mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 22 Sep 2024

134 papers

  1. Protein-Mamba: Biological Mamba Models for Protein Function PredictionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  2. Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  3. Implicit Dynamical Flow Fusion (IDFF) for Generative ModelingDiffusion models → Flow matching, time series and science
  4. URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  5. Backtracking Improves Generation SafetyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  6. Exploiting Exogenous Structure for Sample-Efficient Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  7. RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge GraphRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  8. Distributionally Robust Inverse Reinforcement Learning for Identifying Multi-Agent Coordinated SensingOffline RL and imitation learning from data → Inverse reinforcement learning
  9. What Are They Doing? Joint Audio-Speech Co-ReasoningLLM reasoning → Audio-language model reasoning
  10. Order of Magnitude Speedups for LLM Membership InferenceLLM safety and security → Membership inference attacks
  11. A is for Absorption: Studying Feature Splitting and Absorption in Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  12. Thought-Path Contrastive Learning via Premise-Oriented Data Augmentation for Logical Reading ComprehensionLLM reasoning → Reasoning benchmarks and evaluation
  13. Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPFOffline RL and imitation learning from data → Imitation learning methods
  14. Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception AttacksEnd-to-end autonomous driving → Large language models for driving +1
  15. Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  16. Sampling-Pattern-Agnostic MRI Reconstruction through Adaptive Consistency Enforcement with Diffusion ModelDiffusion models → Medical imaging and segmentation
  17. A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural LanguageDiffusion models → Flow matching, time series and science
  18. Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic HintsLLM reasoning → Reasoning benchmarks and evaluation
  19. Adaptive Compensation for Robotic Joint Failures Using Partially Observable Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. COSBO: Conservative Offline Simulation-Based Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms +1
  21. Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  22. GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature LearningState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  23. Prior Knowledge Distillation Network for Face Super-ResolutionKnowledge distillation → General knowledge distillation methods
  24. The Ability of Large Language Models to Evaluate Constraint-satisfaction in Agent Responses to Open-ended RequestsLLM agents and tool use → General LLM agent frameworks and benchmarks
  25. Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language ModelsEfficient LLM inference and serving → Prompt and context compression
  26. MobileViews: A Million-scale and Diverse Mobile GUI DatasetMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  27. Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie SynopsesLLM reasoning → Multimodal reasoning
  28. Anisotropic Diffusion Probabilistic Model for Imbalanced Image ClassificationDiffusion models → Diffusion foundations and sampling
  29. DilateQuant: Accurate and Efficient Diffusion Quantization via Weight DilationDiffusion models → Diffusion foundations and sampling
  30. An Uncertainty-Aware Generalization Framework for Cardiovascular Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  31. Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  32. Margin-bounded Confidence Scores for Out-of-Distribution Detection
  33. SARF: Enhancing Stock Market Prediction with Sentiment-Augmented Random Forest
  34. Diagnosis and Pathogenic Analysis of Autism Spectrum Disorder Using Fused Brain Connection Graph
  35. Causal Inference with Double/Debiased Machine Learning for Evaluating the Health Effects of Multiple Mismeasured Pollutants
  36. Linear Independence of Generalized Neurons and Related Functions
  37. Floating-floating point: a highly accurate number representation with flexible Counting ranges
  38. SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
  39. EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars
  40. Prediction and Detection of Terminal Diseases Using Internet of Medical Things: A Review
  41. On the Within-class Variation Issue in Alzheimer's Disease Detection
  42. Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
  43. Supply Risk-Aware Alloy Discovery and Design
  44. Coverage and Bias of Street View Imagery in Mapping the Urban Environment
  45. EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
  46. Can a Neural Model Guide Fieldwork? A Case Study on Morphological Data Collection
  47. SOS: Segment Object System for Open-World Instance Segmentation With Object Priors
  48. From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
  49. LatentQGAN: A Hybrid QGAN with Classical Convolutional Autoencoder
  50. Secrets of Edge-Informed Contrast Maximization for Event-Based Vision
  51. Patch Ranking: Efficient CLIP by Learning to Rank Local Patches
  52. Brain Surgery: Ensuring GDPR Compliance in Large Language Models via Concept Erasure
  53. Can pre-trained language models generate titles for research papers?
  54. EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models
  55. Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies
  56. Explainable AI needs formalization
  57. A convergent scheme for the Bayesian filtering problem based on the Fokker--Planck equation and deep splitting
  58. The X Types -- Mapping the Semantics of the Twitter Sphere
  59. LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenarios
  60. AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way
  61. Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries
  62. Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions
  63. Encoder with the Empirical Mode Decomposition (EMD) to remove muscle artefacts from EEG signal
  64. Event-ECC: Asynchronous Tracking of Events with Continuous Optimization
  65. GlamTry: Advancing Virtual Try-On for High-End Accessories
  66. Unleashing the Power of Emojis in Texts via Self-supervised Graph Pre-Training
  67. Adaptive Feedforward Gradient Estimation in Neural ODEs
  68. Why Is Anything Conscious?
  69. TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps
  70. Towards Model-Agnostic Dataset Condensation by Heterogeneous Models
  71. RobotFingerPrint: Unified Gripper Coordinate Space for Multi-Gripper Grasp Synthesis and Transfer
  72. Beyond Words: Evaluating Large Language Models in Transportation Planning
  73. SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms
  74. Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
  75. GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
  76. On a measure of intelligence
  77. Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
  78. Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization
  79. One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance
  80. Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort
  81. Lesion Segmentation in Whole-Body Multi-Tracer PET-CT Images; a Contribution to AutoPET 2024 Challenge
  82. SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration
  83. On logic and generative AI
  84. AggregHate: An Efficient Aggregative Approach for the Detection of Hatemongers on Social Platforms
  85. Low-Light Enhancement Effect on Classification and Detection: An Empirical Study
  86. Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
  87. Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends
  88. Scoring rule nets: beyond mean target prediction in multivariate regression
  89. A High-Performance External Validity Index for Clustering with a Large Number of Clusters
  90. A Unified Approach for Learning the Dynamics of Power System Generators and Inverter-based Resources
  91. Detection of pulmonary pathologies using convolutional neural networks, Data Augmentation, ResNet50 and Vision Transformers
  92. Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection
  93. A Visualized Malware Detection Framework with CNN and Conditional GAN
  94. Automotive innovation landscaping using LLM
  95. OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength
  96. EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition
  97. Pomo3D: 3D-Aware Portrait Accessorizing and More
  98. Challenging the Performance-Interpretability Trade-off: An Evaluation of Interpretable Machine Learning Models
  99. Dormant: Defending against Pose-driven Human Image Animation
  100. Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance
All 134
  1. Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
  2. Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
  3. Predicting User Stances from Target-Agnostic Information using Large Language Models
  4. Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction
  5. MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting
  6. Investigating Layer Importance in Large Language Models
  7. GroupDiff: Diffusion-based Group Portrait Editing
  8. Sparse Low-Ranked Self-Attention Transformer for Remaining Useful Lifetime Prediction of Optical Fiber Amplifiers
  9. To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems
  10. J2N -- Nominal Adjective Identification and its Application
  11. Evaluating the Quality of Code Comments Generated by Large Language Models for Novice Programmers
  12. MANTA -- Model Adapter Native generations that's Affordable
  13. Using Natural Language Processing to find Indication for Burnout with Text Classification: From Online Data to Real-World Data
  14. A Feature Engineering Approach for Literary and Colloquial Tamil Speech Classification using 1D-CNN
  15. Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation
  16. Self-Supervised Audio-Visual Soundscape Stylization
  17. Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
  18. MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators
  19. PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects
  20. Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues
  21. Transforming Multidimensional Time Series into Interpretable Event Sequences for Advanced Data Mining
  22. Scene-Text Grounding for Text-Based Video Question Answering
  23. MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views
  24. Sketch 'n Solve: An Efficient Python Package for Large-Scale Least Squares Using Randomized Numerical Linear Algebra
  25. LLMs are One-Shot URL Classifiers and Explainers
  26. Reliable and diverse evaluation of LLM medical knowledge mastery
  27. A competitive baseline for deep learning enhanced data assimilation using conditional Gaussian ensemble Kalman filtering
  28. HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation
  29. Opinion Mining on Offshore Wind Energy for Environmental Engineering
  30. Deep Learning Technology for Face Forgery Detection: A Survey
  31. ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination
  32. Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning
  33. Proof Automation with Large Language Models
  34. Lidar Panoptic Segmentation in an Open World