mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sun 21 Jul 2024

117 papers

  1. CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  2. VideoGameBunny: Towards vision assistants for video gamesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  3. SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge LinkingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  4. MIBench: Evaluating Multimodal Large Language Models over Multiple ImagesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRIDiffusion models → Medical imaging and segmentation
  6. Benchmark Granularity and Model Robustness for Image-Text RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  7. LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  8. A Practical Analysis of Human Alignment with *POLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. Efficient Visual Transformer by Learnable Token MergingEfficient LLM inference and serving → Token pruning and merging for ViTs
  10. Failures to Find Transferable Image Jailbreaks Between Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  11. HoloDreamer: Holistic 3D Panoramic World Generation from Text DescriptionsDiffusion models → 3D, point cloud and scene generation
  12. Back-in-Time Diffusion: Unsupervised Detection of Medical DeepfakesDiffusion models → Medical imaging and segmentation
  13. Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt DiversificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. D4M: Dataset Distillation via Disentangled Diffusion ModelDiffusion models → Diffusion foundations and sampling
  15. DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting LayerMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  16. Diffusion Models for Unsupervised Anomaly Detection in Fetal Brain UltrasoundDiffusion models → Medical imaging and segmentation
  17. SeqMIA: Sequential-Metric Based Membership Inference AttackLLM safety and security → Membership inference attacks
  18. Multi-Agent Causal Discovery Using Large Language ModelsLLM agents and tool use → Medical and scientific domain agents
  19. Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak PromptsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  20. Audio-visual training for improved grounding in video-text LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  21. Few-Shot Transfer Learning for Individualized Braking Intent Detection on Neuromorphic Hardware
  22. Explainable AI-based Intrusion Detection System for Industry 5.0: An Overview of the Literature, associated Challenges, the existing Solutions, and Potential Research Directions
  23. No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size
  24. Synthetic Time Series for Anomaly Detection in Cloud Microservices
  25. They Look Like Each Other: Case-based Reasoning for Explainable Depression Detection on Twitter using Large Language Models
  26. Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned
  27. AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs
  28. Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning
  29. LSTM Autoencoder-based Deep Neural Networks for Barley Genotype-to-Phenotype Prediction
  30. A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language
  31. Separable DeepONet: Breaking the Curse of Dimensionality in Physics-Informed Machine Learning
  32. Improving Prediction of Need for Mechanical Ventilation using Cross-Attention
  33. A Novel Method to Improve Quality Surface Coverage in Multi-View Capture
  34. Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection
  35. Enhancing Retinal Disease Classification from OCTA Images via Active Learning Techniques
  36. Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
  37. Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing
  38. Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
  39. Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation
  40. Conformal Predictions under Markovian Data
  41. Unifying Invariant and Variant Features for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
  42. Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation
  43. LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme
  44. On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling
  45. New Rules for Causal Identification with Background Knowledge
  46. Explaining Decisions of Agents in Mixed-Motive Games
  47. An Adaptive System for Wearable Devices to Detect Stress Using Physiological Signals
  48. XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
  49. TimeInf: Time Series Data Contribution via Influence Functions
  50. Weyl Calculus and Exactly Solvable Schr"odinger Bridges with Quadratic State Cost
  51. Genetic Algorithm to Optimize Design of Micro-Surgical Scissors
  52. Temporal Abstraction in Reinforcement Learning with Offline Data
  53. BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
  54. Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling
  55. Two eyes, Two views, and finally, One summary! Towards Multi-modal Multi-tasking Knowledge-Infused Medical Dialogue Summarization
  56. Deep State Space Recurrent Neural Networks for Time Series Forecasting
  57. TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
  58. 3D Reconstruction of the Human Colon from Capsule Endoscope Video
  59. A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech
  60. PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning
  61. Privacy-Preserving Multi-Center Differential Protein Abundance Analysis with FedProt
  62. Explainability Paths for Sustained Artistic Practice with AI
  63. Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
  64. Flow as the Cross-Domain Manipulation Interface
  65. Mask Guided Gated Convolution for Amodal Content Completion
  66. Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors
  67. HyperbolicLR: Epoch insensitive learning rate scheduler
  68. Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis
  69. Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge
  70. A Survey on Employing Large Language Models for Text-to-SQL Tasks
  71. Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
  72. Generalizing Trilateration: Approximate Maximum Likelihood Estimator for Initial Orbit Determination in Low-Earth Orbit
  73. ReAttention: Training-Free Infinite Context with Finite Attention Scope
  74. it Asparagus: A Toolkit for Autonomous, User-Guided Construction of Machine-Learned Potential Energy Surfaces
  75. TADA: Temporal Adversarial Data Augmentation for Time Series Data
  76. Rethinking Domain Adaptation and Generalization in the Era of CLIP
  77. Assessing Sample Quality via the Latent Space of Generative Models
  78. Semi-Supervised Pipe Video Temporal Defect Interval Localization
  79. Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
  80. The VEP Booster: A Closed-Loop AI System for Visual EEG Biomarker Auto-generation
  81. Adversarial Circuit Evaluation
  82. FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
  83. When Can Transformers Count to n?
  84. HERGen: Elevating Radiology Report Generation with Longitudinal Data
  85. Fine-grained Gender Control in Machine Translation with Large Language Models
  86. Anchored Diffusion for Video Face Reenactment
  87. Investigating Long-term Training for Remote Sensing Object Detection
  88. Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation
  89. A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts
  90. Proximal Policy Distillation
  91. Deep multimodal saliency parcellation of cerebellar pathways: linking microstructure and individual function through explainable multitask learning
  92. Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation
  93. Chemical Reaction Extraction from Long Patent Documents
  94. D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On
  95. Practical multi-fidelity machine learning: fusion of deterministic and Bayesian models
  96. A General Framework for Data-Use Auditing of ML Models
  97. Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling
  98. Navigation Instruction Generation with BEV Perception and Large Language Models
  99. MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery
  100. Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
All 117
  1. Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning
  2. Learning to Compile Programs to Neural Networks
  3. Relational Database Augmented Large Language Model
  4. GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction
  5. VoxDepth: Rectification of Depth Images on Edge Devices
  6. LSReGen: Large-Scale Regional Generator via Backward Guidance Framework
  7. MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation
  8. Training Zero-Shot Generalizable End-to-End Task-Oriented Dialog System Without Turn-level Dialog Annotations
  9. Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
  10. End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling
  11. Efficient Sampling for Data-Driven Frequency Stability Constraint via Forward-Mode Automatic Differentiation
  12. MedSAGa: Few-shot Memory Efficient Medical Image Segmentation using Gradient Low-Rank Projection in SAM
  13. Self-training Room Layout Estimation via Geometry-aware Ray-casting
  14. AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learning
  15. Enhancing Incremental Summarization with Structured Representations
  16. Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
  17. Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization