mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 10 Jan 2025

221 papers

  1. Counterfactually Fair Reinforcement Learning via Sequential Data PreprocessingDeep reinforcement learning methods → RL for games and combinatorial optimization
  2. Multi-Agent Collaboration Mechanisms: A Survey of LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent SystemsLLM agents and tool use → Medical and scientific domain agents
  4. MinMo: A Multimodal Large Language Model for Seamless Voice InteractionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMsLLM reasoning → Multimodal reasoning
  6. Model Alignment SearchLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  7. GenMol: A Drug Discovery Generalist with Discrete DiffusionDiffusion models → Flow matching, time series and science
  8. From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster trainingDiffusion models → Diffusion and flow policies for robotics
  9. xLSTM-SENet: xLSTM for Single-Channel Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
  10. MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed VideosState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  11. Vehicle-in-Virtual-Environment (VVE) Based Autonomous Driving Function Development and Evaluation Methodology for Vulnerable Road User SafetyEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  12. Geometry and Optimization of Shallow Polynomial NetworksKnowledge distillation → General knowledge distillation methods
  13. Generate, Transduct, Adapt: Iterative Transduction with VLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. Investigating the Impact of Observation Space Design Choices On Training Reinforcement Learning Solutions for Spacecraft ProblemsDeep reinforcement learning methods → RL for robot navigation and UAV control
  15. Scalable Vision Language Model Training via High Quality Data CurationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  16. Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. Text-to-Edit: Controllable End-to-End Video Ad Creation via Multimodal LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  18. VideoRAG: Retrieval-Augmented Generation over Video CorpusRetrieval-augmented generation → Multimodal RAG
  19. Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  20. PersonaHOI: Effortlessly Improving Personalized Face with Human-Object Interaction GenerationDiffusion models → Image generation, text-to-image and editing
  21. Diffusion Models for Smarter UAVs: Decision-Making and ModelingDiffusion models → Diffusion and flow policies for robotics +1
  22. Real-Time Integrated Dispatching and Idle Fleet Steering with Deep Reinforcement Learning for A Meal Delivery PlatformDeep reinforcement learning methods → RL for games and combinatorial optimization
  23. Test-time Alignment of Diffusion Models without Reward Over-optimizationDiffusion models → Diffusion foundations and sampling +1
  24. Understanding Impact of Human Feedback via Influence FunctionsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  25. Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene GenerationDiffusion models → Video generation
  27. Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language ModelsLLM reasoning → Test-time compute and efficient thinking
  28. TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/VideosMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  29. Self-Evolving Critique Abilities in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
  30. Multi-Step Reasoning in Korean and the Emergent MirageLLM reasoning → Reasoning benchmarks and evaluation
  31. From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric SupervisionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  32. Multiagent Finetuning: Self Improvement with Diverse Reasoning ChainsLLM reasoning → Reasoning for agents, planning and code
  33. Overcoming Language Priors for Visual Question Answering Based on Knowledge DistillationKnowledge distillation → Multimodal distillation
  34. EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  35. Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  36. TAMER: A Test-Time Adaptive MoE-Driven Framework for EHR Representation LearningMixture-of-experts → Medical and biomedical MoE
  37. SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech
  38. A Capability Approach to AI Ethics
  39. A Frugal Model for Accurate Early Student Failure Prediction
  40. Low rank matrix completion and realization of graphs: results and problems
  41. Interpolation pour l'augmentation de donnees : Application `a la gestion des adventices de la canne a sucre a la Reunion
  42. Delay Neural Networks (DeNN) for exploiting temporal information in event-based datasets
  43. Do we actually understand the impact of renewables on electricity prices? A causal inference approach
  44. CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback
  45. An Explainable Pipeline for Machine Learning with Functional Data
  46. Real-Time Decision-Making for Digital Twin in Additive Manufacturing with Model Predictive Control using Time-Series Deep Neural Networks
  47. Impact of Data Breadth and Depth on Performance of Siamese Neural Network Model: Experiments with Three Keystroke Dynamic Datasets
  48. Analyzing Spatio-Temporal Dynamics of Dissolved Oxygen for the River Thames using Superstatistical Methods and Machine Learning
  49. Automated Heterogeneous Network learning with Non-Recursive Message Passing
  50. Learning-based Detection of GPS Spoofing Attack for Quadrotors
  51. Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
  52. Kolmogorov-Arnold networks for metal surface defect classification
  53. Using Pre-trained LLMs for Multivariate Time Series Forecasting
  54. Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention
  55. Robustness in the Face of Partial Identifiability in Reward Learning
  56. AFRIDOC-MT: Document-level MT Corpus for African Languages
  57. Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software
  58. Towards Robust Nonlinear Subspace Clustering: A Kernel Learning Approach
  59. Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts
  60. Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
  61. Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection
  62. Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
  63. On The Statistical Complexity of Offline Decision-Making
  64. MEt3R: Measuring Multi-View Consistency in Generated Images
  65. Aggregating Low Rank Adapters in Federated Fine-tuning
  66. On Creating A Brain-To-Text Decoder
  67. TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
  68. Understanding How Paper Writers Use AI-Generated Captions in Figure Caption Writing
  69. Towards Iris Presentation Attack Detection with Foundation Models
  70. Uncertainty Estimation for Path Loss and Radio Metric Models
  71. Tensorization of neural networks for improved privacy and interpretability
  72. LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network
  73. Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks
  74. Dafny as Verification-Aware Intermediate Language for Code Generation
  75. Visualizing Uncertainty in Image Guided Surgery a Review
  76. Aligning Brain Activity with Advanced Transformer Models: Exploring the Role of Punctuation in Semantic Processing
  77. Environmental large language model Evaluation (ELLE) dataset: A Benchmark for Evaluating Generative AI applications in Eco-environment Domain
  78. PROEMO: Prompt-Driven Text-to-Speech Synthesis Based on Emotion and Intensity Control
  79. Polarized Patterns of Language Toxicity and Sentiment of Debunking Posts on Social Media
  80. Underwater Image Enhancement using Generative Adversarial Networks: A Survey
  81. Large Language Models for Bioinformatics
  82. Multi-subject Open-set Personalization in Video Generation
  83. PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
  84. VideoAuteur: Towards Long Narrative Video Generation
  85. Machine Learning Force-Field Approach for Itinerant Electron Magnets
  86. Meta-Learning for Physically-Constrained Neural System Identification
  87. Efficient Transition State Searches by Freezing String Method with Graph Neural Network Potentials
  88. PySpatial: A High-Speed Whole Slide Image Pathomics Toolkit
  89. Multilingual Performance of a Multimodal Artificial Intelligence System on Multisubject Physics Concept Inventories
  90. Emergent Symbol-like Number Variables in Artificial Neural Networks
  91. Supervision policies can shape long-term risk management in general-purpose AI models
  92. CoDriveVLM: VLM-Enhanced Urban Cooperative Dispatching and Motion Planning for Future Autonomous Mobility on Demand Systems
  93. Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI
  94. Merging Feed-Forward Sublayers for Compressed Transformers
  95. Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
  96. Inferring Higher-Order Couplings with Neural Networks
  97. Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation
  98. From Conversation to Automation: Leveraging LLMs for Problem-Solving Therapy Analysis
  99. Explaining Deep Learning-based Anomaly Detection in Energy Consumption Data by Focusing on Contextually Relevant Data
  100. Towards Developing Socially Compliant Automated Vehicles: Advances, Expert Insights, and A Conceptual Framework
All 221
  1. All AI Models are Wrong, but Some are Optimal
  2. Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems
  3. Scale-up Unlearnable Examples Learning with High-Performance Computing
  4. Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations
  5. Explainable Federated Bayesian Causal Inference and Its Application in Advanced Manufacturing
  6. A monthly sub-national Harmonized Food Insecurity Dataset for comprehensive analysis and predictive modeling
  7. Distilling Calibration via Conformalized Credal Inference
  8. Personalized Language Model Learning on Text Data Without User Identifiers
  9. COMIX: Compositional Explanations using Prototypes
  10. Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination
  11. Enhancing, Refining, and Fusing: Towards Robust Multi-Scale and Dense Ship Detection
  12. Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
  13. MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets
  14. AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery
  15. A Holistically Point-guided Text Framework for Weakly-Supervised Camouflaged Object Detection
  16. Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
  17. Geometric-Based Nail Segmentation for Clinical Measurements
  18. How to Tune a Multilingual Encoder Model for Germanic Languages: A Study of PEFT, Full Fine-Tuning, and Language Adapters
  19. BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response
  20. Pose-independent 3D Anthropometry from Sparse Data
  21. CoNOAir: A Neural Operator for Forecasting Carbon Monoxide Evolution in Cities
  22. CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control
  23. SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples
  24. Learning to generate feasible graphs using graph grammars
  25. DeltaGNN: Graph Neural Network with Information Flow Control
  26. Self-Supervised Partial Cycle-Consistency for Multi-View Matching
  27. Minimizing Occlusion Effect on Multi-View Camera Perception in BEV with Multi-Sensor Fusion
  28. An Attention-Guided Deep Learning Approach for Classifying 39 Skin Lesion Types
  29. Constraining constructions with WordNet: pros and cons for the semantic annotation of fillers in the Italian Constructicon
  30. Addressing speaker gender bias in large scale speech translation systems
  31. Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing
  32. Deep Variational Sequential Monte Carlo for High-Dimensional Observations
  33. Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea
  34. A Brain Age Residual Biomarker (BARB): Leveraging MRI-Based Models to Detect Latent Health Conditions in U.S. Veterans
  35. Towards Early Prediction of Self-Supervised Speech Model Performance
  36. Model Inversion in Split Learning for Personalized LLMs: New Insights from Information Bottleneck Theory
  37. Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations
  38. Effective faking of verbal deception detection with target-aligned adversarial attacks
  39. Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers
  40. Universal-2-TF: Robust All-Neural Text Formatting for ASR
  41. Reusable specimen-level inference in computational pathology
  42. Soft regression trees: a model variant and a decomposition training algorithm
  43. A Multimodal Dataset for Enhancing Industrial Task Monitoring and Engagement Prediction
  44. Encoded Spatial Attribute in Multi-Tier Federated Learning
  45. Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2
  46. DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information
  47. Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks
  48. Towards Backdoor Stealthiness in Model Parameter Space
  49. LLMs Reproduce Stereotypes of Sexual and Gender Minorities
  50. Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction
  51. The New Anticipatory Governance Culture for Innovation: Regulatory Foresight, Regulatory Experimentation and Regulatory Learning
  52. Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms
  53. Binary Event-Driven Spiking Transformer
  54. Discovery of sustainable energy materials via the machine-learned material space
  55. Text2Playlist: Generating Personalized Playlists from Text on Deezer
  56. Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation
  57. Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs
  58. EDNet: Edge-Optimized Small Target Detection in UAV Imagery -- Faster Context Attention, Better Feature Fusion, and Hardware Acceleration
  59. Solving nonograms using Neural Networks
  60. TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios
  61. Collaborative Content Moderation in the Fediverse
  62. A Neighbor-based Approach to Pitch Ownership Models in Soccer
  63. Neural Network Verification is a Programming Language Challenge
  64. Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning
  65. ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability
  66. MRI Patterns of the Hippocampus and Amygdala for Predicting Stages of Alzheimer's Progression: A Minimal Feature Machine Learning Framework
  67. Identity-aware Feature Decoupling Learning for Clothing-change Person Re-identification
  68. Annealing Machine-assisted Learning of Graph Neural Network for Combinatorial Optimization
  69. "Cause" is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of "Causal Machine Learning"
  70. Orthogonal projection-based regularization for efficient model augmentation
  71. Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
  72. UltraRay: Introducing Full-Path Ray Tracing in Physics-Based Ultrasound Simulation
  73. AI-Driven Diabetic Retinopathy Screening: Multicentric Validation of AIDRSS in India
  74. IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages
  75. AdaPRL: Adaptive Pairwise Regression Learning with Uncertainty Estimation for Universal Regression Tasks
  76. Robust Counterfactual Explanations under Model Multiplicity Using Multi-Objective Optimization
  77. MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model
  78. Cryptanalysis of Cancelable Biometrics Vault
  79. UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping
  80. StructSR: Refuse Spurious Details in Real-World Image Super-Resolution
  81. STHFL: Spatio-Temporal Heterogeneous Federated Learning
  82. rmlnomogram: An R package to construct an explainable nomogram for any machine learning algorithms
  83. Conditional Diffusion Model for Electrical Impedance Tomography
  84. Halal or Not: Knowledge Graph Completion for Predicting Cultural Appropriateness of Daily Products
  85. Deontic Temporal Logic for Formal Verification of AI Ethics
  86. Controlling Large Language Models Through Concept Activation Vectors
  87. Development and Comparison of Model-Based and Data-Driven Approaches for the Prediction of the Mechanical Properties of Lattice Structures
  88. Locality-aware Gaussian Compression for Fast and High-quality Rendering
  89. CognoSpeak: an automatic, remote assessment of early cognitive decline in real-world conversational speech
  90. Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directions
  91. Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models
  92. Covariate Dependent Mixture of Bayesian Networks
  93. LLVD: LSTM-based Explicit Motion Modeling in Latent Space for Blind Video Denoising
  94. ELENA: Epigenetic Learning through Evolved Neural Adaptation
  95. Diving Deep: Forecasting Sea Surface Temperatures and Anomalies
  96. Element-wise Attention Is All You Need
  97. ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
  98. Super-class guided Transformer for Zero-Shot Attribute Classification
  99. Zero-shot Shark Tracking and Biometrics from Aerial Imagery
  100. How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond
  101. EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model
  102. Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages
  103. eKalibr: Dynamic Intrinsic Calibration for Event Cameras From First Principles of Events
  104. UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation
  105. Deep Reversible Consistency Learning for Cross-modal Retrieval
  106. Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection
  107. Network Diffuser for Placing-Scheduling Service Function Chains with Inverse Demonstration
  108. LPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds
  109. TransPlace: Transferable Circuit Global Placement via Graph Neural Network
  110. Learning to Measure Quantum Neural Networks
  111. Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks
  112. A Bring-Your-Own-Model Approach for ML-Driven Storage Placement in Warehouse-Scale Computers
  113. Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
  114. Efficient Representations for High-Cardinality Categorical Variables in Machine Learning
  115. Interpretable Enzyme Function Prediction via Residue-Level Detection
  116. Iconicity in Large Language Models
  117. Automating Date Format Detection for Data Visualization
  118. Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport
  119. Regularized Top-k: A Bayesian Framework for Gradient Sparsification
  120. HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection
  121. The Impact of Model Scaling on Seen and Unseen Language Performance