mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 22 Dec 2023

227 papers

  1. Voila-A: Aligning Vision-Language Models with User's Gaze AttentionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. Empowering Working Memory for Large Language Model AgentsLLM agents and tool use → Agent memory systems
  3. Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  4. Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  5. GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Towards a Unified Multimodal Reasoning FrameworkLLM reasoning → Multimodal reasoning
  7. Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative CasesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. Assessing the Impact of Prompting Methods on ChatGPT's Mathematical CapabilitiesLLM reasoning → Mathematical reasoning
  9. FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and EditingDiffusion models → Video generation
  10. FoodLMM: A Versatile Food Assistant using Large Multi-modal ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. Emage: Non-Autoregressive Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  12. A Survey of Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  13. Fast-NTK: Parameter-Efficient Unlearning for Large-Scale ModelsLLM safety and security → Machine unlearning
  14. FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative ModelsLLM safety and security → Vision-language and text-to-image safety
  15. NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity ClassesLLM reasoning → Reasoning benchmarks and evaluation
  16. Pangu-Agent: A Fine-Tunable Generalist Agent with Structured ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  17. Numerical Reasoning for Financial ReportsLLM reasoning → Reasoning for agents, planning and code
  18. Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion ModelsDiffusion models → Medical imaging and segmentation
  19. Harnessing Diffusion Models for Visual Perception with Meta PromptsDiffusion models → Image generation, text-to-image and editing
  20. Tuning-Free Inversion-Enhanced Control for Consistent Image EditingDiffusion models → Image generation, text-to-image and editing
  21. Reasons to Reject? Aligning Language Models with JudgmentsLLM reasoning → Reinforcement learning for reasoning +1
  22. Non-Denoising Forward-Time DiffusionsDiffusion models → Diffusion foundations and sampling
  23. Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-TuningMixture-of-experts → MoE large language models
  24. Revisiting Few-Shot Object Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  25. QUAR-VLA: Vision-Language-Action Model for Quadruped RobotsVision-language-action models → Generalist VLA models and benchmarks
  26. Asymmetric Bias in Text-to-Image Generation with Adversarial AttacksLLM safety and security → Vision-language and text-to-image safety
  27. REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  28. Predicting Confinement Effect of Carbon Fiber Reinforced Polymers on Strength of Concrete using Metaheuristics-based Artificial Neural Networks
  29. The Global Impact of AI-Artificial Intelligence: Recent Advances and Future Directions, A Review
  30. Learning with Geometry: Including Riemannian Geometric Features in Coefficient of Pressure Prediction on Aircraft Wings
  31. Diffusion-Driven Generative Framework for Molecular Conformation Prediction
  32. Joining Forces for Pathology Diagnostics with AI Assistance: The EMPAIA Initiative
  33. Tumbug: A pictorial, universal knowledge representation method
  34. A debiasing technique for place-based algorithmic patrol management
  35. Trustworthy human-centric based Automated Decision-Making Systems
  36. Future-proofing Education: A Prototype for Simulating Oral Examinations Using Large Language Models
  37. FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
  38. Multi-Modal Cognitive Maps based on Neural Networks trained on Successor Representations
  39. Resource-Limited Automated Ki67 Index Estimation in Breast Cancer
  40. Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
  41. TimePillars: Temporally-Recurrent 3D LiDAR Object Detection
  42. Flying By ML -- CNN Inversion of Affine Transforms
  43. Personalized Large Language Model Assistant with Evolving Conditional Memory
  44. A Method for Auto-Differentiation of the Voronoi Tessellation
  45. SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning
  46. EGAIN: Extended GAn INversion
  47. Identifying built environment factors influencing driver yielding behavior at unsignalized intersections: A naturalistic open-source dataset collected in Minnesota
  48. UAS-based Automated Structural Inspection Path Planning via Visual Data Analytics and Optimization
  49. Generative AI and the History of Architecture
  50. Energy-based learning algorithms for analog computing: a comparative study
  51. Robust Sclera Segmentation for Skin-tone Agnostic Face Image Quality Assessment
  52. FetaFix: Automatic Fault Localization and Repair of Deep Learning Model Conversions
  53. Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks
  54. Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)
  55. A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays
  56. Adaptive Domain Inference Attack with Concept Hierarchy
  57. HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings
  58. Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning
  59. Learning Rich Rankings
  60. Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection
  61. Joint Self-Supervised and Supervised Contrastive Learning for Multimodal MRI Data: Towards Predicting Abnormal Neurodevelopment
  62. A universal approximation theorem for nonlinear resistive networks
  63. Deformable 3D Gaussian Splatting for Animatable Human Avatars
  64. The State of Documentation Practices of Third-party Machine Learning Models and Datasets
  65. Deep Learning for Efficient GWAS Feature Selection
  66. Information-seeking polynomial NARX model-predictive control through expected free energy minimization
