mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 23 Aug 2023

226 papers

  1. A Survey of Graph UnlearningLLM safety and security → Graph unlearning
  2. Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionDiffusion models → Medical imaging and segmentation
  3. InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion ModelDiffusion models → Medical imaging and segmentation
  4. Augmenting medical image classifiers with synthetic data from latent diffusion modelsDiffusion models → Medical imaging and segmentation
  5. Renormalizing Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  6. Improving Generative Model-based Unfolding with Schr"odinger BridgesDiffusion models → Diffusion foundations and sampling
  7. Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic SegmentationDiffusion models → Medical imaging and segmentation
  8. KL Convergence Guarantees for Score diffusion models under minimal data assumptionsDiffusion models → Diffusion foundations and sampling
  9. Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-FinetuningDiffusion models → Discrete and text diffusion
  10. A Probabilistic Fluctuation based Membership Inference Attack for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  11. Category Adaptation Meets Projected Distillation in Generalized Continual Category DiscoveryKnowledge distillation → General knowledge distillation methods
  12. Identifying Reaction-Aware Driving Styles of Stochastic Model Predictive Controlled Vehicles by Inverse Reinforcement LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  13. MM-LIMA: Less Is More for Alignment in Multi-Modal DatasetsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert InferenceMixture-of-experts → Efficient MoE training and inference systems
  15. Manipulating Embeddings of Stable Diffusion PromptsDiffusion models → Image generation, text-to-image and editing
  16. Aligning Language Models with Offline Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  17. Large Multilingual Models Pivot Zero-Shot Multimodal Learning across LanguagesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  19. Quantum-Noise-Driven Generative Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  20. EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoEMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  21. CED: Consistent ensemble distillation for audio taggingKnowledge distillation → Speech and audio distillation
  22. High-quality Image Dehazing with Diffusion ModelDiffusion models → Inverse problems and image restoration
  23. Efficient Transfer Learning in Diffusion Models via Adversarial NoiseDiffusion models → Diffusion foundations and sampling
  24. LongDanceDiff: Long-term Dance Generation with Conditional Diffusion ModelDiffusion models → Audio, speech and music
  25. Boosting Diffusion Models with an Adaptive Momentum SamplerDiffusion models → Diffusion foundations and sampling
  26. Audio Generation with Multiple Conditional Diffusion ModelDiffusion models → Audio, speech and music
  27. Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMsLLM reasoning → Causal reasoning in LLMs +1
  28. Computational models of object motion detectors accelerated using FPGA technology
  29. Vulnerability Clustering and other Machine Learning Applications of Semantic Vulnerability Embeddings
  30. DF-3DFace: One-to-Many Speech Synchronized 3D Face Animation with Diffusion
  31. Towards Safe Autonomy in Hybrid Traffic: Detecting Unpredictable Abnormal Behaviors of Human Drivers via Information Sharing
  32. Computational limits to the legibility of the imaged human brain
  33. Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network
  34. A Systematic Study on Quantifying Bias in GAN-Augmented Data
  35. Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models
  36. Performance Comparison of Design Optimization and Deep Learning-based Inverse Design
  37. An approach based on Open Research Knowledge Graph for Knowledge Acquisition from scientific papers
  38. Diagnosing Infeasible Optimization Problems Using Large Language Models
  39. LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition
  40. MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
  41. Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis
  42. Overcoming Generic Knowledge Loss with Selective Parameter Update
  43. Consistent Signal Reconstruction from Streaming Multivariate Time Series
  44. PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learning
  45. ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization
  46. MOFO: MOtion FOcused Self-Supervision for Video Understanding
  47. An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems
  48. TAI-GAN: Temporally and Anatomically Informed GAN for early-to-late frame conversion in dynamic cardiac PET motion correction
  49. HNAS-reg: hierarchical neural architecture search for deformable medical image registration
  50. BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
  51. Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges
  52. Characterising representation dynamics in recurrent neural networks for object recognition
  53. A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications
  54. Evolution of ESG-focused DLT Research: An NLP Analysis of the Literature
  55. Toward American Sign Language Processing in the Real World: Data, Tasks, and Methods
  56. Reframing the Brain Age Prediction Problem to a More Interpretable and Quantitative Approach
  57. Benchmarking Causal Study to Interpret Large Language Models for Source Code
  58. A Theory of Intelligences
  59. An Initial Exploration: Learning to Generate Realistic Audio for Silent Video
  60. Self-Supervised Learning for Endoscopic Video Analysis
  61. Machine learning in parameter estimation of nonlinear systems
  62. Missing Data Imputation Based on Dynamically Adaptable Structural Equation Modeling with Self-Attention
  63. With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning
  64. FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features
  65. Vision Transformer Adapters for Generalizable Multitask Learning
  66. Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature Augmentation
  67. AdVerb: Visually Guided Audio Dereverberation
  68. SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies
  69. Continual Zero-Shot Learning through Semantically Guided Generative Random Walks
  70. Saliency-based Video Summarization for Face Anti-spoofing
  71. Predicting Drug Solubility Using Different Machine Learning Methods -- Linear Regression Model with Extracted Chemical Features vs Graph Convolutional Neural Network
  72. Understanding Dark Scenes by Contrasting Multi-Modal Observations
  73. RemovalNet: DNN Fingerprint Removal Attacks
  74. Graph Neural Stochastic Differential Equations
  75. Trustworthy Representation Learning Across Domains
  76. Gaze Estimation on Spresense
  77. Physics informed Neural Networks applied to the description of wave-particle resonance in kinetic simulations of fusion plasmas
  78. Fast Exact NPN Classification with Influence-aided Canonical Form
  79. CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images
  80. D4: Improving LLM Pretraining via Document De-Duplication and Diversification
  81. Extended Linear Regression: A Kalman Filter Approach for Minimizing Loss via Area Under the Curve
  82. On-Manifold Projected Gradient Descent
  83. Simple is Better and Large is Not Enough: Towards Ensembling of Foundational Language Models
  84. A Generative Approach for Image Registration of Visible-Thermal (VT) Cancer Faces
  85. Language Reward Modulation for Pretraining Reinforcement Learning
  86. Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement
  87. Prompt2Model: Generating Deployable Models from Natural Language Instructions
  88. Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders
  89. How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy
  90. How to Protect Copyright Data in Optimization of Large Language Models?
  91. Multi-Objective Optimization for Sparse Deep Multi-Task Learning
  92. LLMRec: Benchmarking Large Language Models on Recommendation Task
  93. MolGrapher: Graph-based Visual Recognition of Chemical Structures
  94. SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation
  95. Enhancing cardiovascular risk prediction through AI-enabled calcium-omics
  96. Critical Learning Periods Emerge Even in Deep Linear Networks
  97. CIParsing: Unifying Causality Properties into Multiple Human Parsing
  98. SG-Former: Self-guided Transformer with Evolving Token Reallocation
  99. SoK: Machine Learning for Misinformation Detection
  100. CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No
All 226
  1. Learning to Learn Financial Networks for Optimising Momentum Strategies
  2. ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
  3. Curriculum Learning with Adam: The Devil Is in the Wrong Details
  4. Towards Real-Time Analysis of Broadcast Badminton Videos
  5. Self-Supervised Knowledge-Driven Deep Learning for 3D Magnetic Inversion
  6. Robustness Analysis of Continuous-Depth Models with Lagrangian Techniques
  7. Sign Language Translation with Iterative Prototype
  8. Development and external validation of a lung cancer risk estimation tool using gradient-boosting
  9. Unsupervised anomalies detection in IIoT edge devices networks using federated learning
  10. Tumor-Centered Patching for Enhanced Medical Image Segmentation
  11. NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos
  12. Data-driven decision-focused surrogate modeling
  13. Evaluation of Faithfulness Using the Longest Supported Subsequence
  14. Multimodal Latent Emotion Recognition from Micro-expression and Physiological Signals
  15. Mesh Conflation of Oblique Photogrammetric Models using Virtual Cameras and Truncated Signed Distance Field
  16. Select-and-Combine (SAC): A Novel Multi-Stereo Depth Fusion Algorithm for Point Cloud Generation via Efficient Local Markov Netlets
  17. Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection
  18. Semantic Change Detection for the Romanian Language
  19. Masking Strategies for Background Bias Removal in Computer Vision Models
  20. An Accelerated Block Proximal Framework with Adaptive Momentum for Nonconvex and Nonsmooth Optimization
  21. An Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators
  22. The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures
  23. Less is More -- Towards parsimonious multi-task models using structured sparsity
  24. Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey
  25. Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection
  26. Constrained Stein Variational Trajectory Optimization
  27. The Local Learning Coefficient: A Singularity-Aware Complexity Measure
  28. Instruction Position Matters in Sequence Generation with Large Language Models
  29. Cached Operator Reordering: A Unified View for Fast GNN Training
  30. Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
  31. DISGAN: Wavelet-informed Discriminator Guides GAN to MRI Super-resolution with Noise Cleaning
  32. Stabilizing RNN Gradients through Pre-training
  33. Ensembling Uncertainty Measures to Improve Safety of Black-Box Classifiers
  34. SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels
  35. HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing
  36. FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
  37. DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration
  38. Sample Complexity of Robust Learning against Evasion Attacks
  39. Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
  40. Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation
  41. Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation
  42. CgT-GAN: CLIP-guided Text GAN for Image Captioning
  43. A multiobjective continuation method to compute the regularization path of deep neural networks
  44. IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning
  45. Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track
  46. RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D
  47. PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine
  48. From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
  49. CACTUS: a Comprehensive Abstraction and Classification Tool for Uncovering Structures
  50. Prompt-Based Length Controlled Generation with Reinforcement Learning
  51. Dual-Balancing for Multi-Task Learning
  52. LKPNR: LLM and KG for Personalized News Recommendation Framework
  53. Knowledge-injected Prompt Learning for Chinese Biomedical Entity Normalization
  54. Reranking Passages with Coarse-to-Fine Neural Retriever Enhanced by List-Context Information
  55. Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
  56. Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
  57. MKL-L0/1-SVM
  58. StofNet: Super-resolution Time of Flight Network
  59. Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature
  60. Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition
  61. Neural oscillators for magnetic hysteresis modeling
  62. Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment
  63. On Universally Optimal Algorithms for A/B Testing
  64. Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
  65. Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrieval
  66. Critical Evaluation of Artificial Intelligence as Digital Twin of Pathologist for Prostate Cancer Pathology
  67. Relational Concept Bottleneck Models
  68. RankMixup: Ranking-Based Mixup Training for Network Calibration
  69. Multi-Modal Multi-Task (3MT) Road Segmentation
  70. Rotation-Invariant Completion Network
  71. Will More Expressive Graph Neural Networks do Better on Generative Tasks?
  72. Approximating Score-based Explanation Techniques Using Conformal Regression
  73. Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields
  74. Anisotropic Hybrid Networks for liver tumor segmentation with uncertainty quantification
  75. Value of Assistance for Mobile Agents
  76. Maintaining Plasticity in Continual Learning via Regenerative Regularization
  77. When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation
  78. Pose Modulated Avatars from Video
  79. Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecasting
  80. RamseyRL: A Framework for Intelligent Ramsey Number Counterexample Searching
  81. Retail Demand Forecasting: A Comparative Study for Multivariate Time Series
  82. Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification
  83. System Identification for Continuous-time Linear Dynamical Systems
  84. Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement
  85. Dynamic landslide susceptibility mapping over recent three decades to uncover variations in landslide causes in subtropical urban mountainous areas
  86. OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
  87. Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies
  88. Solving Elliptic Optimal Control Problems via Neural Networks and Optimality System
  89. Diverse Policies Converge in Reward-free Markov Decision Processe
  90. Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement
  91. Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification
  92. AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection
  93. LFS-GAN: Lifelong Few-Shot Image Generation
  94. Semantic-Aware Implicit Template Learning via Part Deformation Consistency
  95. Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach
  96. ACLS: Adaptive and Conditional Label Smoothing for Network Calibration
  97. Edge-aware Hard Clustering Graph Pooling for Brain Imaging
  98. On Using Admissible Bounds for Learning Forward Search Heuristics
  99. Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation
  100. Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification
  101. HashReID: Dynamic Network with Binary Codes for Efficient Person Re-identification
  102. Exploring the Optimization Objective of One-Class Classification for Anomaly Detection
  103. Age Prediction From Face Images Via Contrastive Learning
  104. Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
  105. Bridging the Gap: Deciphering Tabular Data Using Large Language Model
  106. Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models
  107. A Unified Framework for 3D Point Cloud Visual Grounding
  108. YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
  109. Adversarial Training Using Feedback Loops
  110. SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
  111. Cabrita: closing the gap for foreign languages
  112. Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach
  113. Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking
  114. Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch
  115. Dcc --help: Generating Context-Aware Compiler Error Explanations with Large Language Models
  116. KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods
  117. Example-Based Framework for Perceptually Guided Audio Texture Generation
  118. CoC-GAN: Employing Context Cluster for Unveiling a New Pathway in Image Generation
  119. Finding the Perfect Fit: Applying Regression Models to ClimateBench v1.0
  120. A Mobile Data-Driven Hierarchical Deep Reinforcement Learning Approach for Real-time Demand-Responsive Railway Rescheduling and Station Overcrowding Mitigation
  121. A Data-Driven Approach to Morphogenesis under Structural Instability
  122. SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
  123. rm E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  124. A Survey for Federated Learning Evaluations: Goals and Measures
  125. Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition
  126. A Benchmark Study on Calibration