mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 10 May 2025

135 papers

  1. PRIME: Physics-Related Intelligent Mixture of Experts for Transistor Characteristics PredictionMixture-of-experts → Expert routing strategies
  2. Multi-modal Synthetic Data Training and Model Collapse: Insights from VLMs and Diffusion ModelsDiffusion models → Discrete and text diffusion +1
  3. OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal RetrievalRetrieval-augmented generation → Multimodal RAG
  4. JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 MinutesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  5. Learning Graph Representation of Agent DiffusersDiffusion models → Image generation, text-to-image and editing
  6. AI-CDA4All: Democratizing Cooperative Autonomous Driving for All Drivers via Affordable Dash-cam Hardware and Open-source AI SoftwareEnd-to-end autonomous driving → Cooperative and V2X driving
  7. Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  8. STRIVE: Structured Representation Integrating VLM Reasoning for Efficient Object NavigationLLM reasoning → Spatial and embodied reasoning +1
  9. Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeMixture-of-experts → MoE large language models
  10. Do Language Model Agents Align with Humans in Rating Visualizations? An Empirical StudyLLM agents and tool use → Multimodal and embodied agents +1
  11. Emotion-Qwen: A Unified Framework for Emotion and Vision UnderstandingMixture-of-experts → Multimodal MoE models
  12. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak AttacksDiffusion models → Robustness, privacy and adversarial aspects +1
  13. VTutor: An Animated Pedagogical Agent SDK that Provide Real Time Multi-Model FeedbackLLM agents and tool use → Educational agents and math problem solving
  14. Video Dataset Condensation with Diffusion ModelsDiffusion models → Video generation
  15. StableMotion: One-Step Motion Estimation with Diffusion PriorDiffusion models → Video generation
  16. Practical Reasoning Interruption Attacks on Reasoning Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  17. Boosting Neural Language Inference via Cascaded Interactive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  18. Learning Guarantee of Reward Modeling Using Deep Neural NetworksLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  19. Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and EvaluationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  20. POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language ModelsRetrieval-augmented generation → Privacy and security of RAG
  21. MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  22. References Indeed Matter? Reference-Free Preference Optimization for Conversational Query ReformulationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  23. REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated FeedbackSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  24. HDGlyph: A Hierarchical Disentangled Glyph-Based Framework for Long-Tail Text Rendering in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  25. Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning ModelLLM reasoning → Reasoning for agents, planning and code +2
  26. PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural NetworksLLM safety and security → Machine unlearning
  27. HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  28. System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User InjectionLLM safety and security → Prompt injection and agent security
  29. Video-Enhanced Offline Reinforcement Learning: A Model-Based ApproachOffline RL and imitation learning from data → Offline RL algorithms
  30. QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime ReconfigurationMixture-of-experts → Efficient MoE training and inference systems
  31. Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and EfficiencyState-space sequence models (S4, Mamba) → Core SSM architectures for language
  32. People Are Highly Cooperative with Large Language Models, Especially When Communication Is Possible or Following Human Interaction
  33. Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity
  34. More Expert-like Eye Gaze Movement Patterns are Related to Better X-ray Reading
  35. TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognition
  36. FMEnets: Flow, Material, and Energy networks for non-ideal plug flow reactor design
  37. Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language
  38. Signals from the Floods: AI-Driven Disaster Analysis through Multi-Source Data Fusion
  39. Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge
  40. A Computational Approach to Epilepsy Treatment: An AI-optimized Global Natural Product Prescription System
  41. OptiGait-LGBM: An Efficient Approach of Gait-based Person Re-identification in Non-Overlapping Regions
  42. Development of a WAZOBIA-Named Entity Recognition System
  43. Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints
  44. Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey
  45. Efficient Telecom Specific LLM: TSLAM-Mini with QLoRA and Digital Twin Data
  46. Getting Ready for the EU AI Act in Healthcare. A call for Sustainable AI Development and Deployment
  47. The Sound of Populism: Distinct Linguistic Features Across Populist Variants
  48. Utilizing LLMs to Investigate the Disputed Role of Evidence in Electronic Cigarette Health Policy Formation in Australia and the UK
  49. Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations
  50. Value Iteration with Guessing for Markov Chains and Markov Decision Processes
  51. Investigating Robotaxi Crash Severity with Geographical Random Forest and the Urban Environment
  52. Privacy-aware Berrut Approximated Coded Computing applied to general distributed learning
  53. Out-of-Sample Embedding with Proximity Data: Projection versus Restricted Reconstruction
  54. Boltzmann Classifier: A Thermodynamic-Inspired Approach to Supervised Learning
  55. M3CAD: Towards Generic Cooperative Autonomous Driving Benchmark
  56. Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers
  57. LineFlow: A Framework to Learn Active Control of Production Lines
  58. TPK: Trustworthy Trajectory Prediction Integrating Prior Knowledge For Interpretability and Kinematic Feasibility
  59. Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving
  60. Deeply Explainable Artificial Neural Network
  61. Activity and Subject Detection for UCI HAR Dataset with & without missing Sensor Data
  62. Efficient Parallelization of Message Passing Neural Network Potentials for Large-scale Molecular Dynamics
  63. SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images
  64. Beyond tildeO(√T) Constraint Violation for Online Convex Optimization with Adversarial Constraints
  65. Bi-level Mean Field: Dynamic Grouping for Large-Scale MARL
  66. RuleGenie: SIEM Detection Rule Set Optimization
  67. Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
  68. SCAN: Structured Capability Assessment and Navigation for LLMs
  69. Enhancing BERTopic with Intermediate Layer Representations
  70. Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search
  71. A Causality- and Frequency-Aware Deep Learning Framework for Wave Elevation Prediction Behind Floating Breakwaters
  72. A Novel Framework for Significant Wave Height Prediction based on Adaptive Feature Extraction Time-Frequency Network
  73. FNBench: Benchmarking Robust Federated Learning against Noisy Labels
  74. UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration
  75. A Short Overview of Multi-Modal Wi-Fi Sensing
  76. A Survey on Data-Driven Modeling of Human Drivers' Lane-Changing Decisions
  77. MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning
  78. METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection
  79. TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models
  80. Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
  81. Enfoque Odychess: Un m'etodo dial'ectico, constructivista y adaptativo para la ense~nanza del ajedrez con inteligencias artificiales generativas
  82. Dyn-D2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee
  83. Dataset Distillation with Probabilistic Latent Features
  84. Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification
  85. Exploring Multimodal Foundation AI and Expert-in-the-Loop for Sustainable Management of Wild Salmon Fisheries in Indigenous Rivers
  86. Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization
  87. Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models
  88. AI-Powered Anomaly Detection with Blockchain for Real-Time Security and Reliability in Autonomous Vehicles
  89. Dynamic Domain Information Modulation Algorithm for Multi-domain Sentiment Analysis
  90. CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs
  91. The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification
  92. Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models
  93. Integrating Explainable AI in Medical Devices: Technical, Clinical and Regulatory Insights and Recommendations
  94. Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation
  95. Using External knowledge to Enhanced PLM for Semantic Matching
  96. ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detection
  97. Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation
  98. Phase Transitions between Accuracy Regimes in L2 regularized Deep Neural Networks
  99. Feature Representation Transferring to Lightweight Models via Perception Coherence
  100. Batch Augmentation with Unimodal Fine-tuning for Multimodal Fusion of Large Language Models
All 135
  1. Evaluating LLM-Generated Q&A Test: a Student-Centered Study
  2. Optimal Transport for Machine Learners
  3. JAEGER: Dual-Level Humanoid Whole-Body Controller
  4. An tildeOptimal Differentially Private Learner for Concept Classes with VC Dimension 1
  5. TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification
  6. Compact and Efficient Neural Networks for Image Recognition Based on Learned 2D Separable Transform
  7. Two-Stage Random Alternation Framework for One-Shot Pansharpening
  8. GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images
  9. ElectricSight: 3D Hazard Monitoring for Power Lines Using Low-Cost Sensors
  10. Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search
  11. Quadrupedal Robot Skateboard Mounting via Reverse Curriculum Learning
  12. Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining
  13. Good Things Come in Pairs: Paired Autoencoders for Inverse Problems
  14. dcFCI: Robust Causal Discovery Under Latent Confounding, Unfaithfulness, and Mixed Data
  15. ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images
  16. TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition
  17. Online Feedback Efficient Active Target Discovery in Partially Observable Environments
  18. GBDTSVM: Combined Support Vector Machine and Gradient Boosting Decision Tree Framework for efficient snoRNA-disease association prediction
  19. High-Dimensional Importance-Weighted Information Criteria: Theory and Optimality
  20. Unmasking Deep Fakes: Leveraging Deep Learning for Video Authenticity Detection
  21. Improving Generalization of Medical Image Registration Foundation Model
  22. Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation
  23. Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design
  24. Provable Distributional Value Iteration under Partial Observability
  25. Edge-Enabled VIO with Long-Tracked Features for High-Accuracy Low-Altitude IoT Navigation
  26. Quantum Conflict Measurement in Decision Making for Out-of-Distribution Detection
  27. RESAR-BEV: An Explainable Progressive Residual Autoregressive Approach for Camera-Radar Fusion in BEV Segmentation
  28. Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
  29. On Definite Iterated Belief Revision with Belief Algebras
  30. Attention Mechanisms in Dynamical Systems: A Case Study with Predator-Prey Models
  31. PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations
  32. FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
  33. xGen-small Technical Report
  34. SmartPilot: A Multiagent CoPilot for Adaptive and Intelligent Manufacturing
  35. CompSLAM: Complementary Hierarchical Multi-Modal Localization and Mapping for Robot Autonomy in Underground Environments