mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 14 Aug 2024

198 papers

  1. The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligenceLLM agents and tool use → Agent threats, guardrails and governance
  2. SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red TeamingLLM safety and security → Prompt injection and agent security
  3. TurboEdit: Instant text-based image editingDiffusion models → Image generation, text-to-image and editing
  4. Cropper: Vision-Language Model for Image Cropping through In-Context LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  5. Out-of-Distribution Learning with Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based PoliciesDiffusion models → Image generation, text-to-image and editing
  7. Re-Thinking Process Mining in the AI-Based Agents EraLLM reasoning → Reasoning for agents, planning and code +1
  8. Knowledge Distillation with Refined LogitsKnowledge distillation → General knowledge distillation methods
  9. The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  10. Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability DistributionsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  11. Off-Policy Reinforcement Learning with High Dimensional RewardDeep reinforcement learning methods → RL theory and sample complexity
  12. Drug Discovery SMILES-to-Pharmacokinetics Diffusion Models with Deep Molecular UnderstandingDiffusion models → Flow matching, time series and science
  13. WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge GraphsRetrieval-augmented generation → Agentic RAG, agents and memory
  14. FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual TeacherLLM safety and security → Federated unlearning and poisoning +1
  15. A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooningDeep reinforcement learning methods → RL for autonomous driving and traffic
  16. PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform GenerationDiffusion models → Audio, speech and music
  17. MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical ContextsLLM reasoning → Multimodal reasoning +1
  18. New Curriculum, New Chance -- Retrieval Augmented Generation for Lesson Planning in Ugandan Secondary Schools. Prototype Quality EvaluationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  19. DifuzCam: Replacing Camera Lens with a Mask and a Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  20. DIffSteISR: Harnessing Diffusion Prior for Superior Real-world Stereo Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  21. DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion ConsistencyDiffusion models → Video generation
  22. One Step Diffusion-based Super-Resolution with Time-Aware DistillationDiffusion models → Inverse problems and image restoration
  23. Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion ModelsDiffusion models → Audio, speech and music
  24. Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  25. Costal Cartilage Segmentation with Topology Guided Deformable Mamba: Method and BenchmarkState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  26. BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt LearningLLM safety and security → Backdoor and data poisoning attacks
  27. Real-world validation of safe reinforcement learning, model predictive control and decision tree-based home energy management systemsDeep reinforcement learning methods → RL for energy, networks and operations
  28. MagicFace: Training-free Universal-Style Human Image Customized SynthesisDiffusion models → Image generation, text-to-image and editing
  29. Exploring Retrieval Augmented Generation in ArabicRetrieval-augmented generation → RAG pipeline design and evaluation
  30. Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  31. MultiSurf-GPT: Facilitating Context-Aware Reasoning with Large-Scale Language Models for Multimodal Surface SensingLLM reasoning → Spatial and embodied reasoning
  32. Evaluating LLM-based Personal Information Extraction and CountermeasuresLLM safety and security → Prompt injection and agent security
  33. GRIF-DM: Generation of Rich Impression Fonts using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  34. ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry AreaMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  35. q-exponential family for policy optimizationDeep reinforcement learning methods → RL theory and sample complexity
  36. Cognitive Networks and Performance Drive fMRI-Based State Classification Using DNN Models
  37. Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy
  38. An Effective Information Theoretic Framework for Channel Pruning
  39. Novel Methods for Analyzing Cellular Interactions in Deep Learning-Based Image Cytometry: Spatial Interaction Potential and Co-Localization Index
  40. Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reduction
  41. Fast Training Dataset Attribution via In-Context Learning
  42. Relational Graph Convolutional Networks Do Not Learn Sound Rules
  43. Optical Music Recognition in Manuscripts from the Ricordi Archive
  44. Supervised and Unsupervised Alignments for Spoofing Behavioral Biometrics
  45. Cyclic Supports in Recursive Bipolar Argumentation Frameworks: Semantics and LP Mapping
  46. A Survey on Blockchain-based Supply Chain Finance with Progress and Future directions
  47. CodeMirage: Hallucinations in Code Generated by Large Language Models
  48. CON-FOLD -- Explainable Machine Learning with Confidence
  49. Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
  50. SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition
  51. Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal
  52. A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites
  53. Enhancing Equitable Access to AI in Housing and Homelessness System of Care through Federated Learning
  54. SustainDC: Benchmarking for Sustainable Data Center Control
  55. ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model
  56. Learning-Augmented Competitive Algorithms for Spatiotemporal Online Allocation with Deadline Constraints
  57. Algebraic Representations for Faster Predictions in Convolutional Neural Networks
  58. Differentiating Policies for Non-Myopic Bayesian Optimization
  59. Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
  60. Ranking and Combining Latent Structured Predictive Scores without Labeled Data
  61. An Efficient and Explanatory Image and Text Clustering System with Multimodal Autoencoder Architecture
  62. Perspectives: Comparison of Deep Learning Segmentation Models on Biophysical and Biomedical Data
  63. NeuroPapyri: A Deep Attention Embedding Network for Handwritten Papyri Retrieval
  64. Knowledge-based Neural Ordinary Differential Equations for Cosserat Rod-based Soft Robots
  65. MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis
  66. On learning capacities of Sugeno integrals with systems of fuzzy relational equations
  67. Heterogeneous Treatment Effect Estimation under Noncompliance in the Illinois Workplace Wellness Study with Bayesian Tree Ensembles
  68. Data Clustering and Visualization with Recursive Goemans-Williamson MaxCut Algorithm
  69. How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
  70. Enhancing Model Interpretability with Local Attribution over Global Exploration
  71. Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
  72. Development of a graph neural network surrogate for travel demand modelling
  73. "Normalized Stress" is Not Normalized: How to Interpret Stress Correctly
  74. Operator Feature Neural Network for Symbolic Regression
  75. Impact of Inaccurate Contamination Ratio on Robust Unsupervised Anomaly Detection
  76. Quantifying over Optimum Answer Sets
  77. End-to-end Semantic-centric Video-based Multimodal Affective Computing
  78. Detecting Near-Duplicate Face Images
  79. RSD-DOG : A New Image Descriptor based on Second Order Derivatives
  80. A Spitting Image: Modular Superpixel Tokenization in Vision Transformers
  81. Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques
  82. G2V2former: Graph Guided Video Vision Transformer for Face Anti-Spoofing
  83. Deep Learning: a Heuristic Three-stage Mechanism for Grid Searches to Optimize the Future Risk Prediction of Breast Cancer Metastasis Using EHR-based Clinical Data
  84. Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
  85. Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models
  86. Interpretable Graph Neural Networks for Heterogeneous Tabular Data
  87. Graph Triple Attention Network: A Decoupled Perspective
  88. See It All: Contextualized Late Aggregation for 3D Dense Captioning
  89. Adaptive Behavioral AI: Reinforcement Learning to Enhance Pharmacy Services
  90. SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning
  91. Boosting Unconstrained Face Recognition with Targeted Style Adversary
  92. Synaptic Theory of Chunking in Working Memory
  93. Towards Fair and Rigorous Evaluations: Hyperparameter Optimization for Top-N Recommendation Task with Implicit Feedback
  94. Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings
  95. Battery GraphNets : Relational Learning for Lithium-ion Batteries(LiBs) Life Estimation
  96. Latent Anomaly Detection Through Density Matrices
  97. Rethinking the Key Factors for the Generalization of Remote Sensing Stereo Matching Networks
  98. Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
  99. Disentangle and denoise: Tackling context misalignment for video moment retrieval
  100. Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations
All 198
  1. Progressive Radiance Distillation for Inverse Rendering with Gaussian Splatting
  2. Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
  3. Transformers and Large Language Models for Efficient Intrusion Detection Systems: A Comprehensive Survey
  4. Theoretical and Practical Progress in Hyperspectral Pixel Unmixing with Large Spectral Libraries from a Sparse Perspective
  5. TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
  6. MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
  7. A General Framework on Conditions for Constraint-based Causal Learning
  8. Multi-task Heterogeneous Graph Learning on Electronic Health Records
  9. Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms
  10. PolyCL: Contrastive Learning for Polymer Representation Learning via Explicit and Implicit Augmentations
  11. chiSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
  12. Planning with OWL-DL Ontologies (Extended Version)
  13. 3D Gaussian Editing with A Single Image
  14. Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation
  15. Information-Theoretic Measures on Lattices for High-Order Interactions
  16. Improved 3D Whole Heart Geometry from Sparse CMR Slices
  17. Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departments
  18. Towards Real-time Video Compressive Sensing on Mobile Devices
  19. Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation
  20. Learning-based Models for Vulnerability Detection: An Extensive Study
  21. Fast Inference for Probabilistic Answer Set Programs via the Residual Program
  22. Optimising MFCC parameters for the automatic detection of respiratory diseases
  23. Optimising Dynamic Traffic Distribution for Urban Networks with Answer Set Programming
  24. Whitening Consistently Improves Self-Supervised Learning
  25. CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture
  26. Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
  27. Dominating Set Reconfiguration with Answer Set Programming
  28. Decoder ensembling for learned latent geometries
  29. Large Language Models Know What Makes Exemplary Contexts
  30. Faster Stochastic Optimization with Arbitrary Delays via Asynchronous Mini-Batching
  31. Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
  32. Wasserstein Gradient Flows of MMD Functionals with Distance Kernel and Cauchy Problems on Quantile Functions
  33. QirK: Question Answering via Intermediate Representation on Knowledge Graphs
  34. Attention-Guided Perturbation Network for Industrial Anomaly Detection
  35. OMR: Occlusion-Aware Memory-Based Refinement for Video Lane Detection
  36. GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution
  37. Training Overhead Ratio: A Practical Reliability Metric for Large Language Model Training Systems
  38. Adaptive Basis Function Selection for Computationally Efficient Predictions
  39. A Study on Bias Detection and Classification in Natural Language Processing
  40. Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification
  41. Large Language Models Prompting With Episodic Memory
  42. Problem Solving Through Human-AI Preference-Based Cooperation
  43. From Brazilian Portuguese to European Portuguese
  44. Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection
  45. Fact or Fiction? Improving Fact Verification with Knowledge Graphs through Simplified Subgraph Retrievals
  46. CMU's IWSLT 2024 Simultaneous Speech Translation System
  47. LiveFC: A System for Live Fact-Checking of Audio Streams
  48. Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach
  49. Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
  50. UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection
  51. LLMI3D: MLLM-based 3D Perception from a Single 2D Image
  52. Unsupervised Stereo Matching Network For VHR Remote Sensing Images Based On Error Prediction
  53. The Restaurant Meal Delivery Problem with Ghost Kitchens
  54. Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space
  55. Aquila2 Technical Report
  56. Efficient Edge AI: Deploying Convolutional Neural Networks on FPGA with the Gemmini Accelerator
  57. A Quantum-Inspired Analysis of Human Disambiguation Processes
  58. DataVisT5: A Pre-trained Language Model for Jointly Understanding Text and Data Visualization
  59. Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space
  60. Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
  61. Segment Using Just One Example
  62. DPSNN: Spiking Neural Network for Low-Latency Streaming Speech Enhancement
  63. Fading memory and the convolution theorem
  64. Posterior Covariance Structures in Gaussian Processes
  65. Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics
  66. An Adaptive Importance Sampling for Locally Stable Point Processes
  67. The Complexity of Manipulation of k-Coalitional Games on Graphs
  68. Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation
  69. BadMerging: Backdoor Attacks Against Model Merging
  70. Only One Relation Possible? Modeling the Ambiguity in Event Temporal Relation Extraction
  71. Automated Retinal Image Analysis and Medical Report Generation through Deep Learning
  72. RTAT: A Robust Two-stage Association Tracker for Multi-Object Tracking
  73. Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation
  74. Robust Semi-supervised Multimodal Medical Image Segmentation via Cross Modality Collaboration
  75. Towards Few-shot Self-explaining Graph Neural Networks
  76. KIND: Knowledge Integration and Diversion for Training Decomposable Models
  77. RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation
  78. An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems
  79. On-the-fly Synthesis for LTL over Finite Traces: An Efficient Approach that Counts
  80. A systematic dataset generation technique applied to data-driven automotive aerodynamics
  81. Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis
  82. Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
  83. Learning Decisions Offline from Censored Observations with ε-insensitive Operational Costs
  84. Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion
  85. LiPCoT: Linear Predictive Coding based Tokenizer for Self-supervised Learning of Time Series Data via Language Models
  86. Abstract Operations Research Modeling Using Natural Language Inputs
  87. Image-Based Leopard Seal Recognition: Approaches and Challenges in Current Automated Systems
  88. Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods
  89. Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling
  90. Lesion-aware network for diabetic retinopathy diagnosis
  91. Ensemble architecture in polyp segmentation
  92. Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
  93. All-around Neural Collapse for Imbalanced Classification
  94. Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach
  95. BiLSTM and Attention-Based Modulation Classification of Realistic Wireless Signals
  96. Sign language recognition based on deep learning and low-cost handcrafted descriptors
  97. Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks
  98. Enhancing Autonomous Vehicle Perception in Adverse Weather through Image Augmentation during Semantic Segmentation Training