mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 29 Nov 2024

237 papers

  1. Pretrained Reversible Generation as Unsupervised Visual Representation LearningDiffusion models → Diffusion foundations and sampling
  2. Assessing How Ride-hailing Rebalancing Strategies Improve the Resilience of Multi-modal Transportation SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  3. One-Shot Real-to-Sim via End-to-End Differentiable Simulation and RenderingWorld models → Embodied and robot world models
  4. Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  5. Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty EstimationDiffusion models → Diffusion foundations and sampling
  6. LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene RelightingDiffusion models → 3D, point cloud and scene generation
  7. STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-TrainingLLM reasoning → Multimodal reasoning +1
  8. VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion ModelsDiffusion models → Inverse problems and image restoration
  9. ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and TrustworthinessLLM reasoning → Multimodal reasoning
  11. Sparrow: Data-Efficient Video-LLM with Text-to-Image AugmentationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityLLM reasoning → Test-time compute and efficient thinking
  13. VLSBench: Unveiling Visual Leakage in Multimodal SafetyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  14. On Domain-Adaptive Post-Training for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script GenerationRetrieval-augmented generation → Multimodal RAG
  16. LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM statesLLM safety and security → Membership inference attacks
  17. Reverse Thinking Makes LLMs Stronger ReasonersLLM reasoning → Test-time compute and efficient thinking
  18. Q-learning-based Model-free Safety FilterDeep reinforcement learning methods → Safe and constrained RL
  19. Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  20. CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectivesDeep reinforcement learning methods → RL training of language and agent models
  21. MoTe: Learning Motion-Text Diffusion Model for Multiple Generation TasksDiffusion models → Video generation
  22. Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  23. JetFormer: An Autoregressive Generative Model of Raw Images and TextMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  24. Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  25. SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA TasksMultimodal LLMs / vision-language models → Medical vision-language models
  26. Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and EditingDiffusion models → Image generation, text-to-image and editing
  27. CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
  28. LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic ClassificationKnowledge distillation → Knowledge distillation for LLMs
  29. Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model BotLLM agents and tool use → Social simulation and multi-agent debate
  30. Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  31. Can Large Language Models Reason about the Region Connection Calculus?LLM reasoning → Spatial and embodied reasoning
  32. Solving Rubik's Cube Without Tricky SamplingDeep reinforcement learning methods → Deep RL algorithms and representations
  33. Ensemble Watermarks for Large Language ModelsLLM safety and security → Watermarking generated content and models
  34. ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online RestorationWorld models → World models for autonomous driving +1
  35. Training Agents with Weakly Supervised Feedback from Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  36. Knowledge Management for Automobile Failure Analysis Using Graph RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  37. Quantized Delta Weight Is Safety KeeperLLM safety and security → Jailbreaking
  38. DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow DecodingDiffusion models → Video generation
  39. Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head SynthesisDiffusion models → Audio, speech and music
  40. COLD: Causal reasOning in cLosed Daily activitiesLLM reasoning → Causal reasoning in LLMs
  41. SANGO: Socially Aware Navigation through Grouped ObstaclesDeep reinforcement learning methods → RL for robot navigation and UAV control
  42. Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-based ApproachDiffusion models → Diffusion and flow policies for robotics
  43. Interleaved-Modal Chain-of-ThoughtLLM reasoning → Multimodal reasoning
  44. V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified FlowDiffusion models → Audio, speech and music
  45. Zero-Indexing Internet Search Augmented Generation for Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  46. Provable Scaling Laws for the Test-Time Compute of Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  47. ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  48. Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  49. Look Every Frame All at Once: Video-Ma2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient CheckpointingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  50. Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  51. Core Placement Optimization of Many-core Brain-Inspired Near-Storage Systems for Spiking Neural Network TrainingDeep reinforcement learning methods → Spiking and neuromorphic RL
  52. Proto Successor Measure: Representing the Behavior Space of an RL AgentDeep reinforcement learning methods → Deep RL algorithms and representations
  53. Responsible AI Governance: A Response to UN Interim Report on Governing AI for Humanity
  54. Generative AI Literacy: Twelve Defining Competencies
  55. AI-assisted summary of suicide risk Formulation
  56. The AI Interface: Designing for the Ideal Machine-Human Experience (Editorial)
  57. BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
  58. Streamlining Video Analysis for Efficient Violence Detection
  59. Volumetric Reconstruction of Prostatectomy Specimens from Histology
  60. Data Augmentation through Background Removal for Apple Leaf Disease Classification Using the MobileNetV2 Model
  61. Hyperspectral Images Efficient Spatial and Spectral non-Linear Model with Bidirectional Feature Learning
  62. Streamlining the review process: AI-generated annotations in research manuscripts
  63. Average-Over-Time Spiking Neural Networks for Uncertainty Estimation in Regression
  64. Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
  65. Attribute-Enhanced Similarity Ranking for Sparse Link Prediction
  66. Excretion Detection in Pigsties Using Convolutional and Transformerbased Deep Neural Networks
  67. Fine-Tuning Open-Weight Language Models to Deliver Cognitive Behavioral Therapy for Depression: A Feasibility Study
  68. Integrating Social Determinants of Health into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare
  69. Robust Testing for Deep Learning using Human Label Noise
  70. Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction
  71. MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributes
  72. Generating a Low-code Complete Workflow via Task Decomposition and RAG
  73. Twisted Convolutional Networks (TCNs): Enhancing Feature Interactions for Non-Spatial Data Classification
  74. Hybrid Spiking Neural Network -- Transformer Video Classification Model
  75. Clinical Document Corpora -- Real Ones, Translated and Synthetic Substitutes, and Assorted Domain Proxies: A Survey of Diversity in Corpus Design, with Focus on German Text Data
  76. Meta-learning Loss Functions of Parametric Partial Differential Equations Using Physics-Informed Neural Networks
  77. An AI-Driven Data Mesh Architecture Enhancing Decision-Making in Infrastructure Construction and Public Procurement
  78. NushuRescue: Revitalization of the Endangered Nushu Language with AI
  79. Digital Twin in Industries: A Comprehensive Survey
  80. Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction
  81. Towards the Ultimate Programming Language: Trust and Benevolence in the Age of Artificial Intelligence
  82. Scaling of Stochastic Normalizing Flows in SU(3) lattice gauge theory
  83. Improving the performance of weak supervision searches using data augmentation
  84. Opt-In Art: Learning Art Styles Only from Few Examples
  85. Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
  86. SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters
  87. Enhanced Spatial Clustering of Single-Molecule Localizations with Graph Neural Networks
  88. RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World
  89. Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective
  90. To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models
  91. Modelling Networked Dynamical System by Temporal Graph Neural ODE with Irregularly Partial Observed Time-series Data
  92. Dynamic High-Order Control Barrier Functions with Diffuser for Safety-Critical Trajectory Planning at Signal-Free Intersections
  93. AerialGo: Walking-through City View Generation from Aerial Perspectives
  94. T-3DGS: Removing Transient Objects for 3D Scene Reconstruction
  95. o1-Coder: an o1 Replication for Coding
  96. Dynamic Neural Curiosity Enhances Learning Flexibility for Autonomous Goal Discovery
  97. Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
  98. Motion Modes: What Could Happen Next?
  99. AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
  100. DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation
All 237
  1. FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling
  2. Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark
  3. Transfer Learning for High-dimensional Quantile Regression with Distribution Shift
  4. Scalable Out-of-distribution Robustness in the Presence of Unobserved Confounders
  5. Dynamic EEG-fMRI mapping: Revealing the relationship between brain connectivity and cognitive state
  6. Geometry of fibers of the multiplication map of deep linear neural networks
  7. Handling irresolvable conflicts in the Semantic Web: an RDF-based conflict-tolerant version of the Deontic Traditional Scheme
  8. Quantifying the synthetic and real domain gap in aerial scene understanding
  9. Another look at statistical inference with machine learning-imputed data
  10. A Graph-Based Classical and Quantum Approach to Deterministic L-System Inference
  11. Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives
  12. Noncommutative Model Selection for Data Clustering and Dimension Reduction Using Relative von Neumann Entropy
  13. Efficient quantum-enhanced classical simulation for patches of quantum landscapes
  14. GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
  15. Noncommutative Model Selection and the Data-Driven Estimation of Real Cohomology Groups
  16. FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentation
  17. PDDLFuse: A Tool for Generating Diverse Planning Domains
  18. Open source Differentiable ODE Solving Infrastructure
  19. Enhanced anomaly detection in well log data through the application of ensemble GANs
  20. DeMo: Decoupled Momentum Optimization
  21. AIDetx: a compression-based method for identification of machine-learning generated text
  22. SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection
  23. What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis
  24. Artificial intelligence contribution to translation industry: looking back and forward
  25. Towards Class-wise Robustness Analysis
  26. A Visual-inertial Localization Algorithm using Opportunistic Visual Beacons and Dead-Reckoning for GNSS-Denied Large-scale Applications
  27. Scaling Transformers for Low-Bitrate High-Quality Speech Coding
  28. Feedback-driven object detection and iterative model improvement
  29. Sensitive Content Classification in Social Media: A Holistic Resource and Evaluation
  30. SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
  31. SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition
  32. GradAlign for Training-free Model Performance Inference
  33. Gaussian multi-target filtering with target dynamics driven by a stochastic differential equation
  34. Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures
  35. INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  36. Rethinking the initialization of Momentum in Federated Learning with Heterogeneous Data
  37. Tractable Agreement Protocols
  38. Machine learning force-field model for kinetic Monte Carlo simulations of itinerant Ising magnets
  39. PerLA: Perceptive 3D Language Assistant
  40. LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
  41. Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning
  42. Riemannian Denoising Model for Molecular Structure Optimization with Chemical Accuracy
  43. Stock Price Prediction using Multi-Faceted Information based on Deep Recurrent Neural Networks
  44. Forecasting Foreign Exchange Market Prices Using Technical Indicators with Deep Learning and Attention Mechanism
  45. LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment
  46. Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
  47. DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
  48. A Comprehensive Content Verification System for ensuring Digital Integrity in the Age of Deep Fakes
  49. A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses
  50. HVAC-DPT: A Decision Pretrained Transformer for HVAC Control
  51. Amplifying human performance in combinatorial competitive programming
  52. Graph Neural Networks for Heart Failure Prediction on an EHR-Based Patient Similarity Graph
  53. A Note on Small Percolating Sets on Hypercubes via Generative AI
  54. A Deep Learning Approach to Language-independent Gender Prediction on Twitter
  55. Real-Time Anomaly Detection in Video Streams
  56. Risk-Averse Certification of Bayesian Neural Networks
  57. Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation
  58. Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization
  59. TakeLab Retriever: AI-Driven Search Engine for Articles from Croatian News Outlets
  60. MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications
  61. Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
  62. The Streetscape Application Services Stack (SASS): Towards a Distributed Sensing Architecture for Urban Applications
  63. CantorNet: A Sandbox for Testing Geometrical and Topological Complexity Measures
