mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 2 Aug 2024

210 papers

  1. GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPSEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  2. Conformal Diffusion Models for Individual Treatment Effect Estimation and InferenceDiffusion models → Diffusion foundations and sampling
  3. Adaptive Planning with Generative Models under UncertaintyDeep reinforcement learning methods → RL with diffusion and flow models
  4. Mission Impossible: A Statistical Perspective on Jailbreaking LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  5. Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  6. The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation AnalysisMechanistic interpretability → Circuits and mechanistic analysis
  7. Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
  8. Coalitions of Large Language Models Increase the Robustness of AI AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  10. Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed InputsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious CodeLLM safety and security → Watermarking generated content and models
  12. HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate PredictionMixture-of-experts → MoE for recommender systems
  13. A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different TasksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and ResamplingDiffusion models → 3D, point cloud and scene generation
  15. Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image EnhancementState-space sequence models (S4, Mamba) → Mamba for image restoration
  16. RAGEval: Scenario Specific RAG Evaluation Dataset Generation FrameworkRetrieval-augmented generation → RAG pipeline design and evaluation
  17. Jacta: A Versatile Planner for Learning Dexterous and Whole-body ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  18. Deep progressive reinforcement learning-based flexible resource scheduling framework for IRS and UAV-assisted MEC systemDeep reinforcement learning methods → RL for energy, networks and operations
  19. CLIP4Sketch: Enhancing Sketch to Mugshot Matching through Dataset Augmentation using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  20. WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  21. The Phantom Menace: Unmasking Privacy Leakages in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  22. Multi-head Spatial-Spectral Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  23. Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous SystemsDeep reinforcement learning methods → RL for games and combinatorial optimization
  24. Optimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  25. Astra: Efficient Transformer Architecture and Contrastive Dynamics Learning for Embodied Instruction FollowingVision-language-action models → Human-video and latent-action pretraining
  26. A Survey of MambaState-space sequence models (S4, Mamba) → Core SSM architectures for language
  27. Agentic LLM Workflows for Generating Patient-Friendly Medical ReportsLLM agents and tool use → Medical and scientific domain agents
  28. BioRAG: A RAG-LLM Framework for Biological Question ReasoningLLM reasoning → Clinical and biomedical applications +1
  29. Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory InstructionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  30. Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy ContextsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  31. A Survey on Self-play Methods in Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  32. Towards Agentic Runtime HealingLLM agents and tool use → Software engineering coding agents
  33. Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMixLLM safety and security → Membership inference attacks
  34. Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  35. Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  36. FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image TranslationDiffusion models → Image generation, text-to-image and editing
  37. A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid EnvironmentsDeep reinforcement learning methods → Safe and constrained RL
  38. On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Responsible AI Question Bank: A Comprehensive Tool for AI Risk Assessment
  40. A General-Purpose Device for Interaction with LLMs
  41. ECG Unveiled: Analysis of Client Re-identification Risks in Real-World ECG Datasets
  42. SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes
  43. Regularized Contrastive Partial Multi-view Outlier Detection
  44. SumRecom: A Personalized Summarization Approach by Learning from Users' Feedback
  45. Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course
  46. Telecom Foundation Models: Applications, Challenges, and Future Trends
  47. A semantic approach to mapping the Provenance Ontology to Basic Formal Ontology
  48. Spatio-Temporal Partial Sensing Forecast for Long-term Traffic
  49. A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training data
  50. Compositional Physical Reasoning of Objects and Events from Videos
  51. A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications
  52. Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
  53. Deep Learning Meets OBIA: Tasks, Challenges, Strategies, and Perspectives
  54. CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
  55. FIVB ranking: Misstep in the right direction
  56. Physics-Informed Geometry-Aware Neural Operator
  57. Trustworthy Machine Learning under Social and Adversarial Data Sources
  58. Deep Learning Approach for Ear Recognition and Longitudinal Evaluation in Children
  59. LibreLog: Accurate and Efficient Unsupervised Log Parsing Using Open-Source Large Language Models
  60. Huge Ensembles Part II: Properties of a Huge Ensemble of Hindcasts Generated with Spherical Fourier Neural Operators
  61. THOR2: Topological Analysis for 3D Shape and Color-Based Human-Inspired Object Recognition in Unseen Environments
  62. Deep Learning Framework for History Matching CO2 Storage with 4D Seismic and Monitoring Well Data
  63. Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
  64. On Validation of Search & Retrieval of Tissue Images in Digital Pathology
  65. Full-range Head Pose Geometric Data Augmentations
  66. Embodiment: Self-Supervised Depth Estimation Based on Camera Models
  67. Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring
  68. Enhanced Knee Kinematics: Leveraging Deep Learning and Morphing Algorithms for 3D Implant Modeling
  69. Robot-Enabled Machine Learning-Based Diagnosis of Gastric Cancer Polyps Using Partial Surface Tactile Imaging
  70. Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation
  71. Trainable Pointwise Decoder Module for Point Cloud Segmentation
  72. Momentum Capture and Prediction System Based on Wimbledon Open2023 Tournament Data
  73. Non-linear Analysis Based ECG Classification of Cardiovascular Disorders
  74. Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
  75. SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts
  76. Active Learning for Neural PDE Solvers
  77. An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression
  78. Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization
  79. A Structured Framework for Predicting Sustainable Aviation Fuel Properties using Liquid-Phase FTIR and Machine Learning
  80. Can multivariate Granger causality detect directed connectivity of a multistable and dynamic biological decision network model?
  81. Using LLMs to Establish Implicit User Sentiment of Software Desirability
  82. Recognizing and Reconstructing a Multi-Unit Floor Plan
  83. Gradient flow in parameter space is equivalent to linear interpolation in output space
  84. MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts
  85. Efficient Graph Coloring with Neural Networks: A Physics-Inspired Approach for Large Graphs
  86. NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities
  87. Using a CNN Model to Assess Paintings' Creativity
  88. Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting
  89. DebateQA: Evaluating Question Answering on Debatable Knowledge
  90. Conditional LoRA Parameter Generation
  91. Derivation of Back-propagation for Graph Convolutional Networks using Matrix Calculus and its Application to Explainable Artificial Intelligence
  92. Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
  93. FT K-means: A High-Performance K-means on GPU with Fault Tolerance
  94. NeuralBeta: Estimating Beta Using Deep Learning
  95. NOLO: Navigate Only Look Once
  96. Explaining a probabilistic prediction on the simplex with Shapley compositions
  97. Resampling and averaging coordinates on data
  98. Adaptive Recruitment Resource Allocation to Improve Cohort Representativeness in Participatory Biomedical Datasets
  99. Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent
  100. EVIT: Event-based Visual-Inertial Tracking in Semi-Dense Maps Using Windowed Nonlinear Optimization
All 210
  1. Transformers are Universal In-context Learners
  2. Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation
  3. Data Debugging is NP-hard for Classifiers Trained with SGD
  4. Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation
  5. Autoencoders in Function Space
  6. Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation
  7. PC2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
  8. Prompt Refinement or Fine-tuning? Best Practices for using LLMs in Computational Social Science Tasks
  9. StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
  10. Leveraging Knowledge Graph Embedding for Effective Conversational Recommendation
  11. MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models
  12. Sparse Linear Regression when Noises and Covariates are Heavy-Tailed and Contaminated by Outliers
  13. A Backbone for Long-Horizon Robot Task Understanding
  14. UnifiedNN: Efficient Neural Network Training on the Cloud
  15. FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only
  16. A Robotics-Inspired Scanpath Model Reveals the Importance of Uncertainty and Semantic Object Cues for Gaze Guidance in Dynamic Scenes
  17. Point Prediction for Streaming Data
  18. Synergistic pathways of modulation enable robust task packing within neural dynamics
  19. TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplification
  20. Reconsidering Degeneration of Token Embeddings with Definitions for Encoder-based Pre-trained Language Models
  21. Decentralized Smoothing ADMM for Quantile Regression with Non-Convex Sparse Penalties
  22. A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessment
  23. Assessing Robustness of Machine Learning Models using Covariate Perturbations
  24. Optimal Mixed Integer Linear Optimization Trained Multivariate Classification Trees
  25. Feature Clock: High-Dimensional Effects in Two-Dimensional Plots
  26. Underwater Object Detection Enhancement via Channel Stabilization
  27. 3DPX: Progressive 2D-to-3D Oral Image Reconstruction with Hybrid MLP-CNN Networks
  28. Deep Learning based Visually Rich Document Content Understanding: A Survey
  29. Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?
  30. Out-Of-Distribution Detection for Audio-visual Generalized Zero-Shot Learning: A General Framework
  31. A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognition
  32. Certified Robust Invariant Polytope Training in Neural Controlled ODEs
  33. A General Framework to Boost 3D GS Initialization for Text-to-3D Generation by Lexical Richness
  34. Designing the virtual CAT: A digital tool for algorithmic thinking assessment in compulsory education
  35. Detection and Characterization of Coordinated Online Behavior: A Survey
  36. TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Dataflow and Analytical Modelling
  37. Metareasoning in uncertain environments: a meta-BAMDP framework
  38. Automated Classification of Dry Bean Varieties Using XGBoost and SVM Models
  39. Tailoring Graph Neural Network-based Flow-guided Localization to Individual Bloodstreams and Activities
  40. HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling
  41. Rubric-based Learner Modelling via Noisy Gates Bayesian Networks for Computational Thinking Skills Assessment
  42. S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch
  43. ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification
  44. High-Throughput Phenotyping of Clinical Text Using Large Language Models
  45. Certifiably Robust Encoding Schemes
  46. A Weakly Supervised and Globally Explainable Learning Framework for Brain Tumor Segmentation
  47. VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
  48. Nested Music Transformer: Sequentially Decoding Compound Tokens in Symbolic Music and Audio Generation
  49. Sustainable Diffusion-based Incentive Mechanism for Generative AI-driven Digital Twins in Industrial Cyber-Physical Systems
  50. Misinforming LLMs: vulnerabilities, challenges and opportunities
  51. Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification
  52. Domain Adaptation-Enhanced Searchlight: Enabling classification of brain states from visual perception to mental imagery
  53. PreMix: Label-Efficient Multiple Instance Learning via Non-Contrastive Pre-training and Feature Mixing
  54. Robust Curve Detection in Volumetric Medical Imaging via Attraction Field
  55. TCR-GPT: Integrating Autoregressive Model and Reinforcement Learning for T-Cell Receptor Repertoires Generation
  56. DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs
  57. Enhanced Prediction of Ventilator-Associated Pneumonia in Patients with Traumatic Brain Injury Using Advanced Machine Learning Techniques
  58. Machine learning topological energy braiding of non-Bloch bands
  59. Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
  60. PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network
  61. IG-SLAM: Instant Gaussian SLAM
  62. CFBench: A Comprehensive Constraints-Following Benchmark for LLMs
  63. Being Accountable is Smart: Navigating the Technical and Regulatory Landscape of AI-based Services for Power Grid
  64. An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding
  65. Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
  66. IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection
  67. Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration
  68. Six Dragons Fly Again: Reviving 15th-Century Korean Court Music with Transformers and Novel Encoding
  69. Revisiting Bi-Encoder Neural Search: An Encoding--Searching Separation Perspective
  70. General-purpose Dataflow Model with Neuromorphic Primitives
  71. Prototypical Partial Optimal Transport for Universal Domain Adaptation
  72. Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs
  73. Effect of Fog Particle Size Distribution on 3D Object Detection Under Adverse Weather Conditions
  74. FCDFusion: a Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs
  75. PhysMamba: State Space Duality Model for Remote Physiological Measurement
  76. Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
  77. The EAP-AIAS: Adapting the AI Assessment Scale for English for Academic Purposes
  78. Amodal Segmentation for Laparoscopic Surgery Video Instruments
  79. Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction
  80. Universality of Kernel Random Matrices and Kernel Regression in the Quadratic Regime
  81. From Stem to Stern: Contestability Along AI Value Chains
  82. The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines
  83. QUDSELECT: Selective Decoding for Questions Under Discussion Parsing
  84. Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model
  85. UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents
  86. MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection
  87. Structure from Motion-based Motion Estimation and 3D Reconstruction of Unknown Shaped Space Debris
  88. POA: Pre-training Once for Models of All Sizes
  89. PINNs for Medical Image Analysis: A Survey
  90. Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments
  91. Distilling interpretable causal trees from causal forests
  92. A Family of Distributions of Random Subsets for Controlling Positive and Negative Dependence
  93. GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs
  94. IBB Traffic Graph Data: Benchmarking and Road Traffic Prediction Model
  95. Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs
  96. Enhancing Financial Market Predictions: Causality-Driven Feature Selection
  97. Adaptive Two-Stage Cloud Resource Scaling via Hierarchical Multi-Indicator Forecasting and Bayesian Decision-Making
  98. IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing
  99. ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models
  100. Fairness in Large Language Models in Three Hours
  101. A SAT-based approach to rigorous verification of Bayesian networks
  102. Reconstructing Richtmyer-Meshkov instabilities from noisy radiographs using low dimensional features and attention-based neural networks
  103. Cross-domain Named Entity Recognition via Graph Matching
  104. META-ANOVA: Screening interactions for interpretable machine learning
  105. Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach
  106. Extracting Object Heights From LiDAR & Aerial Imagery
  107. Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts
  108. Integrating ESG and AI: A Comprehensive Responsible AI Assessment Framework
  109. MIS-ME: A Multi-modal Framework for Soil Moisture Estimation
  110. PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting