mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 4 Jul 2025

217 papers

  1. A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent ModellingLLM reasoning → Multimodal reasoning
  2. VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMsLLM reasoning → Multimodal reasoning +1
  3. Advancing network resilience theories with symbolized reinforcement learningDeep reinforcement learning methods → RL for games and combinatorial optimization
  4. Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation AnalysisDiffusion models → Diffusion foundations and sampling
  5. StreamDiT: Real-Time Streaming Text-to-Video GenerationDiffusion models → Video generation
  6. FACM: Flow-Anchored Consistency ModelsDiffusion models → Flow matching, time series and science
  7. Less is More: Empowering GUI Agent with Context-Aware SimplificationLLM agents and tool use → GUI and mobile agents
  8. FAROS: Fair Graph Generation via Attribute Switching MechanismsDiffusion models → Flow matching, time series and science
  9. Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. MemOS: A Memory OS for AI SystemRetrieval-augmented generation → Generation and context integration
  11. Controlling Thinking Speed in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  12. Towards Unified Neurosymbolic Reasoning on Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
  13. STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and BenchmarkingLLM agents and tool use → Web, search, and research agents
  14. TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data SelectionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. Recon, Answer, Verify: Agents in Search of TruthLLM agents and tool use → Web, search, and research agents
  16. TRACE: Training and Inference-Time Interpretability Analysis for Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  17. Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  18. Dynamic Multimodal Prototype Learning in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box SettingDiffusion models → Robustness, privacy and adversarial aspects +1
  20. SecureT2I: No More Unauthorized Manipulation on AI Generated Images from PromptsDiffusion models → Robustness, privacy and adversarial aspects
  21. Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPyLLM safety and security → Prompt injection and agent security
  22. EvoAgentX: An Automated Framework for Evolving Agentic WorkflowsLLM agents and tool use → Software engineering coding agents
  23. Multi-Hop Reasoning for Question Answering with Hyperbolic RepresentationsLLM reasoning → Knowledge- and tool-augmented reasoning
  24. Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)Retrieval-augmented generation → RAG robustness and adaptive retrieval
  25. Kinetic Langevin Diffusion for Crystalline Materials GenerationDiffusion models → Flow matching, time series and science
  26. Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical SegmentationLLM reasoning → Clinical and biomedical applications
  27. Learning to Translate Ambiguous Terminology by Preference Optimization on Post-EditsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. A Universal Approach to Feature Representation in Dynamic Task Assignment ProblemsDeep reinforcement learning methods → RL for energy, networks and operations
  29. Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual DescriptorMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  30. Decoupled Relative Learning Rate SchedulesMixture-of-experts → Expert routing strategies
  31. Reinforcement Learning-based Feature Generation Algorithm for Scientific DataDeep reinforcement learning methods → RL with diffusion and flow models
  32. AI-VaxGuide: An Agentic RAG-Based LLM for Vaccination DecisionsLLM agents and tool use → Medical and scientific domain agents
  33. ObjectRL: An Object-Oriented Reinforcement Learning CodebaseDeep reinforcement learning methods → Deep RL algorithms and representations
  34. BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning DatasetLLM reasoning → Multimodal reasoning +1
  35. Multi-Agent Reasoning for Cardiovascular Imaging Phenotype AnalysisLLM reasoning → Clinical and biomedical applications +1
  36. Helping CLIP See Both the Forest and the Trees: A Decomposition and Description ApproachMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  37. Unlearning the Noisy Correspondence Makes CLIP More RobustMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  38. Action Robust Reinforcement Learning via Optimal Adversary Aware Policy OptimizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  39. Adaptive Gate-Aware Mamba Networks for Magnetic Resonance FingerprintingState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  40. Effects of structure on reasoning in instance-level Self-DiscoverLLM reasoning → Test-time compute and efficient thinking
  41. Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less RiskyLLM agents and tool use → Tool learning and function calling
  42. Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  43. GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine TranslationLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. Dyn-O: Building Structured World Models with Object-Centric RepresentationsWorld models → Latent predictive world models
  45. CPKD: Clinical Prior Knowledge-Constrained Diffusion Models for Surgical Phase Recognition in Endoscopic Submucosal DissectionDiffusion models → Medical imaging and segmentation
  46. LogicGuard: Improving Embodied LLM agents through Temporal Logic based CriticsLLM agents and tool use → General LLM agent frameworks and benchmarks
  47. MolVision: Molecular Property Prediction with Vision Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  48. NOVO: Unlearning-Compliant Vision TransformersLLM safety and security → Machine unlearning
  49. Investigating Redundancy in Multimodal Large Language Models with Multiple Vision EncodersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  50. MoDA: Multi-modal Diffusion Architecture for Talking Head GenerationDiffusion models → Audio, speech and music
  51. CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMsLLM reasoning → Reasoning for agents, planning and code +1