  64. Fast Mutual Information Computation for Large Binary Datasets
  65. Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanation
  66. Gated-Attention Feature-Fusion Based Framework for Poverty Prediction
  67. MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks
  68. Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation
  69. On the Performance Analysis of Momentum Method: A Frequency Domain Perspective
  70. ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information
  71. Multimodal Whole Slide Foundation Model for Pathology
  72. Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis
  73. TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting
  74. Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal
  75. CAdam: Confidence-Based Optimization for Online Learning
  76. Learned Random Label Predictions as a Neural Network Complexity Metric
  77. PACMANN: Point Adaptive Collocation Method for Artificial Neural Networks
  78. Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks
  79. OpenQDC: Open Quantum Data Commons
  80. GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding
  81. FairDD: Fair Dataset Distillation
  82. Materials Learning Algorithms (MALA): Scalable Machine Learning for Electronic Structure Calculations in Large-Scale Atomistic Simulations
  83. Tortho-Gaussian: Splatting True Digital Orthophoto Maps
  84. Self-Supervised Denoiser Framework
  85. Gaussian Splashing: Direct Volumetric Rendering Underwater
  86. LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention
  87. Enhancing Sentiment Analysis in Bengali Texts: A Hybrid Approach Using Lexicon-Based Algorithm and Pretrained Language Model Bangla-BERT
  88. In-Context Learning with Noisy Labels
  89. ICPR 2024 Competition on Multilingual Claim-Span Identification
  90. KV Shifting Attention Enhances Language Modeling
  91. A Comprehensive Framework for Automated Segmentation of Perivascular Spaces in Brain MRI with the nnU-Net
  92. Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
  93. Differentiable Causal Discovery For Latent Hierarchical Causal Models
  94. Unimib Assistant: designing a student-friendly RAG-based chatbot for all their needs
  95. Analysis of High-dimensional Gaussian Labeled-unlabeled Mixture Model via Message-passing Algorithm
  96. Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding
  97. Contextual Checkerboard Denoise -- A Novel Neural Network-Based Approach for Classification-Aware OCT Image Denoising
  98. SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
  99. Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
  100. Development of Low-Cost IoT Units for Thermal Comfort Measurement and AC Energy Consumption Prediction System
  101. QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain
  102. RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
  103. A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation
  104. LokiTalk: Learning Fine-Grained and Generalizable Correspondences to Enhance NeRF-based Talking Head Synthesis
  105. Localized Conformal Multi-Quantile Regression
  106. Subjective and Objective Quality Assessment Methods of Stereoscopic Videos with Visibility Affecting Distortions
  107. RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs
  108. Enhancing AI microscopy for foodborne bacterial classification via adversarial domain adaptation across optical and biological variability
  109. ContextGNN: Beyond Two-Tower Recommendation Systems
  110. Topology-Preserving Scaling in Data Augmentation
  111. Retrieval-guided Cross-view Image Synthesis
  112. GEFM: Graph-Enhanced EEG Foundation Model
  113. Real-time Anomaly Detection at the L1 Trigger of CMS Experiment
  114. TQA-Bench: Evaluating LLMs for Multi-Table Question Answering
  115. Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification
  116. Protecting Multiple Types of Privacy Simultaneously in EEG-based Brain-Computer Interfaces
  117. An Approach Towards Learning K-means-friendly Deep Latent Representation
  118. Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling
  119. Action Engine: Automatic Workflow Generation in FaaS
  120. FLARE: Toward Universal Dataset Purification against Backdoor Attacks
  121. GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis
  122. Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB
  123. Learning Expressive Random Feature Models via Parametrized Activations
  124. Robust Bayesian Scene Reconstruction with Retrieval-Augmented Priors for Precise Grasping and Planning
  125. Fleximo: Towards Flexible Text-to-Human Motion Video Generation
  126. Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
  127. Multi-task CNN Behavioral Embedding Model For Transaction Fraud Detection
  128. Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
  129. Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
  130. GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
  131. Learning Visual Abstract Reasoning through Dual-Stream Networks
  132. Unsupervised Learning Approach to Anomaly Detection in Gravitational Wave Data
  133. Adaptive Interactive Segmentation for Multimodal Medical Imaging via Selection Engine
  134. MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices
  135. Gradient Inversion Attack on Graph Neural Networks
  136. Actions and Objects Pathways for Domain Adaptation in Video Question Answering
  137. A Simple Sparse Matrix Vector Multiplication Approach to Padded Convolution