReasoningLLM reasoning → Test-time compute and efficient thinking
  23. LLMPC: Large Language Model Predictive ControlLLM reasoning → Reasoning for agents, planning and code
  24. Representation Convergence: Mutual Distillation is Secretly a Form of RegularizationDeep reinforcement learning methods → Deep RL algorithms and representations
  25. DeTrack: In-model Latent Denoising Learning for Visual Object TrackingDiffusion models → Image generation, text-to-image and editing
  26. FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  27. Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical ApplicationsRetrieval-augmented generation → Medical and biomedical RAG
  28. Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning GapLLM reasoning → Mathematical reasoning
  29. MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion SegmentationDiffusion models → Medical imaging and segmentation
  30. RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking FrameworkLLM safety and security → Watermarking generated content and models
  31. FOLDER: Accelerating Multi-modal Large Language Models with Enhanced PerformanceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  32. A Study about Distribution and Acceptance of Conversational Agents for Mental Health in Germany: Keep the Human in the Loop?
  33. Punch Out Model Synthesis: A Stochastic Algorithm for Constraint Based Tiling Generation
  34. Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior
  35. Understanding colors of Dufaycolor: Can we recover them using historical colorimetric and spectral data?
  36. Fitting Different Interactive Information: Joint Classification of Emotion and Intention
  37. Traits of a Leader: User Influence Level Prediction through Sociolinguistic Modeling
  38. From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
  39. Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model
  40. DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
  41. HonkaiChat: Companions from Anime that feel alive!
  42. ComMer: a Framework for Compressing and Merging User Data for Personalization
  43. GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
  44. Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head
  45. Improving Quantum Machine Learning via Heat-Bath Algorithmic Cooling
  46. From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets
  47. Exploring the Impact of Dataset Statistical Effect Size on Model Performance and Data Sample Size Sufficiency
  48. Re-examining Granger Causality with Causal Bayesian Networks and Reichenbachs Principles
  49. Multi-Aggregator Time-Warping Heterogeneous Graph Neural Network for Personalized Micro-Video Recommendation
  50. Incentive-Compatible Federated Learning with Stackelberg Game Modeling
  51. Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
  52. Tighnari: Multi-modal Plant Species Prediction Based on Hierarchical Cross-Attention Using Graph-Based and Vision Backbone-Extracted Features
  53. Representation Learning of Lab Values via Masked AutoEncoders
  54. Trust and Dependability in Blockchain & AI Based MedIoT Applications: Research Challenges and Future Directions
  55. Multispectral Pedestrian Detection with Sparsely Annotated Label
  56. Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian
  57. Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets
  58. HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
  59. Simultaneous analysis of approximate leave-one-out cross-validation and mean-field inference
  60. LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment
  61. Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network
  62. Multi-layer Radial Basis Function Networks for Out-of-distribution Detection
  63. LWFNet: Coherent Doppler Wind Lidar-Based Network for Wind Field Retrieval
  64. Chameleon2++: An Efficient and Scalable Variant Of Chameleon Clustering
  65. TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms
  66. Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models
  67. GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation
  68. Evolving Skeletons: Motion Dynamics in Action Recognition
  69. Gaze Behavior During a Long-Term, In-Home, Social Robot Intervention for Children with ASD
  70. LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations
  71. Efficient Graph Condensation via Gaussian Process
  72. Balanced Multi-view Clustering
  73. Neural Error Covariance Estimation for Precise LiDAR Localization
  74. Multi-LLM Collaborative Caption Generation in Scientific Documents
  75. From Language To Vision: A Case Study of Text Animation
  76. Transformers Simulate MLE for Sequence Generation in Bayesian Networks
  77. TreeMatch: A Fully Unsupervised WSD System Using Dependency Knowledge on a Specific Domain
  78. AHMSA-Net: Adaptive Hierarchical Multi-Scale Attention Network for Micro-Expression Recognition
  79. A completely uniform transformer for parity
  80. Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigm
  81. Evaluating Large Language Models Against Human Annotators in Latent Content Analysis: Sentiment, Political Leaning, Emotional Intensity, and Sarcasm
  82. Vision-Driven Prompt Optimization for Large Language Models in Multimodal Generative Tasks
  83. Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization
  84. CHAIR -- Classifier of Hallucination as Improver
  85. Can Impressions of Music be Extracted from Thumbnail Images?
  86. Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
  87. Estimation of partial rankings from sparse, noisy comparisons
  88. Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
  89. Predicting Vulnerability to Malware Using Machine Learning Models: A Study on Microsoft Windows Machines
  90. Rethinking IDE Customization for Enhanced HAX: A Hyperdimensional Perspective
  91. ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
  92. Decoding News Bias: Multi Bias Detection in News Articles
  93. A Deep Positive-Negative Prototype Approach to Integrated Prototypical Discriminative Learning
  94. Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
  95. Generalization-Enhanced Few-Shot Object Detection in Remote Sensing
  96. IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors
  97. Hengqin-RA-v1: Advanced Large Language Model for Diagnosis and Treatment of Rheumatoid Arthritis with Dataset based Traditional Chinese Medicine
  98. Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera
  99. Neural Reflectance Fields for Radio-Frequency Ray Tracing
  100. Enhancing Contrastive Learning for Retinal Imaging via Adjusted Augmentation Scales
All 114
  1. GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
  2. Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Set
  3. A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
  4. Efficient Deployment of Large Language Models on Resource-constrained Devices
  5. Network Dynamics-Based Framework for Understanding Deep Neural Networks
  6. Towards Multimodal Metaphor Understanding: A Chinese Dataset and Model for Metaphor Mapping Identification
  7. Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding
  8. Framework for lung CT image segmentation based on UNet++
  9. MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance
  10. Scaling Laws for Floating Point Quantization Training
  11. Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluation
  12. Transfer learning via Regularized Linear Discriminant Analysis
  13. Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
  14. Towards the Anonymization of the Language Modeling