  52. KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  53. On Jailbreaking Quantized Language Models Through Fault Injection AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  54. Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at ScaleRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  55. Inclusive Review on Advances in Masked Human Face Recognition Technologies
  56. All-atom inverse protein folding through discrete flow matching
  57. The Free Will Equation: Quantum Field Analogies for AGI
  58. Surface EMG Profiling in Parkinson's Disease: Advancing Severity Assessment with GCN-SVM
  59. Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance
  60. Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives
  61. SFATTI: Spiking FPGA Accelerator for Temporal Task-driven Inference -- A Case Study on MNIST
  62. Efficient Triple Modular Redundancy for Reliability Enhancement of DNNs Using Explainable AI
  63. Recurrent Expansion: A Pathway Toward the Next Generation of Deep Learning
  64. Energy Management for Renewable-Colocated Artificial Intelligence Data Centers
  65. Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation
  66. Compressing Deep Neural Networks Using Explainable AI
  67. Beyond classical and contemporary models: a transformative AI framework for student dropout prediction in distance learning using RAG, Prompt engineering, and Cross-modal fusion
  68. Temporal Window Smoothing of Exogenous Variables for Improved Time Series Prediction
  69. Chat2SPaT: A Large Language Model Based Tool for Automating Traffic Signal Control Plan Management
  70. Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging
  71. CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
  72. Hungary and AI: efforts and opportunities in comparison with Singapore
  73. ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy
  74. Distributed Equivariant Graph Neural Networks for Large-Scale Electronic Structure Prediction
  75. Participatory Evolution of Artificial Life Systems via Semantic Feedback
  76. F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding
  77. Economic Evaluation of LLMs
  78. MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search
  79. Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition
  80. RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation
  81. IMPACT: Importance-Aware Activation Space Reconstruction
  82. Zero Memory Overhead Approach for Protecting Vision Transformer Parameters
  83. Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts
  84. Certified Coil Geometry Learning for Short-Range Magnetic Actuation and Spacecraft Docking Application
  85. Generating Novelty in Open-World Multi-Agent Strategic Board Games
  86. Learning Dark Souls Combat Through Pixel Input With Neuroevolution
  87. Efficient and Effective Query Context-Aware Learning-to-Rank Model for Sequential Recommendation
  88. Effective Capacitance Modeling Using Graph Neural Networks
  89. FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
  90. Optimizing UAV Trajectories via a Simplified Close Enough TSP Approach
  91. Alpay Algebra IV: Symbiotic Semantics and the Fixed-Point Convergence of Observer Embeddings
  92. Skewed Score: A statistical framework to assess autograders
  93. Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach
  94. Causal Evidence for the Primordiality of Colors in Trans-Neptunian Objects
  95. Sequential Regression Learning with Randomized Algorithms
  96. ChestGPT: Integrating Large Language Models and Vision Transformers for Disease Detection and Localization in Chest X-Rays
  97. Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
  98. Determination of Particle-Size Distributions from Light-Scattering Measurement Using Constrained Gaussian Process Regression
  99. Inverse Synthetic Aperture Fourier Ptychography
  100. Transforming Calabi-Yau Constructions: Generating New Calabi-Yau Manifolds with Transformers
All 217
  1. 3D PixBrush: Image-Guided Local Texture Synthesis
  2. Differentially private scale testing via rank transformations and percentile modifications
  3. Roadmap for using large language models (LLMs) to accelerate cross-disciplinary research with an example from computational biology
  4. Predicting Business Angel Early-Stage Decision Making Using AI
  5. Can LLMs Play O uAn Quan Game? A Study of Multi-Step Planning and Decision Making
  6. CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
  7. Computationally efficient non-Intrusive pre-impact fall detection system
  8. Sign Spotting Disambiguation using Large Language Models
  9. SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
  10. Graph Neural Networks for Electricity Load Forecasting
  11. A Resource Efficient Quantum Kernel
  12. On the rankability of visual embeddings
  13. Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning
  14. Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data
  15. Interaction Techniques that Encourage Longer Prompts Can Improve Psychological Ownership when Writing with AI
  16. Single vs. Multiple Branches in DeepONet and S-DeepONet: Network Architecture Follows Coupling in Multiphysics Systems
  17. Detecting and explaining clinical-omics inconsistencies to improve patient cohort stratification: an application to Parkinson's disease
  18. Segmentation of separated Lumens in 3D CTA images of Aortic Dissection
  19. Disentangling the Roles of Representation and Selection in Data Pruning
  20. Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion
  21. Dual-Alignment Knowledge Retention for Continual Medical Image Segmentation
  22. Large Language Models for Combinatorial Optimization: A Systematic Review
  23. From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Saptiotemporal Dynamics in Brain Signal Analysis
  24. Scientific Machine Learning of Chaotic Systems Learns Reduced-Order Equations for Neural Populations
  25. Localising Dropout Variance in Twin Networks
  26. EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge
  27. Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery
  28. MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI
  29. RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
  30. SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
  31. Articulatory clarity and variability before and after surgery for tongue cancer
  32. From Street Form to Spatial Justice: Explaining Urban Exercise Inequality via a Triadic SHAP-Informed Framework
  33. 2.5D Object Detection for Intelligent Roadside Infrastructure
  34. Simplifying Graph Kernels for Efficient
