mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 2 Sep 2024

221 papers

  1. Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  2. Democratizing MLLMs in Healthcare: TinyLLaVA-Med for Efficient Healthcare Diagnostics in Resource-Constrained SettingsMultimodal LLMs / vision-language models → Medical vision-language models
  3. An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
  4. Agentic Society: Merging skeleton from real world and texture from Large Language ModelLLM agents and tool use → Social simulation and multi-agent debate
  5. EEG-Language Pretraining for Highly Label-Efficient Clinical PhenotypingMultimodal LLMs / vision-language models → Medical vision-language models
  6. MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  7. Efficient and Scalable Estimation of Tool Representations in Vector SpaceLLM agents and tool use → Tool learning and function calling
  8. A Financial Time Series Denoiser Based on Diffusion ModelDiffusion models → Flow matching, time series and science
  9. Reward Augmentation in Reinforcement Learning for Testing Distributed SystemsDeep reinforcement learning methods → RL training of language and agent models
  10. Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert PruningMixture-of-experts → MoE large language models
  11. Compatible Gradient Approximations for Actor-Critic AlgorithmsDeep reinforcement learning methods → RL theory and sample complexity
  12. Real-Time Recurrent Learning using Trace Units in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  13. Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  14. ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. Membership Inference Attacks Against In-Context LearningLLM safety and security → Membership inference attacks
  16. Imitating Language via Scalable Inverse Reinforcement LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs +1
  17. Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled GuidanceDiffusion models → Diffusion foundations and sampling
  18. Language Models Benefit from Preparation with Elicited KnowledgeLLM reasoning → Prompting and chain-of-thought reasoning
  19. SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image GenerationDiffusion models → Image generation, text-to-image and editing
  20. Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image EditingDiffusion models → Image generation, text-to-image and editing
  21. LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusionDiffusion models → Medical imaging and segmentation
  22. Conversational Complexity for Assessing Risk in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  23. Revisiting Safe Exploration in Safe Reinforcement learningDeep reinforcement learning methods → Safe and constrained RL
  24. Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM InferenceEfficient LLM inference and serving → Prompt and context compression
  25. MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge DistillationKnowledge distillation → Multimodal distillation
  26. OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion ModelDiffusion models → Diffusion foundations and sampling
  27. CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP ModelsLLM safety and security → Backdoor and data poisoning attacks
  28. Backdoor Defense through Self-Supervised and Generative LearningLLM safety and security → Backdoor and data poisoning attacks
  29. Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text InformationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  30. Integrating End-to-End and Modular Driving Approaches for Online Corner Case Detection in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  31. Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  32. TempMe: Video Temporal Token Merging for Efficient Text-Video RetrievalEfficient LLM inference and serving → Visual token pruning in multimodal models
  33. Understanding Multimodal Hallucination with Parameter-Free Representation AlignmentMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  34. FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  35. Memoryless Algorithmic Collusion: Sure to Fail, Slow to FallDeep reinforcement learning methods → RL for games and combinatorial optimization
  36. Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous BatchingMixture-of-experts → Efficient MoE training and inference systems +1
  37. Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual LearningDiffusion models → Robustness, privacy and adversarial aspects
  38. AI Olympics challenge with Evolutionary Soft Actor CriticDeep reinforcement learning methods → RL for games and combinatorial optimization
  39. DS MYOLO: A Reliable Object Detector Based on SSMs for Driving ScenariosState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  40. DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image EditingDiffusion models → 3D, point cloud and scene generation
  41. Affordance-based Robot Manipulation with Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  42. Accelerated Multi-objective Task Learning using Modified Q-learning AlgorithmDeep reinforcement learning methods → RL theory and sample complexity
  43. From Bird's-Eye to Street View: Crafting Diverse and Condition-Aligned Images with Latent Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
  44. Evolution of Social Norms in LLM Agents using Natural LanguageLLM agents and tool use → Social simulation and multi-agent debate
  45. 3D Priors-Guided Diffusion for Blind Face RestorationDiffusion models → Inverse problems and image restoration
  46. Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language InterfacesLLM agents and tool use → Reinforcement learning for LLM agents
  47. Solving Integrated Process Planning and Scheduling Problem via Graph Neural Network Based Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  48. Self-Judge: Selective Instruction Following with Alignment Self-EvaluationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  49. ToolACE: Winning the Points of LLM Function CallingLLM agents and tool use → Tool learning and function calling
  50. MarsCode Agent: AI-native Automated Bug FixingLLM agents and tool use → Software engineering coding agents
  51. Beyond Parameter Count: Implicit Bias in Soft Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
  52. Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics
  53. TRACE: Transformer-based user Representations from Attributed Clickstream Event sequences
  54. MITHOS: Interactive Mixed Reality Training to Support Professional Socio-Emotional Interactions at Schools
  55. MaskMol: Knowledge-guided Molecular Image Pre-Training Framework for Activity Cliffs
  56. AI Literacy for All: Adjustable Interdisciplinary Socio-technical Curriculum
  57. SINDyG: Sparse Identification of Nonlinear Dynamical Systems from Graph-Structured Data, with Applications to Stuart-Landau Oscillator Networks
  58. GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling
  59. MLOmics: Cancer Multi-Omics Database for Machine Learning
  60. Self-Supervised Learning for Identifying Defects in Sewer Footage
  61. The Role of Transformer Models in Advancing Blockchain Technology: A Systematic Survey
  62. Large Language Models versus Classical Machine Learning: Performance in COVID-19 Mortality Prediction Using High-Dimensional Tabular Data
  63. Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling
  64. Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks
  65. Recognition of Schrodinger cat state based on CNN
  66. AMG: Avatar Motion Guided Video Generation
  67. Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather Conditions
  68. A practical generalization metric for deep networks benchmarking
  69. DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using Large Language Models
  70. Can Geometric Quantum Machine Learning Lead to Advantage in Barcode Classification?
  71. The Compressor-Retriever Architecture for Language Model OS
  72. EarthGen: Generating the World from Top-Down Views
  73. Masked Mixers for Language Generation and Retrieval
  74. Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition
  75. Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning
  76. Stein transport for Bayesian inference
  77. 3D-LSPTM: An Automatic Framework with 3D-Large-Scale Pretrained Model for Laryngeal Cancer Detection Using Laryngoscopic Videos
  78. FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
  79. Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis
  80. Landscape-Aware Automated Algorithm Configuration using Multi-output Mixed Regression and Classification
  81. Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets
  82. A causal viewpoint on prediction model performance under changes in case-mix: discrimination and calibration respond differently for prognosis and diagnosis predictions
  83. Kvasir-VQA: A Text-Image Pair GI Tract Dataset
  84. Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation
  85. Domain Decomposition-based coupling of Operator Inference reduced order models via the Schwarz alternating method
  86. Self-Directed Learning of Convex Labelings on Graphs
  87. DiffCSG: Differentiable CSG via Rasterization
  88. Erasure Coded Neural Network Inference via Fisher Averaging
  89. Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching
  90. Probabilistic Iterative Hard Thresholding for Sparse Learning
  91. Performance-Aware Self-Configurable Multi-Agent Networks: A Distributed Submodular Approach for Simultaneous Coordination and Network Design
  92. Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learning
  93. mathttemuflow: Normalising Flows for Joint Cosmological Analysis
  94. Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics
  95. CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding
  96. VLSI Hypergraph Partitioning with Deep Learning
  97. Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities
  98. H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
  99. Debiasing Graph Representation Learning based on Information Bottleneck
  100. CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
All 221
  1. Correlating Time Series with Interpretable Convolutional Kernels
  2. Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain
  3. Explanation Space: A New Perspective into Time Series Interpretability
  4. From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
  5. Spectron: Target Speaker Extraction using Conditional Transformer with Adversarial Refinement
  6. PatternPaint: Practical Layout Pattern Generation Using Diffusion-Based Inpainting
  7. Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A
  8. Enhancing Test Time Adaptation with Few-shot Guidance
  9. Pediatric brain tumor classification using digital histopathology and deep learning: evaluation of SOTA methods on a multi-center Swedish cohort
  10. Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning
  11. Grounding Language Models in Autonomous Loco-manipulation Tasks
  12. Multi-frequency Neural Born Iterative Method for Solving 2-D Inverse Scattering Problems
  13. Disentangling Mean Embeddings for Better Diagnostics of Image Generators
  14. Representing Neural Network Layers as Linear Operations via Koopman Operator Theory
  15. Highly Accurate Real-space Electron Densities with Neural Networks
  16. Topological degree as a discrete diagnostic for disentanglement, with applications to the DeltaVAE
  17. One-Index Vector Quantization Based Adversarial Attack on Image Classification
  18. DAVIDE: Depth-Aware Video Deblurring
  19. Double Machine Learning meets Panel Data -- Promises, Pitfalls, and Potential Solutions
  20. Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling
  21. GAS: Generative Activation-Aided Asynchronous Split Federated Learning
  22. Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
  23. Sample Complexity of the Sign-Perturbed Sums Method
  24. CyberCortex.AI: An AI-based Operating System for Autonomous Robotics and Complex Automation
  25. Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification
  26. MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning
  27. THInC: A Theory-Driven Framework for Computational Humor Detection
  28. A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches
  29. A multilingual training strategy for low resource Text to Speech
  30. ESP-PCT: Enhanced VR Semantic Performance through Efficient Compression of Temporal and Spatial Redundancies in Point Cloud Transformers
  31. Supervised Pattern Recognition Involving Skewed Feature Densities
  32. Statistical Jump Model for Mixed-Type Data with Missing Data Imputation
  33. Towards General Industrial Intelligence: A Survey of Continual Large Models in Industrial IoT
  34. EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance
  35. Ground-truth effects in learning-based fiber orientation distribution estimation in neonatal brains
  36. PitVis-2023 Challenge: Workflow Recognition in videos of Endoscopic Pituitary Surgery
  37. Logit Scaling for Out-of-Distribution Detection
  38. Variation of Camera Parameters due to Common Physical Changes in Focal Length and Camera Pose
  39. PACSBO: Probably approximately correct safe Bayesian optimization
  40. Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning
  41. Forecasting infectious disease prevalence with associated uncertainty using neural networks
  42. Real World Conversational Entity Linking Requires More Than Zeroshots
  43. LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learning
  44. LLM-PQA: LLM-enhanced Prediction Query Answering
  45. Generating Synthetic Satellite Imagery for Rare Objects: An Empirical Comparison of Models and Metrics
  46. Smart E-commerce Recommendations with Semantic AI
  47. Large Language Models Can Understanding Depth from Monocular Images
  48. Learning Robust Representations for Communications over Noisy Channels
  49. Two-stage initial-value iterative physics-informed neural networks for simulating solitary waves of nonlinear wave equations
  50. Time series classification with random convolution kernels: pooling operators and input representations matter
  51. KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding
  52. SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation
  53. OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Clouds
  54. Two-Timescale Synchronization and Migration for Digital Twin Networks: A Multi-Agent Deep Reinforcement Learning Approach
  55. CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads
  56. Towards Split Learning-based Privacy-Preserving Record Linkage
  57. Pre-Trained Language Models for Keyphrase Prediction: A Review
  58. Evidential Transformers for Improved Image Retrieval
  59. Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
  60. Bootstrap SGD: Algorithmic Stability and Robustness
  61. SCOPE: Sign Language Contextual Processing with Embedding from LLMs
  62. DAWA: Dynamic Ambiguity-Wise Adaptation for Real-Time Domain Adaptive Semantic Segmentation
  63. VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
  64. Progressive Retinal Image Registration via Global and Local Deformable Transformations
  65. Learning in Hybrid Active Inference Models
  66. Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?
  67. Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
  68. A Perspective on Literary Metaphor in the Context of Generative AI
  69. Robust Vehicle Localization and Tracking in Rain using Street Maps
  70. NYK-MS: A Well-annotated Multi-modal Metaphor and Sarcasm Understanding Benchmark on Cartoon-Caption Dataset
  71. Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
  72. Learning to Discover Forgery Cues for Face Forgery Detection
  73. Variation in prediction accuracy due to randomness in data division and fair evaluation using interval estimation
  74. SINET: Sparsity-driven Interpretable Neural Network for Underwater Image Enhancement
  75. CONDA: Condensed Deep Association Learning for Co-Salient Object Detection
  76. Fed-MUnet: Multi-modal Federated Unet for Brain Tumor Segmentation
  77. SeCo-INR: Semantically Conditioned Implicit Neural Representations for Improved Medical Image Super-Resolution
  78. Improved Diversity-Promoting Collaborative Metric Learning for Recommendation
  79. Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts
  80. Fitting trees to ℓ1-hyperbolic distances
  81. Unlocking the Wisdom of Large Language Models: An Introduction to The Path to Artificial General Intelligence
  82. Free-DyGS: Camera-Pose-Free Scene Reconstruction for Dynamic Surgical Videos with Gaussian Splatting
  83. DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning
  84. Physics-informed DeepONet with stiffness-based loss functions for structural response prediction
  85. Self-Supervised Multi-Scale Network for Blind Image Deblurring via Alternating Optimization
  86. Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language
  87. GCCRR: A Short Sequence Gait Cycle Segmentation Method Based on Ear-Worn IMU
  88. DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data
  89. Regret Analysis for Randomized Gaussian Process Upper Confidence Bound
  90. Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications
  91. IVGF: The Fusion-Guided Infrared and Visible General Framework
  92. Interpretable Convolutional SyncNet
  93. A computational transition for detecting correlated stochastic block models by low-degree polynomials
  94. What does it take to get state of the art in simultaneous speech-to-speech translation?
  95. Physics-Informed Neural Network Based Digital Image Correlation Method
  96. PNVC: Towards Practical INR-based Video Compression
  97. Semantically Controllable Augmentations for Generalizable Robot Learning
  98. XNet v2: Fewer Limitations, Better Results and Greater Universality
  99. A Framework for Synthetic Audio Conversations Generation using Large Language Models
  100. VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
  101. Large Language Models for Automatic Detection of Sensitive Topics
  102. Towards Student Actions in Classroom Scenes: New Dataset and Baseline
  103. MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM
  104. Development of Occupancy Prediction Algorithm for Underground Parking Lots
  105. Statically Contextualizing Large Language Models with Typed Holes
  106. MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT
  107. Large Scale Unsupervised Brain MRI Image Registration Solution for Learn2Reg 2024
  108. On the Pinsker bound of inner product kernel regression in large dimensions
  109. Generalized Continuous-Time Models for Nesterov's Accelerated Gradient Methods
  110. Merging Multiple Datasets for Improved Appearance-Based Gaze Estimation
  111. ViRED: Prediction of Visual Relations in Engineering Drawings
  112. EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
  113. Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction
  114. MV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies
  115. On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks
  116. A Noise and Edge extraction-based dual-branch method for Shallowfake and Deepfake Localization
  117. Improving Adaptivity via Over-Parameterization in Sequence Models
  118. User-Specific Dialogue Generation with User Profile-Aware Pre-Training Model and Parameter-Efficient Fine-Tuning
  119. A Novel Hybrid Parameter-Efficient Fine-Tuning Approach for Hippocampus Segmentation and Alzheimer's Disease Diagnosis
  120. Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment
  121. Digital Twins in Additive Manufacturing: A Systematic Review