mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 3 May 2025

122 papers

  1. Advancing AI Research Assistants with Expert-Involved LearningMultimodal LLMs / vision-language models → Medical vision-language models
  2. Adaptive Token Boundaries: Integrating Human Chunking Mechanisms into Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  4. Accelerating Large Language Model Reasoning via Speculative SearchLLM reasoning → Test-time compute and efficient thinking
  5. Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMsLLM safety and security → Jailbreaking
  6. Discrete Spatial Diffusion: Intensity-Preserving Diffusion ModelingDiffusion models → Diffusion foundations and sampling
  7. LookAlike: Consistent Distractor Generation in Math MCQsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  8. Rethinking Score Distilling Sampling for 3D Editing and GenerationDiffusion models → 3D, point cloud and scene generation
  9. DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic FusionWorld models → World models for autonomous driving +1
  10. Mitigating Group-Level Fairness Disparities in Federated Visual Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  11. Analytic Energy-Guided Policy Optimization for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  12. Enhancing the Learning Experience: Using Vision-Language Models to Generate Questions for Educational VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  13. An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  14. PosePilot: Steering Camera Pose for Generative World Models with Self-supervised DepthWorld models → World models for autonomous driving
  15. World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular NetworksWorld models → World models for autonomous driving +1
  16. RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Inducing Robustness in a 2 Dimensional Direct Preference Optimization ParadigmLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. Topology-Aware CLIP Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report ClassifiersKnowledge distillation → Distillation for medical imaging
  20. RAGAR: Retrieval Augmented Personalized Image Generation Guided by RecommendationRetrieval-augmented generation → Multimodal RAG
  21. Structured Prompting and Feedback-Guided Reasoning with LLMs for Data InterpretationLLM reasoning → Reasoning benchmarks and evaluation
  22. The Memory Paradox: Why Our Brains Need Knowledge in an Age of AI
  23. An Affective-Taxis Hypothesis for Alignment and Interpretability
  24. Detecting Musical Deepfakes
  25. Fair Clustering with Clusterlets
  26. ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
  27. VideoLLM Benchmarks and Evaluation: A Survey
  28. Sentiment-Aware Recommendation Systems in E-Commerce: A Review from a Natural Language Processing Perspective
  29. MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation
  30. In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry
  31. Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments
  32. Memory Assisted LLM for Personalized Recommendation System
  33. DRSLF: Double Regularized Second-Order Low-Rank Representation for Web Service QoS Prediction
  34. RESAnything: Attribute Prompting for Arbitrary Referring Segmentation
  35. Understanding University Students' Use of Generative AI: The Roles of Demographics and Personality Traits
  36. Neural Orchestration for Multi-Agent Systems: A Deep Learning Framework for Optimal Agent Selection in Multi-Domain Task Environments
  37. Multi-Scale Graph Learning for Anti-Sparse Downscaling
  38. Runtime Anomaly Detection for Drones: An Integrated Rule-Mining and Unsupervised-Learning Approach
  39. Explainability by design: an experimental analysis of the legal coding process
  40. HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
  41. Faster logconcave sampling from a cold start in high dimension
  42. GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels
  43. Unemployment Dynamics Forecasting with Machine Learning Regression Models
  44. OT-Talk: Animating 3D Talking Head with Optimal Transportation
  45. Semantic Intelligence: Integrating GPT-4 with A Planning in Low-Cost Robotics
  46. GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting
  47. BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
  48. From Players to Champions: A Generalizable Machine Learning Approach for Match Outcome Prediction with Insights from the FIFA World Cup
  49. CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation
  50. DiTOX: Fault Detection and Localization in the ONNX Optimizer
  51. Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Images
  52. Automated Sentiment Classification and Topic Discovery in Large-Scale Social Media Streams
  53. CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture
  54. PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications
  55. Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network
  56. Humans can learn to detect AI-generated texts, or at least learn when they can't
  57. Towards Trustworthy Federated Learning with Untrusted Participants
  58. Visual enhancement and 3D representation for underwater scenes: a review
  59. Positional Attention for Efficient BERT-Based Named Entity Recognition
  60. PQS-BFL: A Post-Quantum Secure Blockchain-based Federated Learning Framework
  61. Bayesian learning of the optimal action-value function in a Markov decision process
  62. Intra-Layer Recurrence in Transformers for Language Modeling
  63. Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
  64. MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization
  65. CVVNet: A Cross-Vertical-View Network for Gait Recognition
  66. Multi-Scale Target-Aware Representation Learning for Fundus Image Enhancement
  67. Rank-One Modified Value Iteration
  68. PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach
  69. Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
  70. An LSTM-PINN Hybrid Method to the specific problem of population forecasting
  71. Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp
  72. textitNew News: System-2 Fine-tuning for Robust Integration of New Knowledge
  73. Conformal Prediction for Indoor Positioning with Correctness Coverage Guarantees
  74. 3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment
  75. Surrogate to Poincar'e inequalities on manifolds for dimension reduction in nonlinear feature spaces
  76. Not Every Tree Is a Forest: Benchmarking Forest Types from Satellite Remote Sensing
  77. Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows
  78. Distinguishing AI-Generated and Human-Written Text Through Psycholinguistic Analysis
  79. AquaGS: Fast Underwater Scene Reconstruction with SfM-Free Gaussian Splatting
  80. A Multimodal Framework for Explainable Evaluation of Soft Skills in Educational Environments
  81. Privacy Preserving Machine Learning Model Personalization through Federated Personalized Learning
  82. TV-SurvCaus: Dynamic Representation Balancing for Causal Survival Analysis
  83. Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition
  84. Enhancing Black-Litterman Portfolio via Hybrid Forecasting Model Combining Multivariate Decomposition and Noise Reduction
  85. Observation Compression in Rate-Limited Closed-Loop Distributed ISAC Systems: From Signal Reconstruction to Control
  86. Continuous Filtered Backprojection by Learnable Interpolation Network
  87. Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement
  88. Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Models
  89. LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction
  90. Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias
  91. A dynamic view of some anomalous phenomena in SGD
  92. Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion
  93. Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients
  94. Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs
  95. CLOG-CD: Curriculum Learning based on Oscillating Granularity of Class Decomposed Medical Image Classification
  96. Learning Multi-frame and Monocular Prior for Estimating Geometry in Dynamic Scenes
  97. PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems
  98. Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models
  99. PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activation
  100. Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
All 122
  1. Vision and Intention Boost Large Language Model in Long-Term Action Anticipation
  2. Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings
  3. PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking
  4. Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning
  5. Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarking
  6. Automated ARAT Scoring Using Multimodal Video Analysis, Multi-View Fusion, and Hierarchical Bayesian Models: A Clinician Study
  7. Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representations
  8. Adaptively Point-weighting Curriculum Learning
  9. Soft-Masked Semi-Dual Optimal Transport for Partial Domain Adaptation
  10. Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
  11. A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency
  12. WaveInst: A Frequency-Domain Enhanced Network for Fine-Grained Thin Tree Trunk Extraction in Forest Scenes
  13. T-REX: Vision-Based System for Autonomous Leaf Detection and Grasp Estimation
  14. Causally Fair Node Classification on Non-IID Graph Data
  15. Human-AI Governance (HAIG): A Trust-Utility Approach
  16. Toward Onboard AI-Enabled Solutions to Space Object Detection for Space Sustainability
  17. Scalable Speed-ups for the SMS-EMOA from a Simple Aging Strategy
  18. A Dual-Task Synergy-Driven Generalization Framework for Pancreatic Cancer Segmentation in CT Scans
  19. Identifying Doppelganger Active Galactic Nuclei across redshifts from spectroscopic surveys
  20. Fast Likelihood-Free Parameter Estimation for L'evy Processes
  21. Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth
  22. Morello: Compiling Fast Neural Networks with Dynamic Programming and Spatial Compression