  35. Predicting Asphalt Pavement Friction Using Texture-Based Image Indicator
  36. An Efficient Deep Learning Framework for Brain Stroke Diagnosis Using Computed Tomography Images
  37. DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering
  38. H2HTalk: Evaluating Large Language Models as Emotional Companion
  39. Foundation versus Domain-specific Models: Performance Comparison, Fusion, and Explainability in Face Recognition
  40. CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation
  41. PhenoBench: A Comprehensive Benchmark for Cell Phenotyping
  42. Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding
  43. Generating Synthetic Relational Tabular Data via Structural Causal Models
  44. Limits of Safe AI Deployment: Differentiating Oversight and Control
  45. UWB TDoA Error Correction using Transformers: Patching and Positional Encoding Strategies
  46. A Flexible Instruction Set Architecture for Efficient GEMMs
  47. Information-Bottleneck Driven Binary Neural Network for Change Detection
  48. Four Shades of Life Sciences: A Dataset for Disinformation Detection in the Life Sciences
  49. PhotIQA: A photoacoustic image data set with image quality ratings
  50. REAL: Benchmarking Abilities of Large Language Models for Housing Transactions and Services
  51. Molecular Machine Learning Using Euler Characteristic Transforms
  52. Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right
  53. Radar Velocity Transformer: Single-scan Moving Object Segmentation in Noisy Radar Point Clouds
  54. Evaluating the Evaluators: Trust in Adversarial Robustness Tests
  55. Radar Tracker: Moving Instance Tracking in Sparse and Noisy Radar Point Clouds
  56. Improving Social Determinants of Health Documentation in French EHRs Using Large Language Models
  57. Multi-Level Fusion Graph Neural Network for Molecule Property Prediction
  58. Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
  59. Instance Generation for Patient-to-room Assignment and Admission Scheduling Based on Real Hospital Data
  60. Hybrid-View Attention Network for Clinically Significant Prostate Cancer Classification in Transrectal Ultrasound
  61. SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation
  62. Tourist arrival forecasting with game-theoretic social influence weighting and deep learning
  63. Graph Repairs with Large Language Models: An Empirical Study
  64. Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
  65. Artificial intelligence in drug discovery: A comprehensive review with a case study on hyperuricemia, gout arthritis, and hyperuricemic nephropathy
  66. On the Effectiveness of the z-Transform Method in Quadratic Optimization
  67. Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images
  68. Learning Normals of Noisy Points by Local Gradient-Aware Surface Filtering
  69. Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
  70. Absolute Evaluation Measures for Machine Learning: A Survey
  71. MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection
  72. LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization
  73. Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
  74. WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia
  75. Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices
  76. Backtesting Sentiment Signals for Trading: Evaluating the Viability of Alpha Generation from Sentiment Analysis
  77. SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge
  78. UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis
  79. Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
  80. DESign: Dynamic Context-Aware Convolution and Efficient Subnet Regularization for Continuous Sign Language Recognition
  81. De-Fake: Style based Anomaly Deepfake Detection
  82. Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
  83. Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking
  84. NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval
  85. Mirror in the Model: Ad Banner Image Generation via Reflective Multi-LLM and Multi-modal Agents
  86. Cancer cytoplasm segmentation in hyperspectral cell image with data augmentation
  87. Source-Free Domain Adaptation via Multi-view Contrastive Learning
  88. Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization
  89. Towards Interpretable PolSAR Image Classification: Polarimetric Scattering Mechanism Informed Concept Bottleneck and Kolmogorov-Arnold Network
  90. Partial Label Learning for Automated Theorem Proving
  91. Personalized Image Generation from an Author Writing Style
  92. MPX: Mixed Precision Training for JAX
  93. Causal Discovery for Irregularly Time Series with Consistency Guarantees
  94. Scaffolding Recursive Divergence and Convergence in Story Ideation
  95. MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
  96. Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations
  97. Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model
  98. LRM-1B: Towards Large Routing Model
  99. MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs
  100. Zero-shot Inexact CAD Model Alignment from a Single Image
  101. Global Variational Inference Enhanced Robust Domain Adaptation
  102. Do Tensorized Large-Scale Spatiotemporal Dynamic Atmospheric Data Exhibit Low-Rank Properties?
  103. Memory Mosaics at scale
  104. Conformal Information Pursuit for Interactively Guiding Large Language Models
  105. Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators
  106. ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization
  107. Event2Audio: Event-Based Optical Vibration Sensing
  108. LILI clustering algorithm: Limit Inferior Leaf Interval Integrated into Causal Forest for Causal Interference
  109. Dual-frequency Selected Knowledge Distillation with Statistical-based Sample Rectification for PolSAR Image Classification
  110. GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
  111. LACONIC: A 3D Layout Adapter for Controllable Image Creation
  112. ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis
  113. RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
  114. Toward Efficient Speech Emotion Recognition via Spectral Learning and Attention
  115. Subject Invariant Contrastive Learning for Human Activity Recognition
  116. A Vision-Based Closed-Form Solution for Measuring the Rotation Rate of an Object by Tracking One Point
  117. A Lie-algebraic perspective on Tree-Adjoining Grammars