mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 5 Apr 2025

128 papers

  1. Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  2. Impact of Price Inflation on Algorithmic Collusion Through Reinforcement Learning AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  3. Evaluating Graphical Perception with Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code GenerationLLM agents and tool use → Software engineering coding agents
  5. Towards Understanding and Improving Refusal in Compressed Models via Mechanistic InterpretabilityMechanistic interpretability → Steering and probing for LLM safety
  6. Investigating and Mitigating Stereotype-aware Unfairness in LLM-based RecommendationsLLM reasoning → LLM reasoning for recommendation
  7. MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  8. OrbitZoo: Real Orbital Systems Challenges for Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  9. JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image RestorationEnd-to-end autonomous driving → VLMs for autonomous driving
  10. Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and ResourcesLLM reasoning → Reasoning benchmarks and evaluation
  11. Reasoning on Multiple Needles In A HaystackLLM reasoning → Reasoning benchmarks and evaluation
  12. A General Peg-in-Hole Assembly Policy Based on Domain Randomized Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  13. Multi-identity Human Image Animation with Structural Video DiffusionDiffusion models → Video generation
  14. PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic RefinementLLM reasoning → Reasoning benchmarks and evaluation
  15. SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  16. TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative ConnectionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  17. Corrected with the Latest Version: Make Robust Asynchronous Federated Learning PossibleKnowledge distillation → Federated, robust and private distillation
  18. Among Us: A Sandbox for Measuring and Detecting Agentic DeceptionLLM agents and tool use → Social simulation and multi-agent debate +1
  19. Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question AnsweringRetrieval-augmented generation → Multimodal RAG
  20. QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry ErrorsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  21. Stochastic, Dynamic, Fluid Autonomy in Agentic AI: Implications for Authorship, Inventorship, and LiabilityLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video ModelsDiffusion models → Video generation
  23. An Explicit Syllogistic Legal Reasoning Framework for Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  24. ADAPT: Actively Discovering and Adapting to Preferences for any TaskLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  25. Rethinking Reflection in Pre-TrainingLLM reasoning → Test-time compute and efficient thinking
  26. DiTaiListener: Controllable High Fidelity Listener Video Generation with DiffusionDiffusion models → Audio, speech and music
  27. Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
  28. TALLMesh: a simple application for performing Thematic Analysis with Large Language Models
  29. Mozualization: Crafting Music and Visual Representation with Multimodal AI
  30. Large Language Model-Based Knowledge Graph System Construction for Sustainable Development Goals: An AI-Based Speculative Design Perspective
  31. Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability
  32. SLOs-Serve: Optimized Serving of Multi-SLO LLMs
  33. Efficient Evaluation of Large Language Models via Collaborative Filtering
  34. How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs
  35. Psychological Health Knowledge-Enhanced LLM-based Social Network Crisis Intervention Text Transfer Recognition Method
  36. Resurrecting Socrates in the Age of AI: A Study Protocol for Evaluating a Socratic Tutor to Support Research Question Development in Higher Education
  37. Improving Early Prediction of Type 2 Diabetes Mellitus with ECG-DiaNet: A Multimodal Neural Network Leveraging Electrocardiogram and Clinical Risk Factors
  38. Quantum Adaptive Self-Attention for Quantum Transformer Models
  39. Using ensemble methods of machine learning to predict real estate prices
  40. Sigma: A dataset for text-to-code semantic parsing with statistical analysis
  41. Generative Market Equilibrium Models with Stable Adversarial Learning via Reinforcement
  42. AI-induced sexual harassment: Investigating Contextual Characteristics and User Reactions of Sexual Harassment by a Companion Chatbot
  43. Dynamic Hedging Strategies in Derivatives Markets with LLM-Driven Sentiment and News Analytics
  44. 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS
  45. Cross-Asset Risk Management: Integrating LLMs for Real-Time Monitoring of Equity, Fixed Income, and Currency Markets
  46. CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
  47. Foundation Models for Environmental Science: A Survey of Emerging Frontiers
  48. Could AI Trace and Explain the Origins of AI-Generated Images and Text?
  49. Beyond the Hype: Embeddings vs. Prompting for Multiclass Classification Tasks
  50. A Comparative Study of Explainable AI Methods: Model-Agnostic vs. Model-Specific Approaches
  51. negativas: a prototype for searching and classifying sentential negation in speech data
  52. Randomised Splitting Methods and Stochastic Gradient Descent
  53. ADA-Net: Attention-Guided Domain Adaptation Network with Contrastive Learning for Standing Dead Tree Segmentation Using Aerial Imagery
  54. Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
  55. Improving Chronic Kidney Disease Detection Efficiency: Fine Tuned CatBoost and Nature-Inspired Algorithms with Explainable AI
  56. LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators
  57. Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition
  58. Task load dependent decision referrals for joint binary classification in human-automation teams
  59. Randomised Postiterations for Calibrated BayesCG
  60. From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making
  61. Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest
  62. Task-based Loss Functions in Computer Vision: A Comprehensive Review
  63. oneDAL Optimization for ARM Scalable Vector Extension: Maximizing Efficiency for High-Performance Data Science
  64. Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
  65. Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications
  66. Resilience of Vision Transformers for Domain Generalisation in the Presence of Out-of-Distribution Noisy Images
  67. TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation
  68. A Perplexity and Menger Curvature-Based Approach for Similarity Evaluation of Large Language Models
  69. Adaptive Elicitation of Latent Information Using Natural Language
  70. Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction
  71. The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
  72. GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill
  73. Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
  74. Towards Principled Learning for Re-ranking in Recommender Systems
  75. AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
  76. SDEIT: Semantic-Driven Electrical Impedance Tomography
  77. Variational autoencoders understand knot topology
  78. Digital Gene: Learning about the Physical World through Analytic Concepts
  79. Vehicle Acceleration Prediction Considering Environmental Influence and Individual Driving Behavior
  80. CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation
  81. GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models
  82. Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
  83. STEP: Staged Parameter-Efficient Pre-training for Large Language Models
  84. My Life in Artificial Intelligence: People, anecdotes, and some lessons learnt
  85. Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making
  86. Introducing COGENT3: An AI Architecture for Emergent Cognition
  87. Predicting Soil Macronutrient Levels: A Machine Learning Approach Models Trained on pH, Conductivity, and Average Power of Acid-Base Solutions
  88. Precise Legal Sentence Boundary Detection for Retrieval at Scale: NUPunkt and CharBoundary
  89. Scaling Federated Learning Solutions with Kubernetes for Synthesizing Histopathology Images
  90. Decision-oriented joint optimization of evidence fusion based on event-conditioned credibility
  91. EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection
  92. Improving Question Embeddings with Cognitive Representation Optimization for Knowledge Tracing
  93. Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patients
  94. Overcoming the Identity Mapping Problem in Self-Supervised Hyperspectral Anomaly Detection
  95. Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
  96. Lifting Factor Graphs with Some Unknown Factors for New Individuals
  97. Towards An Efficient and Effective En Route Travel Time Estimation Framework
  98. DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning
  99. A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models
  100. Scalable Robust Bayesian Co-Clustering with Compositional ELBOs
All 128
  1. Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator
  2. Enforcement Agents: Enhancing Accountability and Resilience in Multi-Agent AI Frameworks
  3. Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan
  4. Mapping at First Sense: A Lightweight Neural Network-Based Indoor Structures Prediction Method for Robot Autonomous Exploration
  5. VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation
  6. Deep-Learning-Directed Preventive Dynamic Security Control via Coordinated Demand Response
  7. Learning-Based Multi-Criteria Decision Model for Site Selection Problems
  8. PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networks
  9. FISH-Tuning: Enhancing PEFT Methods with Fisher Information
  10. A Survey of Pathology Foundation Model: Progress and Future Directions
  11. Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
  12. myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging
  13. UCS: A Universal Model for Curvilinear Structure Segmentation
  14. Disparate Privacy Vulnerability: Targeted Attribute Inference Attacks and Defenses
  15. Contrastive and Variational Approaches in Self-Supervised Learning for Complex Data Mining
  16. OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
  17. Simultaneous Motion And Noise Estimation with Event Cameras
  18. Artificial intelligence application in lymphoma diagnosis: from Convolutional Neural Network to Vision Transformer
  19. Window Token Concatenation for Efficient Visual Large Language Models
  20. A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains
  21. Computational Efficient and Minimax Optimal Nonignorable Matrix Completion
  22. Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inference
  23. Spatially-Heterogeneous Causal Bayesian Networks for Seismic Multi-Hazard Estimation: A Variational Approach with Gaussian Processes and Normalizing Flows
  24. Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAVTarget Detection
  25. Foundation Models for Time Series: A Survey
  26. Machine Learning Reveals Composition Dependent Thermal Stability in Halide Perovskites
  27. Edge Approximation Text Detector
  28. View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans