mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 30 Aug 2024

222 papers

  1. Bridging User Dynamics: Transforming Sequential Recommendations with Schr"odinger Bridge and Diffusion ModelsDiffusion models → Diffusion recommenders
  2. OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed TomographyMultimodal LLMs / vision-language models → Medical vision-language models
  3. ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  4. MAPWise: Evaluating Vision-Language Models for Advanced Map QueriesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  5. Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding DataMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  6. Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse ObservationsDiffusion models → Inverse problems and image restoration
  7. Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal GraphsLLM reasoning → Causal reasoning in LLMs
  8. Sequence to Sequence Reward Modeling: Improving RLHF by Language FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  9. MultiMath: Bridging Visual and Mathematical Reasoning for Large Language ModelsLLM reasoning → Multimodal reasoning
  10. Dynamic Depth Decoding: Faster Speculative Decoding for LLMsEfficient LLM inference and serving → Speculative decoding
  11. How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face RecognitionKnowledge distillation → General knowledge distillation methods
  12. Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory controlDeep reinforcement learning methods → RL for autonomous driving and traffic
  13. Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy LeakageLLM safety and security → Membership inference attacks
  14. Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model EvolutionDiffusion models → Image generation, text-to-image and editing
  15. Flexible and Effective Mixing of Large Language Models into a Mixture of Domain ExpertsMixture-of-experts → MoE large language models
  16. UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban ScenariosMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Using Quantum Solved Deep Boltzmann Machines to Increase the Data Efficiency of RL AgentsDeep reinforcement learning methods → Quantum reinforcement learning
  18. Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path ReasoningLLM reasoning → Hallucination detection and mitigation +1
  19. Flow Matching for Optimal Reaction Coordinates of Biomolecular SystemDiffusion models → Flow matching, time series and science
  20. VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  21. RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-GuidanceDiffusion models → Diffusion foundations and sampling
  22. Stochastic Layer-Wise Shuffle for Improving Vision Mamba TrainingState-space sequence models (S4, Mamba) → Vision Mamba backbones
  23. MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → Generation and context integration +1
  24. Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision TransformerEfficient LLM inference and serving → Token pruning and merging for ViTs
  25. Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XLDiffusion models → Inverse problems and image restoration
  26. Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM SamplingLLM reasoning → Test-time compute and efficient thinking
  27. Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question AnsweringLLM reasoning → Multimodal reasoning +1
  28. Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  29. Safety Layers in Aligned Large Language Models: The Key to LLM SecurityLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  30. A Tighter Convergence Proof of Reverse Experience ReplayDeep reinforcement learning methods → Deep RL algorithms and representations
  31. Tool-Assisted Agent on SQL Inspection and Refinement in Real-World ScenariosLLM agents and tool use → Web, search, and research agents
  32. AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. Beyond Preferences in AI AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  34. The Sample-Communication Complexity Trade-off in Federated Q-LearningDeep reinforcement learning methods → RL for energy, networks and operations
  35. Contrastive Learning with Synthetic PositivesDiffusion models → Diffusion foundations and sampling
  36. Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  37. From Latent to Engine Manifolds: Analyzing ImageBind's Multimodal Embedding Space
  38. Towards Empathetic Conversational Recommender Systems
  39. Effective Monitoring of Online Decision-Making Algorithms in Digital Intervention Implementation
  40. "Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration
  41. 3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving
  42. Harnessing Artificial Intelligence for Wildlife Conservation
  43. LSTM Recurrent Neural Networks for Cybersecurity Named Entity Recognition
  44. Achieving Responsible AI through ESG: Insights and Recommendations from Industry Engagement
  45. Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
  46. Higher order definition of causality by optimally conditioned transfer entropy
  47. Deep Neural Implicit Representation of Accessibility for Multi-Axis Manufacturing
  48. Data is missing again -- Reconstruction of power generation data using k-Nearest Neighbors and spectral graph theory
  49. On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic
  50. Credit Scores: Performance and Equity
  51. Box2Flow: Instance-based Action Flow Graphs from Videos
  52. Quantum Machine Learning for Anomaly Detection in Consumer Electronics
  53. REFFLY: Melody-Constrained Lyrics Editing Model
  54. OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters
  55. Reframing Data Value for Large Language Models Through the Lens of Plausibility
  56. RealFace -- Pedestrian Face Dataset
  57. Simple stochastic processes behind Menzerath's Law
  58. Exact Recovery Guarantees for Parameterized Nonlinear System Identification Problem under Sparse Disturbances or Semi-Oblivious Attacks
  59. Towards a dynamical model of English vowels. Evidence from diphthongisation
  60. Finding frames with BERT: A transformer-based approach to generic news frame detection
  61. Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content
  62. Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
  63. The Artificial Intelligence Act: critical overview
  64. AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning
  65. DiverseDialogue: A Methodology for Designing Chatbots with Human-Like Diversity
  66. Reconstructing unsteady flows from sparse, noisy measurements with a physics-constrained convolutional neural network
  67. Improving the Region of Attraction of a Multi-rotor UAV by Estimating Unknown Disturbances
  68. Building Better Datasets: Seven Recommendations for Responsible Design from Dataset Creators
  69. Medical Report Generation Is A Multi-label Classification Problem
  70. Unveiling Processing--Property Relationships in Laser Powder Bed Fusion: The Synergy of Machine Learning and High-throughput Experiments
  71. TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functions
  72. One-Frame Calibration with Siamese Network in Facial Action Unit Recognition
  73. Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale
  74. Self-Supervised Learning for Building Robust Pediatric Chest X-ray Classification Models
  75. Can Large Language Models Address Open-Target Stance Detection?
  76. Learning Latent Space Dynamics with Model-Form Uncertainties: A Stochastic Reduced-Order Modeling Approach
  77. ProGRes: Prompted Generative Rescoring on ASR n-Best
  78. Structuring Quantitative Image Analysis with Object Prominence
  79. Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs
  80. RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning
  81. MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection
  82. The creative psychometric item generator: a framework for item generation and validation using large language models
  83. Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
  84. A Generative Adversarial Network-based Method for LiDAR-Assisted Radar Image Enhancement
  85. Inference, interference and invariance: How the Quantum Fourier Transform can help to learn from data
  86. Facilitating phenotyping from clinical texts: the medkit library
  87. Deep Neural Networks for Predicting Recurrence and Survival in Patients with Esophageal Cancer After Surgery
  88. Learning-Based Finite Element Methods Modeling for Complex Mechanical Systems
  89. LLMs Prompted for Graphs: Hallucinations and Generative Capabilities
  90. Developing an End-to-End Framework for Predicting the Social Communication Severity Scores of Children with Autism Spectrum Disorder
  91. Common Steps in Machine Learning Might Hinder The Explainability Aims in Medicine
  92. Speaker Tagging Correction With Non-Autoregressive Language Models
  93. From Semantics to Hierarchy: A Hybrid Euclidean-Tangent-Hyperbolic Space Model for Temporal Knowledge Graph Reasoning
  94. Invariant Representation Guided Multimodal Sentiment Decoding with Sequential Variation Regularization
  95. Graph neural network-based lithium-ion battery state of health estimation using partial discharging curve
  96. HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
  97. SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists
  98. DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model
  99. Text-to-Speech for Unseen Speakers via Low-Complexity Discrete Unit-Based Frame Selection
  100. Advancing Multi-talker ASR Performance with Large Language Models
All 222
  1. CLOCR-C: Context Leveraging OCR Correction with Pre-trained Language Models
  2. CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusion
  3. Open-Vocabulary Action Localization with Iterative Visual Prompting
  4. Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes
  5. Getting Inspiration for Feature Elicitation: App Store- vs. LLM-based Approach
  6. Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcare
  7. Fairness-Aware Estimation of Graphical Models
  8. Continual learning with the neural tangent ensemble
  9. Bayesian Optimization for Non-Convex Two-Stage Stochastic Optimization Problems
  10. LASSO-MOGAT: A Multi-Omics Graph Attention Framework for Cancer Classification
  11. MoRe Fine-Tuning with 10x Fewer Parameters
  12. EMPOWER: Embodied Multi-role Open-vocabulary Planning with Online Grounding and Execution
  13. NDP: Next Distribution Prediction as a More Broad Target
  14. Exploring the Impact of Environmental Pollutants on Multiple Sclerosis Progression
  15. Leveraging Graph Neural Networks to Forecast Electricity Consumption
  16. Look, Learn and Leverage (L3): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment
  17. Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain
  18. Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
  19. C-RADAR: A Centralized Deep Learning System for Intrusion Detection in Software Defined Networks
  20. Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
  21. AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
  22. Language-guided Scale-aware MedSegmentor for Lesion Segmentation in Medical Imaging
  23. rerankers: A Lightweight Python Library to Unify Ranking Methods
  24. Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method
  25. Evaluating Reliability in Medical DNNs: A Critical Analysis of Feature and Confidence-Based OOD Detection
  26. Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features
  27. Impact of ChatGPT on the writing style of condensed matter physicists
  28. Modularity in Transformers: Investigating Neuron Separability & Specialization
  29. Investigating Neuron Ablation in Attention Heads: The Case for Peak Activation Centering
  30. Bridging Domain Knowledge and Process Discovery Using Large Language Models
  31. Fair Best Arm Identification with Fixed Confidence
  32. Structuring a Training Strategy to Robustify Perception Models with Realistic Image Augmentations
  33. Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation
  34. Hybridizing Base-Line 2D-CNN Model with Cat Swarm Optimization for Enhanced Advanced Persistent Threat Detection
  35. Accelerating the discovery of steady-states of planetary interior dynamics with machine learning
  36. BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities
  37. Risk-averse Total-reward MDPs with ERM and EVaR
  38. DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields
  39. Minimax and Communication-Efficient Distributed Best Subset Selection with Oracle Property
  40. The Transferability of Downsamped Sparse Graph Convolutional Networks
  41. Equation identification for fluid flows via physics-informed neural networks
  42. Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approach
  43. Self-supervised learning for crystal property prediction via denoising
  44. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
  45. Abstracted Gaussian Prototypes for True One-Shot Concept Learning
  46. (Un)supervised Learning of Maximal Lyapunov Functions
  47. Categorical data clustering: 25 years beyond K-modes
  48. A nonlinear elasticity model in computer vision
  49. AI-Driven Intrusion Detection Systems (IDS) on the ROAD Dataset: A Comparative Analysis for Automotive Controller Area Network (CAN)
  50. A methodological framework for Resilience as a Service (RaaS) in multimodal urban transportation networks
  51. CondSeg: Ellipse Estimation of Pupil and Iris via Conditioned Segmentation
  52. OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping
  53. How Could Generative AI Support Compliance with the EU AI Act? A Review for Safe Automated Driving Perception
  54. Geometry of Lightning Self-Attention: Identifiability and Dimension
  55. Democratizing AI in Africa: FL for Low-Resource Edge Devices
  56. NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar
  57. Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
  58. Covariance-corrected Whitening Alleviates Network Degeneration on Imbalanced Classification
  59. Reasoning with maximal consistent signatures
  60. "Benefit Game: Alien Seaweed Swarms" -- Real-time Gamification of Digital Seaweed Ecology
  61. Short-term Wind Speed Forecasting for Power Integration in Smart Grids based on Hybrid LSSVM-SVMD Method
  62. Causal Reasoning in Software Quality Assurance: A Systematic Review
  63. Hybrid Classification-Regression Adaptive Loss for Dense Object Detection
  64. Improving Extraction of Clinical Event Contextual Properties from Electronic Health Records: A Comparative Study
  65. Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance Analysis
  66. Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
  67. SafeTail: Efficient Tail Latency Optimization in Edge Service Scheduling via Computational Redundancy Management
  68. EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs
  69. Learning Multi-Target TDOA Features for Sound Event Localization and Detection
  70. Efficient Testable Learning of General Halfspaces with Adversarial Label Noise
  71. The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
  72. Deep Feature Embedding for Tabular Data
  73. Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG Diagnosis
  74. Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
  75. GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring
  76. The Many Faces of Optimal Weak-to-Strong Learning
  77. Painless Federated Learning: An Interplay of Line-Search and Extrapolation
  78. RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification
  79. Leveraging Digital Twin Technologies for Public Space Protection and Vulnerability Assessment
  80. TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation
  81. Controllable Edge-Type-Specific Interpretation in Multi-Relational Graph Neural Networks for Drug Response Prediction
  82. Exploring User Acceptance Of Portable Intelligent Personal Assistants: A Hybrid Approach Using PLS-SEM And fsQCA
  83. Efficient Estimation of Unique Components in Independent Component Analysis by Matrix Representation
  84. Multi-centric AI Model for Unruptured Intracranial Aneurysm Detection and Volumetric Segmentation in 3D TOF-MRI
  85. Sparse Uncertainty-Informed Sampling from Federated Streaming Data
  86. Understanding the User: An Intent-Based Ranking Dataset
  87. Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms
  88. UTrack: Multi-Object Tracking with Uncertain Detections
  89. FissionVAE: Federated Non-IID Image Generation with Latent Space and Decoder Decomposition
  90. Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
  91. Approximately Invertible Neural Network for Learned Image Compression
  92. Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning
  93. Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning
  94. Instant Adversarial Purification with Adversarial Consistency Distillation
  95. A Survey of the Self Supervised Learning Mechanisms for Vision Transformers
  96. LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model
  97. BTMuda: A Bi-level Multi-source unsupervised domain adaptation framework for breast cancer diagnosis
  98. Estimating Conditional Average Treatment Effects via Sufficient Representation Learning
  99. Can We Leave Deepfake Data Behind in Training Deepfake Detector?
  100. Text-to-Image Generation Via Energy-Based CLIP
  101. CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection
  102. ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
  103. From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs
  104. InkubaLM: A small language model for low-resource African languages
  105. Error-controlled non-additive interaction discovery in machine learning models
  106. Disease Classification and Impact of Pretrained Deep Convolution Neural Networks on Diverse Medical Imaging Datasets across Imaging Modalities
  107. Improving Time Series Classification with Representation Soft Label Smoothing
  108. Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications
  109. A Scalable k-Medoids Clustering via Whale Optimization Algorithm
  110. From Model Explanation to Data Misinterpretation: A Cautionary Analysis of Post Hoc Explainers in Business Research
  111. 2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Features
  112. Cross Fusion RGB-T Tracking with Bi-directional Adapter
  113. Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer
  114. Technical Report of HelixFold3 for Biomolecular Structure Prediction
  115. Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms
  116. Point Neuron Learning: A New Physics-Informed Neural Network Architecture
  117. MemLong: Memory-Augmented Retrieval for Long Text Modeling
  118. UserSumBench: A Benchmark Framework for Evaluating User Summarization Approaches
  119. Causal Representation-Based Domain Generalization on Gaze Estimation
  120. HiTSR: A Hierarchical Transformer for Reference-based Super-Resolution
  121. Transient Fault Tolerant Semantic Segmentation for Autonomous Driving
  122. An Empirical Study of Scaling Laws for Transfer