  67. Probabilistic Modeling for Sequences of Sets in Continuous-Time
  68. Towards Detecting Cascades of Biased Medical Claims on Twitter
  69. Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images
  70. SODA: Protecting Proprietary Information in On-Device Machine Learning Models
  71. Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention
  72. Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
  73. SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology
  74. C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting
  75. Discovering modular solutions that generalize compositionally
  76. Leveraging Habitat Information for Fine-grained Bird Identification
  77. Synthetic images aid the recognition of human-made art forgeries
  78. Bridging AI and Clinical Practice: Integrating Automated Sleep Scoring Algorithm with Uncertainty-Guided Physician Review
  79. Learning to Prompt Knowledge Transfer for Open-World Continual Learning
  80. Deformable Image Registration with Stochastically Regularized Biomechanical Equilibrium
  81. UniHuman: A Unified Model for Editing Human Images in the Wild
  82. TPTNet: A Data-Driven Temperature Prediction Model Based on Turbulent Potential Temperature
  83. MACS: Mass Conditioned 3D Hand and Object Motion Synthesis
  84. Training Convolutional Neural Networks with the Forward-Forward algorithm
  85. Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks
  86. A New Similarity Function for Spectral Clustering with Application to Plant Phenotypic Data
  87. Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers
  88. PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF
  89. DRStageNet: Deep Learning for Diabetic Retinopathy Staging from Fundus Images
  90. On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
  91. Sample Path Regularity of Gaussian Processes from the Covariance Kernel
  92. Sampling and estimation on manifolds using the Langevin diffusion
  93. SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting
  94. Robust Knowledge Extraction from Large Language Models using Social Choice Theory
  95. Automating the Design of Multigrid Methods with Evolutionary Program Synthesis
  96. BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction
  97. Spatiotemporal-Linear: Towards Universal Multivariate Time Series Forecasting
  98. VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
  99. YAYI 2: Multilingual Open-Source Large Language Models
  100. Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code
All 227
  1. TACO: Topics in Algorithmic COde generation dataset
  2. Isolated pulsar population synthesis with simulation-based inference
  3. Large Scale Training of Graph Neural Networks for Optimal Markov-Chain Partitioning Using the Kemeny Constant
  4. On the Use of Metaphor Translation in Psychiatry
  5. Learning Lagrangian Multipliers for the Travelling Salesman Problem
  6. Prototype-Guided Text-based Person Search based on Rich Chinese Descriptions
  7. Plan, Posture and Go: Towards Open-World Text-to-Motion Generation
  8. An investigation of belief-free DRL and MCTS for inspection and maintenance planning
  9. How Smooth Is Attention?
  10. PARDINUS: Weakly supervised discarding of photo-trapping empty images based on autoencoders
  11. A Tricycle Model to Accurately Control an Autonomous Racecar with Locked Differential
  12. The Effects of Signal-to-Noise Ratio on Generative Adversarial Networks Applied to Marine Bioacoustic Data
  13. Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases
  14. On support vector machines under a multiple-cost scenario
  15. An Empirical Study on Compliance with Ranking Transparency in the Software Documentation of EU Online Platforms
  16. The Rate-Distortion-Perception-Classification Tradeoff: Joint Source Coding and Modulation via Inverse-Domain GANs
  17. Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold
  18. Cross-Age and Cross-Site Domain Shift Impacts on Deep Learning-Based White Matter Fiber Estimation in Newborn and Baby Brains
  19. Integration Of Evolutionary Automated Machine Learning With Structural Sensitivity Analysis For Composite Pipelines
  20. Large Language Model (LLM) Bias Index -- LLMBI
  21. Enhanced Latent Multi-view Subspace Clustering
  22. Diffusion Maps for Signal Filtering in Graph Learning
  23. Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
  24. Progressing from Anomaly Detection to Automated Log Labeling and Pioneering Root Cause Analysis
  25. Computational Semantics and Evaluation Benchmark for Interrogative Sentences via Combinatory Categorial Grammar
  26. Images in Discrete Choice Modeling: Addressing Data Isomorphism in Multi-Modality Inputs
  27. Gerrymandering Planar Graphs
  28. Balancing Privacy, Robustness, and Efficiency in Machine Learning
  29. Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising
  30. BonnBeetClouds3D: A Dataset Towards Point Cloud-based Organ-level Phenotyping of Sugar Beet Plants under Field Conditions
  31. SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation
  32. Time-changed normalizing flows for accurate SDE modeling
  33. Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarization
  34. A Mathematical Guide to Operator Learning
  35. Engineered Ordinary Differential Equations as Classification Algorithm (EODECA): thorough characterization and testing
  36. MEAOD: Model Extraction Attack against Object Detectors
  37. Zero-shot Causal Graph Extrapolation from Text via LLMs
  38. Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition
  39. Density Uncertainty Quantification with NeRF-Ensembles: Impact of Data and Scene Constraints
  40. Deep Non-Parametric Time Series Forecaster
  41. SAVAE: Leveraging the variational Bayes autoencoder for survival analysis
  42. Global Occlusion-Aware Transformer for Robust Stereo Matching
  43. Towards Message Brokers for Generative AI: Survey, Challenges, and Opportunities
  44. Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference
  45. Balancing Energy Efficiency and Distributional Robustness in Over-the-Air Federated Learning
  46. Fluid Simulation on Neural Flow Maps
  47. Mining multi-modal communication patterns in interaction with explainable and non-explainable robots
  48. A Language-based solution to enable Metaverse Retrieval
  49. Holistic analysis on the sustainability of Federated Learning across AI product lifecycle
  50. DSAP: Analyzing Bias Through Demographic Comparison of Datasets
  51. Multi-Agent Reinforcement Learning for Assessing False-Data Injection Attacks on Transportation Networks
  52. Towards Loose-Fitting Garment Animation via Generative Model of Deformation Decomposition
  53. BLSTM-Based Confidence Estimation for End-to-End Speech Recognition
  54. Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps
  55. SIG: Speaker Identification in Literature via Prompt-Based Generation
  56. On a Near-Optimal & Efficient Algorithm for the Sparse Pooled Data Problem
  57. Synthesizing Environment-Specific People in Photographs
  58. PoseViNet: Distracted Driver Action Recognition Framework Using Multi-View Pose Estimation and Vision Transformer
  59. MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning
  60. Semidefinite Relaxations of the Gromov-Wasserstein Distance
  61. Data is Moody: Discovering Data Modification Rules from Process Event Logs
  62. BSS-Bench: Towards Reproducible and Effective Band Selection Search
  63. Creating New Voices using Normalizing Flows
  64. Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
  65. Improving Task Instructions for Data Annotators: How Clear Rules and Higher Pay Increase Performance in Data Annotation in the AI Economy
  66. Online Covering with Multiple Experts
  67. CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
  68. Machine learning for structure-guided materials and process design
  69. Inclusive normalization of face images to passport format
  70. Automatic Data Retrieval for Cross Lingual Summarization
  71. Adaptive Reconvergence-driven AIG Rewriting via Strategy Learning
  72. ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
  73. Multi-view user representation learning for user matching without personal information
  74. DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge
  75. ZodiacEdge: a Datalog Engine With Incremental Rule Set Maintenance
  76. An effective and efficient green federated learning method for one-layer neural networks
  77. Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification
  78. Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport
  79. Theory of Hallucinations based on Equivariance
  80. ViStripformer: A Token-Efficient Transformer for Versatile Video Restoration
  81. Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
  82. Context Enhanced Transformer for Single Image Object Detection
  83. Language Model is a Branch Predictor for Simultaneous Machine Translation
  84. SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation
  85. MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models
  86. Federated Learning via Input-Output Collaborative Distillation
  87. MonoLSS: Learnable Sample Selection For Monocular 3D Detection
  88. Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
  89. Prototype-based Cross-Modal Object Tracking
  90. Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration
  91. FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection
  92. Attacking Byzantine Robust Aggregation in High Dimensions
  93. Multiagent Copilot Approach for Shared Autonomy between Human EEG and TD3 Deep Reinforcement Learning
  94. How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?
  95. On the Effectiveness of Unlearning in Session-Based Recommendation
  96. Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset
  97. DMC4ML: Data Movement Complexity for Machine Learning
  98. PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation
  99. PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering
  100. Scalable 3D Reconstruction From Single Particle X-Ray Diffraction Images Based on Online Machine Learning
  101. A Unified Industrial Large Knowledge Model Framework in Industry 4.0 and Smart Manufacturing
  102. GROOD: GRadient-Aware Out-of-Distribution Detection
  103. Room Occupancy Prediction: Exploring the Power of Machine Learning and Temporal Insights
  104. Efficacy of Machine-Generated Instructions
  105. Enhancing Actionable Formal Concept Identification with Base-Equivalent Conceptual-Relevance
  106. Sharp error estimates for target measure diffusion maps with applications to the committor problem
  107. A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition
  108. AdvCloak: Customized Adversarial Cloak for Privacy Protection
  109. Generative Pretraining at Scale: Transformer-Based Encoding of Transactional Behavior for Fraud Detection
  110. Graph Attention-Based Symmetry Constraint Extraction for Analog Circuits
  111. Cross-Covariate Gait Recognition: A Benchmark
  112. The Fairness Fair: Bringing Human Perception into Collective Decision-Making
  113. Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances
  114. Unsupervised Deep Learning Image Verification Method
  115. AdapTraj: A Multi-Source Domain Generalization Framework for Multi-Agent Trajectory Prediction
  116. StyleRetoucher: Generalized Portrait Image Retouching with GAN Priors
  117. Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation
  118. Generative AI Beyond LLMs: System Implications of Multi-Modal Generation
  119. Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal
  120. Federated Learning with Projected Trajectory Regularization
  121. Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification
  122. Learning Socio-Temporal Graphs for Multi-Agent Trajectory Prediction
  123. Generative Models for Simulation of KamLAND-Zen
  124. Quality-Diversity Generative Sampling for Learning with Synthetic Data
  125. Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations
  126. Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
  127. Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs