mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 1 Jun 2024

176 papers

  1. Memorized Images in Diffusion Models share a Subspace that can be Located and DeletedDiffusion models → Diffusion foundations and sampling
  2. Domain-specific ReAct for physics-integrated iterative modeling: A case study of LLM agents for gas path analysis of gas turbinesLLM agents and tool use → Financial trading and forecasting agents
  3. Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher ModelKnowledge distillation → General knowledge distillation methods
  4. RecDiff: Diffusion Model for Social RecommendationDiffusion models → Diffusion recommenders
  5. WebSuite: Systematically Evaluating Why Web Agents FailLLM agents and tool use → Web, search, and research agents
  6. Learning to Approximate Particle Smoothing Trajectories via Diffusion Generative ModelsDiffusion models → Diffusion foundations and sampling
  7. Learning to Play Air Hockey with Model-Based Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  8. FlowIE: Efficient Image Enhancement via Rectified FlowDiffusion models → Inverse problems and image restoration
  9. Improving Text Generation on Images with Synthetic CaptionsDiffusion models → Image generation, text-to-image and editing
  10. Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect DetectionDiffusion models → Flow matching, time series and science
  11. Research on the Application of Computer Vision Based on Deep Learning in Autonomous Driving TechnologyEnd-to-end autonomous driving → End-to-end system architecture
  12. Exploring the limits of Hierarchical World Models in Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
  13. Efficient Open Set Single Image Test Time Adaptation of Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIPDiffusion models → Image generation, text-to-image and editing
  15. Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  16. Dual Hyperspectral Mamba for Efficient Spectral Compressive ImagingState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  17. Artificial Generational Intelligence: Cultural Accumulation in Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  18. Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured EnvironmentsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  19. AudioLCM: Text-to-Audio Generation with Latent Consistency ModelsDiffusion models → Audio, speech and music
  20. DeCoOp: Robust Prompt Tuning with Out-of-Distribution DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  21. Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow MatchingDiffusion models → Audio, speech and music
  22. HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language ModelLLM reasoning → Spatial and embodied reasoning
  23. Multi-Dimensional Optimization for Text Summarization via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  24. GenPalm: Contactless Palmprint Generation with Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  25. A Closer Look at Logical Reasoning with LLMs: The Choice of Tool MattersLLM reasoning → Reasoning benchmarks and evaluation
  26. A Single-Loop Robust Policy Gradient Method for Robust Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  27. Temporally Consistent Object Editing in Videos using Extended AttentionDiffusion models → Video generation
  28. Artemis: Towards Referential Understanding in Complex VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  29. Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMsLLM reasoning → Multimodal reasoning +1
  30. Towards Rationality in Language and Multimodal Agents: A SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. Controlling Large Language Model Agents with Entropic Activation SteeringLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  32. Exploring Vulnerabilities and Protections in Large Language Models: A SurveyLLM safety and security → Prompt injection and agent security
  33. Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models
  34. Improvement of Applicability in Student Performance Prediction Based on Transfer Learning
  35. Group Projected Subspace Pursuit for Block Sparse Signal Reconstruction: Convergence Analysis and Applications
  36. Amortizing Pragmatic Program Synthesis with Rankings
  37. Modelling financial volume curves with hierarchical Poisson processes
  38. Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis
  39. Lightening Anything in Medical Images
  40. RGFN: Synthesizable Molecular Generation Using GFlowNets
  41. Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection
  42. Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach
  43. An Evaluation Benchmark for Autoformalization in Lean4
  44. Effective Data Selection for Seismic Interpretation through Disagreement
  45. Phased Instruction Fine-Tuning for Large Language Models
  46. Large Language Model Confidence Estimation via Black-Box Access
  47. Data Quality in Edge Machine Learning: A State-of-the-Art Survey
  48. Privacy-Aware Randomized Quantization via Linear Programming
  49. Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems
  50. CoNO: Complex Neural Operator for Continous Dynamical Physical Systems
  51. Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
  52. Graph Neural Networks for Brain Graph Learning: A Survey
  53. On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
  54. SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems
  55. Equivariant amortized inference of poses for cryo-EM
  56. GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models
  57. Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition
  58. On the Sample Complexity of Set Membership Estimation for Linear Systems with Disturbances Bounded by Convex Sets
  59. VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability
  60. An Image Segmentation Model with Transformed Total Variation
  61. A Gaussian Process-based Streaming Algorithm for Prediction of Time Series With Regimes and Outliers
  62. Redefining Contributions: Shapley-Driven Federated Learning
  63. An Unsupervised Approach for Periodic Source Detection in Time Series
  64. SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing
  65. Length-scale study in deep learning prediction for non-small cell lung cancer brain metastasis
  66. Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming
  67. Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batch
  68. Strategic Linear Contextual Bandits
  69. Zero Inflation as a Missing Data Problem: a Proxy-based Approach
  70. LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
  71. Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation
  72. Leveraging Knowlegde Graphs for Interpretable Feature Generation
  73. CONFINE: Conformal Prediction for Interpretable Neural Networks
  74. Towards an ontology of portions of matter to support multi-scale analysis and provenance tracking
  75. Causal Contrastive Learning for Counterfactual Regression Over Time
  76. Breast Cancer Diagnosis: A Comprehensive Exploration of Explainable Artificial Intelligence (XAI) Techniques
  77. On the Use of Anchoring for Training Vision Models
  78. Adaptive boosting with dynamic weight adjustment
  79. Learning Discrete Concepts in Latent Hierarchical Models
  80. A Survey on Large Language Models for Code Generation
  81. On the use of first and second derivative approximations for biometric online signature recognition
  82. Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection
  83. Empirical influence functions to understand the logic of fine-tuning
  84. Prompt Chaining or Stepwise Prompt? Refinement in Text Summarization
  85. Research on an Autonomous UAV Search and Rescue System Based on the Improved
  86. Schr"odinger Bridge with Quadratic State Cost is Exactly Solvable
  87. Non-geodesically-convex optimization in the Wasserstein space
  88. 2nd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation
  89. Conformal Transformation of Kernels: A Geometric Perspective on Text Classification
  90. Recent Advances in End-to-End Simultaneous Speech Translation
  91. Audio-Visual Talker Localization in Video for Spatial Sound Reproduction
  92. Activation-Descent Regularization for Input Optimization of ReLU Networks
  93. A Deep Learning Model for Coronary Artery Segmentation and Quantitative Stenosis Detection in Angiographic Images
  94. Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
  95. Federated Model Heterogeneous Matryoshka Representation Learning
  96. Optimistic Rates for Learning from Label Proportions
  97. AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
  98. End-to-End Model-based Deep Learning for Dual-Energy Computed Tomography Material Decomposition
  99. Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth
  100. Pedestrian intention prediction in Adverse Weather Conditions with Spiking Neural Networks and Dynamic Vision Sensors
All 176
  1. Learning to Solve Multiresolution Matrix Factorization by Manifold Optimization and Evolutionary Metaheuristics
  2. Towards a Unified Framework of Clustering-based Anomaly Detection
  3. Bilateral Guided Radiance Field Processing
  4. DroneVis: Versatile Computer Vision Library for Drones
  5. Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
  6. Generating 3D Terrain with 2D Cellular Automata
  7. Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks
  8. Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture
  9. Learning Manipulation by Predicting Interaction
  10. Stein Random Feature Regression
  11. MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors
  12. Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
  13. SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead
  14. Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
  15. Towards Generalizable Multi-Object Tracking
  16. You Only Need Less Attention at Each Stage in Vision Transformers
  17. InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
  18. A Batch Sequential Halving Algorithm without Performance Degradation
  19. Multimodal Metadata Assignment for Cultural Heritage Artifacts
  20. GATE: How to Keep Out Intrusive Neighbors
  21. Representation and De-interleaving of Mixtures of Hidden Markov Processes
  22. Neural Combinatorial Optimization Algorithms for Solving Vehicle Routing Problems: A Comprehensive Survey with Perspectives
  23. Posterior Label Smoothing for Node Classification
  24. Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach
  25. Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks
  26. Dual-perspective Cross Contrastive Learning in Graph Transformers
  27. Stochastic Resetting Mitigates Latent Gradient Bias of SGD from Label Noise
  28. Learning Causal Abstractions of Linear Structural Causal Models
  29. Gender Bias Detection in Court Decisions: A Brazilian Case Study
  30. DS@BioMed at ImageCLEFmedical Caption 2024: Enhanced Attention Mechanisms in Medical Caption Generation through Concept Detection Integration
  31. Understanding the Convergence in Balanced Resonate-and-Fire Neurons
  32. CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
  33. SpikeMM: Flexi-Magnification of High-Speed Micro-Motions
  34. HonestLLM: Toward an Honest and Helpful Large Language Model
  35. Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis
  36. Algebraic Geometrical Analysis of Metropolis Algorithm When Parameters Are Non-identifiable
  37. Learning Spatiotemporal Dynamical Systems from Point Process Observations
  38. RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis
  39. SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions
  40. An Effective Weight Initialization Method for Deep Learning: Application to Satellite Image Classification
  41. E3-Net: Efficient E(3)-Equivariant Normal Estimation Network
  42. Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction
  43. Beyond Metrics: Evaluating LLMs' Effectiveness in Culturally Nuanced, Low-Resource Real-World Scenarios
  44. DSCA: A Digital Subtraction Angiography Sequence Dataset and Spatio-Temporal Model for Cerebral Artery Segmentation
  45. Turnstile ℓp leverage score sampling with applications
  46. Benchmarking for Deep Uplift Modeling in Online Marketing
  47. Image Captioning via Dynamic Path Customization
  48. A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning
  49. Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR Images
  50. Optimal bounds for ℓp sensitivity sampling via ℓ2 augmentation
  51. Quality Sentinel: Estimating Label Quality and Errors in Medical Segmentation Datasets
  52. Do's and Don'ts: Learning Desirable Skills with Instruction Videos
  53. KGLink: A column type annotation method that combines knowledge graph and pre-trained language model
  54. Combining Experimental and Historical Data for Policy Evaluation
  55. Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environments
  56. CASE: Efficient Curricular Data Pre-training for Building Assistive Psychology Expert Models
  57. From Seedling to Harvest: The GrowingSoy Dataset for Weed Detection in Soy Crops via Instance Segmentation
  58. FedAST: Federated Asynchronous Simultaneous Training
  59. Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
  60. Complex Style Image Transformations for Domain Generalization in Medical Images
  61. Creative Text-to-Audio Generation via Synthesizer Programming
  62. Multi-Objective Neural Architecture Search by Learning Search Space Partitions
  63. Phasor-Driven Acceleration for FFT-based CNNs
  64. Neural Optimal Transport with Lagrangian Costs
  65. Adversarial 3D Virtual Patches using Integrated Gradients
  66. Cross-Table Pretraining towards a Universal Function Space for Heterogeneous Tabular Data
  67. Hybrid attention structure preserving network for reconstruction of under-sampled OCT images
  68. Machine Learning-Assisted Sustainable Remanufacturing, Reusing and Recycling for Lithium-ion Batteries
  69. StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
  70. Upright adjustment with graph convolutional networks
  71. Contrastive Learning Via Equivariant Representation
  72. PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify
  73. Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning
  74. Large Language Models for Relevance Judgment in Product Search
  75. A Review of Pulse-Coupled Neural Network Applications in Computer Vision and Image Processing
  76. Robust Biharmonic Skinning Using Geometric Fields