mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 5 Aug 2024

232 papers

  1. Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  2. Generative Organizational Behavior Simulation using Large Language Model based Autonomous Agents: A Holacracy PerspectiveLLM agents and tool use → Social simulation and multi-agent debate
  3. AppAgent v2: Advanced Agent for Flexible Mobile InteractionsLLM agents and tool use → GUI and mobile agents
  4. LLM Agents Improve Semantic Code SearchLLM agents and tool use → Software engineering coding agents
  5. MR Optimized Reconstruction of Simultaneous Multi-Slice Imaging Using Diffusion ModelDiffusion models → Medical imaging and segmentation
  6. DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial LearningKnowledge distillation → Multimodal distillation
  7. Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  8. SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference ServingEfficient LLM inference and serving → Serving systems and request scheduling
  9. Strong and weak alignment of large language models with human valuesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  10. Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  11. VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical KnowledgeMultimodal LLMs / vision-language models → Medical vision-language models
  12. A Framework for Fine-Tuning LLMs using Heterogeneous FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. Creating a Taxonomy for Retrieval Augmented Generation ApplicationsRetrieval-augmented generation → RAG pipeline design and evaluation
  14. Mitigating Malicious Attacks in Federated Learning via Confidence-aware DefenseLLM safety and security → Federated unlearning and poisoning
  15. Development of REGAI: Rubric Enabled Generative Artificial IntelligenceRetrieval-augmented generation → RAG pipeline design and evaluation
  16. Entity Retrieval for Answering Entity-Centric QuestionsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  17. MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion ModelsDiffusion models → Audio, speech and music
  19. RCDM: Enabling Robustness for Conditional Diffusion ModelDiffusion models → Diffusion foundations and sampling
  20. Self-Taught EvaluatorsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  21. Integrating Model-Based Footstep Planning with Model-Free Reinforcement Learning for Dynamic Legged LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  22. Context-aware Mamba-based Reinforcement Learning for social robot navigationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
  23. Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  24. SEAS: Self-Evolving Adversarial Safety Optimization for Large Language ModelsSynthetic data and self-improvement for LLMs → Safety of self-evolving systems +1
  25. LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and MambaDiffusion models → Medical imaging and segmentation +1
  26. Backward explanations via redefinition of predicatesDeep reinforcement learning methods → Interpretable and logic-guided RL
  27. Progressively Label Enhancement for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect InformationLLM agents and tool use → Reinforcement learning for LLM agents
  29. RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  30. Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental DistractionsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  31. Explaining Reinforcement Learning: A Counterfactual Shapley Values ApproachDeep reinforcement learning methods → Interpretable and logic-guided RL
  32. UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noiseDeep reinforcement learning methods → RL for games and combinatorial optimization
  34. From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and FutureLLM agents and tool use → Software engineering coding agents
  35. VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor EnvironmentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  36. Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought DecodingLLM reasoning → Knowledge- and tool-augmented reasoning
  37. Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  38. A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  39. Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  40. Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  41. ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. Evaluating Vision-Language Models for Zero-Shot Detection, Classification, and Association of Motorcycles, Passengers, and HelmetsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  43. SpecRover: Code Intent Extraction via LLMsLLM agents and tool use → Software engineering coding agents
  44. REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative GenerationDiffusion models → Diffusion foundations and sampling
  46. ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual ReasoningLLM reasoning → Multimodal reasoning
  47. Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  48. Unsupervised Domain Adaption Harnessing Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  49. Strategic AI adoption in SMEs: A Prescriptive Framework
  50. Target-Dependent Multimodal Sentiment Analysis Via Employing Visual-to Emotional-Caption Translation Network using Visual-Caption Pairs
  51. MetaEnzyme: Meta Pan-Enzyme Learning for Task-Adaptive Redesign
  52. VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features
  53. TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementation
  54. AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired People
  55. A Conceptual Framework for Ethical Evaluation of Machine Learning Systems
  56. A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series
  57. Tree species classification at the pixel-level using deep learning and multispectral time series in an imbalanced context
  58. Enhancing Supply Chain Visibility with Knowledge Graphs and Large Language Models
  59. Empathic Responding for Digital Interpersonal Emotion Regulation via Content Recommendation
  60. The Literature Review Network: An Explainable Artificial Intelligence for Systematic Literature Reviews, Meta-analyses, and Method Development
  61. Biomimetic Machine Learning approach for prediction of mechanical properties of Additive Friction Stir Deposited Aluminum alloys based walled structures
  62. MaterioMiner -- An ontology-based text mining dataset for extraction of process-structure-property entities
  63. XMainframe: A Large Language Model for Mainframe Modernization
  64. Winning Amazon KDD Cup'24
  65. Towards Semantic Markup of Mathematical Documents via User Interaction
  66. Batching BPE Tokenization Merges
  67. Quantum Transfer Learning for MNIST Classification Using a Hybrid Quantum-Classical Approach
  68. miniCTX: Neural Theorem Proving with (Long-)Contexts
  69. Toward Smart Scheduling in Tapis
  70. On The Stability of Moral Preferences: A Problem with Computational Elicitation Methods
  71. Multistain Pretraining for Slide Representation Learning in Pathology
  72. Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercises
  73. Active Learning for WBAN-based Health Monitoring
  74. Heterogeneous graph attention network improves cancer multiomics integration
  75. Evaluating Posterior Probabilities: Decision Theory, Proper Scoring Rules, and Calibration
  76. GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformers
  77. Mini-batch Estimation for Deep Cox Models: Statistical Foundations and Practical Guidance
  78. Interpretation of the Intent Detection Problem as Dynamics in a Low-dimensional Space
  79. Training a multilayer dynamical spintronic network with standard machine learning tools to perform time series classification
  80. DaCapo: a modular deep learning framework for scalable 3D image segmentation
  81. Adaptive Learning for Quantum Linear Regression
  82. Setting the duration of online A/B experiments
  83. The Impact of Environment Configurations on the Stability of AI-Enabled Systems
  84. Wave-RVFL: A Randomized Neural Network Based on Wave Loss Function
  85. Steady Continuous Monitoring is (Just Barely) Impossible for Tests of Unbounded Length
  86. Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
  87. SiCo: An Interactive Size-Controllable Virtual Try-On Approach for Informed Decision-Making
  88. Deciphering Air Travel Disruptions: A Machine Learning Approach
  89. Sparse Deep Learning Models with the ℓ1 Regularization
  90. Examining Gender and Power on Wikipedia Through Face and Politeness
  91. Algorithm-Informed Graph Neural Networks for Leakage Detection and Localization in Water Distribution Networks
  92. Gaussian Mixture based Evidential Learning for Stereo Matching
  93. Lesion Elevation Prediction from Skin Images Improves Diagnosis
  94. GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths
  95. Segmentation Style Discovery: Application to Skin Lesion Images
  96. LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory
  97. LR-Net: A Lightweight and Robust Network for Infrared Small Target Detection
  98. Refined Infrared Small Target Detection Scheme with Single-Point Supervision
  99. From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
  100. 4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models
All 232
  1. ConDL: Detector-Free Dense Image Matching
  2. Dimensionality Reduction and Nearest Neighbors for Improving Out-of-Distribution Detection in Medical Image Segmentation
  3. Classification of Raw MEG/EEG Data with Detach-Rocket Ensemble: An Improved ROCKET Algorithm for Multivariate Time Series Analysis
  4. A Novel Hybrid Approach for Tornado Prediction in the United States: Kalman-Convolutional BiLSTM with Multi-Head Attention
  5. Privacy-Safe Iris Presentation Attack Detection
  6. KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics example
  7. MDM: Advancing Multi-Domain Distribution Matching for Automatic Modulation Recognition Dataset Synthesis
  8. A Review on Organ Deformation Modeling Approaches for Reliable Surgical Navigation using Augmented Reality
  9. Automatic Voice Identification after Speech Resynthesis using PPG
  10. Enhancing Medical Learning and Reasoning Systems: A Boxology-Based Comparative Analysis of Design Patterns
  11. Scribble-Based Interactive Segmentation of Medical Hyperspectral Images
  12. SnapE -- Training Snapshot Ensembles of Link Prediction Models
  13. Bayesian Kolmogorov Arnold Networks (Bayesian_KANs): A Probabilistic Approach to Enhance Accuracy and Interpretability
  14. PSNE: Efficient Spectral Sparsification Algorithms for Scaling Network Embedding
  15. Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning
  16. Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
  17. Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
  18. On Using Quasirandom Sequences in Machine Learning for Model Weight Initialization
  19. Detection of Compromised Functions in a Serverless Cloud Environment
  20. Command-line Obfuscation Detection using Small Language Models
  21. Interactive 3D Medical Image Segmentation with SAM 2
  22. VidGen-1M: A Large-Scale Dataset for Text-to-video Generation
  23. YOWOv3: An Efficient and Generalized Framework for Human Action Detection and Recognition
  24. Language Model Can Listen While Speaking
  25. Learning rheological parameters of non-Newtonian fluids from velocimetry data
  26. BioMamba: Domain-Adaptive Biomedical Language Models
  27. AI-Driven Strategies for Reducing Student Withdrawal -- A Study of EMU Student Stopout
  28. Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection
  29. Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization
  30. Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition
  31. Operational range bounding of spectroscopy models with anomaly detection
  32. Artificial Intelligence for Public Health Surveillance in Africa: Applications and Opportunities
  33. Contrastive Learning-based Multi Modal Architecture for Emoticon Prediction by Employing Image-Text Pairs
  34. Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification
  35. HQOD: Harmonious Quantization for Object Detection
  36. Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditing
  37. MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
  38. Process-constrained batch Bayesian approaches for yield optimization in multi-reactor systems
  39. The Role of Functional Muscle Networks in Improving Hand Gesture Perception for Human-Machine Interfaces
  40. LMEMs for post-hoc analysis of HPO Benchmarking
  41. Single-tap Latency Reduction with Single- or Double- tap Prediction
  42. OneLove beyond the field -- A few-shot pipeline for topic and sentiment analysis during the FIFA World Cup in Qatar
  43. Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
  44. Black-Box Adversarial Attacks on LLM-Based Code Completion
  45. Estimating Pore Location of PBF-LB/M Processes with Segmentation Models
  46. Automatic rating of incomplete hippocampal inversions evaluated across multiple cohorts
  47. HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions
  48. LiCoEval: Evaluating LLMs on License Compliance in Code Generation
  49. Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection
  50. On the influence of dependent features in classification problems: a game-theoretic perspective
  51. Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
  52. Fairness and Bias Mitigation in Computer Vision: A Survey
  53. An investigation into the causes of race bias in AI-based cine CMR segmentation
  54. Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach
  55. Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
  56. Long Input Benchmark for Russian Analysis
  57. On Probabilistic Embeddings in Optimal Dimension Reduction
  58. Attenuation-adjusted deep learning of pore defects in 2D radiographs of additive manufacturing powders
  59. Boosting Memory Efficiency in Transfer Learning for High-Resolution Medical Image Classification
  60. FE-Adapter: Adapting Image-based Emotion Classifiers to Videos
  61. Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation
  62. Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
  63. PENDRAM: Enabling High-Performance and Energy-Efficient Processing of Deep Neural Networks through a Generalized DRAM Data Mapping Policy
  64. Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
  65. Terracorder: Sense Long and Prosper
  66. Enhancing AI-based Generation of Software Exploits with Contextual Information
  67. Tensorial template matching for fast cross-correlation with rotations and its application for tomography
  68. CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration
  69. Graphical Modelling without Independence Assumptions for Uncentered Data
  70. MaFreeI2P: A Matching-Free Image-to-Point Cloud Registration Paradigm with Active Camera Pose Retrieval
  71. Strategic Federated Learning: Application to Smart Meter Data Clustering
  72. Cross Pseudo Supervision Framework for Sparsely Labelled Geospatial Images
  73. Perfect Information Monte Carlo with Postponing Reasoning
  74. A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models
  75. Operationalizing Contextual Integrity in Privacy-Conscious Assistants
  76. The NPU-ASLP System Description for Visual Speech Recognition in CNVSRC 2024
  77. StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations
  78. On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'
  79. Quantile Regression using Random Forest Proximities
  80. RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders
  81. Earth System Data Cubes: Avenues for advancing Earth system research
  82. Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices
  83. Machine Learning Applications in Medical Prognostics: A Comprehensive Review
  84. An approach to optimize inference of the DIART speaker diarization pipeline
  85. Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
  86. Infusing Environmental Captions for Long-Form Video Language Grounding
  87. Explosive neural networks via higher-order interactions in curved statistical manifolds
  88. A Lean Transformer Model for Dynamic Malware Analysis and Detection
  89. Optimization of Iterative Blind Detection based on Expectation Maximization and Belief Propagation
  90. On the Robustness of Malware Detectors to Adversarial Samples
  91. Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped Convolution
  92. Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization
  93. SNFinLLM: Systematic and Nuanced Financial Domain Adaptation of Chinese Large Language Models
  94. Network Fission Ensembles for Low-Cost Self-Ensembles
  95. Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
  96. Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation
  97. Heart Rate and its Variability from Short-term ECG Recordings as Biomarkers for Detecting Mild Cognitive Impairment in Indian Population
  98. SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes
  99. Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages
  100. Spin glass model of in-context learning
  101. Joint-Motion Mutual Learning for Pose Estimation in Videos
  102. Cascading Refinement Video Denoising with Uncertainty Adaptivity
  103. Hardware Aware Ensemble Selection for Balancing Predictive Accuracy and Cost
  104. DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting
  105. Geometric Algebra Meets Large Language Models: Instruction-Based Transformations of Separate Meshes in 3D, Interactive and Controllable Scenes
  106. COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark
  107. StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement
  108. One-Shot Collaborative Data Distillation
  109. Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts
  110. VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking
  111. To Aggregate or Not to Aggregate. That is the Question: A Case Study on Annotation Subjectivity in Span Prediction
  112. Advancing Post-OCR Correction: A Comparative Study of Synthetic Data
  113. Hierarchical Clustering using Reversible Binary Cellular Automata for High-Dimensional Data
  114. Contrastive Learning and Abstract Concepts: The Case of Natural Numbers
  115. A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoders
  116. Methods to improve run time of hydrologic models: opportunities and challenges in the machine learning era
  117. Pula: Training Large Language Models for Setswana
  118. Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings
  119. A Multi-Source Heterogeneous Knowledge Injected Prompt Learning Method for Legal Charge Prediction
  120. Large Language Model Aided QoS Prediction for Service Recommendation
  121. Cross-modulated Attention Transformer for RGBT Tracking
  122. Climate-Driven Doubling of U.S. Maize Loss Probability: Interactive Simulation with Neural Network Monte Carlo
  123. More Than Positive and Negative: Communicating Fine Granularity in Medical Diagnosis
  124. Is Large Language Model Good at Database Knob Tuning? A Comprehensive Experimental Evaluation
  125. Source-Free Domain-Invariant Performance Prediction
  126. Multi-level Traffic-Responsive Tilt Camera Surveillance through Predictive Correlated Online Learning
  127. MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization
  128. Evaluating the Performance of Large Language Models for SDG Mapping (Technical Report)
  129. Synergistic Learning with Multi-Task DeepONet for Efficient PDE Problem Solving
  130. CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs
  131. Dense Feature Interaction Network for Image Inpainting Localization
  132. AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines