mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 12 Jul 2024

251 papers

  1. A Survey on Symbolic Knowledge Distillation of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  2. Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language ModelsLLM reasoning → Mathematical reasoning
  3. Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM InferenceEfficient LLM inference and serving → Speculative decoding
  4. Investigating the Interplay of Prioritized Replay and GeneralizationDeep reinforcement learning methods → Deep RL algorithms and representations
  5. Mixed-View Panorama Synthesis using Geospatially Guided DiffusionDiffusion models → 3D, point cloud and scene generation
  6. Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  7. Hamilton-Jacobi Reachability in Reinforcement Learning: A SurveyDeep reinforcement learning methods → Safe and constrained RL
  8. Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-ExpertsMixture-of-experts → MoE large language models
  9. ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe PromptsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  10. A Benchmark Environment for Offline Reinforcement Learning in Racing GamesOffline RL and imitation learning from data → Offline RL algorithms
  11. PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric AgentsRetrieval-augmented generation → RAG pipeline design and evaluation +1
  12. PID: Physics-Informed Diffusion Model for Infrared Image GenerationDiffusion models → Image generation, text-to-image and editing
  13. Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  14. Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual EnvironmentsDeep reinforcement learning methods → RL training of language and agent models
  15. Context Embeddings for Efficient Answer Generation in RAGRetrieval-augmented generation → Generation and context integration +1
  16. Constrained Intrinsic Motivation for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  17. Pronunciation Assessment with Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. Salt & Pepper Heatmaps: Diffusion-informed Landmark Detection StrategyDiffusion models → Medical imaging and segmentation
  19. ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMsLLM safety and security → Prompt injection and agent security
  20. Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model TutorsLLM reasoning → Mathematical reasoning
  21. BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge DistillationKnowledge distillation → Distillation for spiking neural networks
  22. Open Vocabulary Multi-Label Video ClassificationMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  23. New Desiderata for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  24. Refusing Safe Prompts for Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  25. Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  26. Textual Query-Driven Mask Transformer for Domain Generalized SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  27. Aligning Diffusion Behaviors with Q-functions for Efficient Continuous ControlDiffusion models → Diffusion and flow policies for robotics +2
  28. 3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health DetectionKnowledge distillation → Multimodal distillation
  29. CompAct: Compressing Retrieved Documents Actively for Question AnsweringRetrieval-augmented generation → Generation and context integration
  30. TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion ModelsDiffusion models → Video generation
  31. Self-interpreting Adversarial ImagesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  32. SlideGCD: Slide-based Graph Collaborative Training with Knowledge Distillation for Whole Slide Image ClassificationKnowledge distillation → Distillation for medical imaging
  33. LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  34. Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  35. Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text ClassificationLLM reasoning → Knowledge- and tool-augmented reasoning
  36. Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy LossLLM safety and security → Backdoor and data poisoning attacks
  37. Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive TrainingDiffusion models → Diffusion foundations and sampling
  38. Bora: Biomedical Generalist Video Generation ModelDiffusion models → Medical imaging and segmentation
  39. LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion ModelsDiffusion models → Inverse problems and image restoration
  40. Self-Evolving GPT: A Lifelong Autonomous Experiential LearnerSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  41. Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic EnvironmentDeep reinforcement learning methods → RL for autonomous driving and traffic
  42. PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral OptimizationOffline RL and imitation learning from data → Imitation learning methods +1
  43. AirSketch: Generative Motion to SketchDiffusion models → Image generation, text-to-image and editing
  44. Real Face Video Animation Platform
  45. Photogrammetry for Digital Twinning Industry 4.0 (I4) Systems
  46. Unexplainability of Artificial Intelligence Judgments and Functional Implementation in Kant's Perspective
  47. Predicting Winning Captions for Weekly New Yorker Comics
  48. Neural-based Video Compression on Solar Dynamics Observatory Images
  49. The Honorific Effect: Exploring the Impact of Japanese Linguistic Formalities on AI-Generated Physics Explanations
  50. GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering
  51. Clustering Time-Evolving Networks Using the Spatio-Temporal Graph Laplacian
  52. MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants
  53. MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs
  54. Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search
  55. Combining Federated Learning and Control: A Survey
  56. Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay
  57. ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers
  58. MSEval: A Dataset for Material Selection in Conceptual Design to Evaluate Algorithmic Models
  59. CLOVER: Context-aware Long-term Object Viewpoint- and Environment- Invariant Representation Learning
  60. Deep-TEMPEST: Using Deep Learning to Eavesdrop on HDMI from its Unintended Electromagnetic Emanations
  61. GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
  62. Diagnosing and Re-learning for Balanced Multimodal Learning
  63. What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages
  64. RIO-CPD: A Riemannian Geometric Method for Correlation-aware Online Change Point Detection
  65. Uplifting Range-View-based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion
  66. Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images
  67. A Mathematical Framework and a Suite of Learning Techniques for Neural-Symbolic Systems
  68. EVOLVE: Predicting User Evolution and Network Dynamics in Social Media Using Fine-Tuned GPT-like Model
  69. Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
  70. Large Language Models for Integrating Social Determinant of Health Data: A Case Study on Heart Failure 30-Day Readmission Prediction
  71. Fast and Robust Phase Retrieval via Deep Expectation-Consistent Approximation
  72. SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images
  73. Accelerating the inference of string generation-based chemical reaction models for industrial applications
  74. Physics-Informed Learning of Characteristic Trajectories for Smoke Reconstruction
  75. Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use
  76. BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
  77. Bridging the Gap Between Information Seeking and Product Search Systems: Q&A Recommendation for E-commerce
  78. How Chinese are Chinese Language Models? The Puzzling Lack of Language Policy in China's LLMs
  79. 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
  80. Seq-to-Final: A Benchmark for Tuning from Sequential Distributions to a Final Time Point
  81. Granger Causality in Extremes
  82. Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators
  83. The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges
  84. Real-time gravitational-wave inference for binary neutron stars using machine learning
  85. A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks
  86. Don't Fear Peculiar Activation Functions: EUAF and Beyond
  87. Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection
  88. FlashNorm: Fast Normalization for Transformers
  89. Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting
  90. StyleSplat: 3D Object Style Transfer with Gaussian Splatting
  91. Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
  92. FairyLandAI: Personalized Fairy Tales utilizing ChatGPT and DALLE-3
  93. Weight Block Sparsity: Training, Compilation, and AI Engine Accelerators
  94. Human-inspired Episodic Memory for Infinite Context LLMs
  95. The μG Language for Programming Graph Neural Networks
  96. Let Me DeCode You: Decoder Conditioning with Tabular Data
  97. MUSCLE: A Model Update Strategy for Compatible LLM Evolution
  98. Foundation Models for the Electric Power Grid
  99. Rethinking temporal self-similarity for repetitive action counting
  100. Open (Clinical) LLMs are Sensitive to Instruction Phrasings
All 251
  1. Flow-Based Generative Emulation of Grids of Stellar Evolutionary Models
  2. TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models
  3. Mitigating Entity-Level Hallucination in Large Language Models
  4. SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
  5. Deep Bag-of-Words Model: An Efficient and Interpretable Relevance Architecture for Chinese E-Commerce
  6. Open-Canopy: Towards Very High Resolution Forest Monitoring
  7. GAVEL: Generating Games Via Evolution and Language Models
  8. Meta-Analysis with Untrusted Data
  9. Radiance Fields from Photons
  10. The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
  11. FANet: Feature Amplification Network for Semantic Segmentation in Cluttered Background
  12. Graph Neural Network Causal Explanation via Neural Causal Models
  13. HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context
  14. Towards Personalised Patient Risk Prediction Using Temporal Hospital Data Trajectories
  15. Segmentation Dataset for Reinforced Concrete Construction
  16. Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
  17. Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
  18. Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text
  19. Novel clustered federated learning based on local loss
  20. A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
  21. Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees
  22. FastImpute: A Baseline for Open-source, Reference-Free Genotype Imputation Methods -- A Case Study in PRS313
  23. Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems
  24. Predictable and Performant Reactive Synthesis Modulo Theories via Functional Synthesis
  25. Pre-training Point Cloud Compact Model with Partial-aware Reconstruction
  26. CFaults: Model-Based Diagnosis for Fault Localization in C Programs with Multiple Test Cases
  27. Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification
  28. Sina at FigNews 2024: Multilingual Datasets Annotated with Bias and Propaganda
  29. Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
  30. Scalability of Bayesian Network Structure Elicitation with Large Language Models: a Novel Methodology and Comparative Analysis
  31. ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
  32. Transformer Layers as Painters
  33. Learning Distances from Data with Normalizing Flows and Score Matching
  34. SS-SfP:Neural Inverse Rendering for Self Supervised Shape from (Mixed) Polarization
  35. WSESeg: Introducing a Dataset for the Segmentation of Winter Sports Equipment with a Baseline for Interactive Segmentation
  36. MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Results
  37. DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection
  38. Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learning
  39. H2O-Danube3 Technical Report
  40. Unifying Sequences, Structures, and Descriptions for Any-to-Any Protein Generation with the Large Multimodal Model HelixProtX
  41. iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
  42. Region Attention Transformer for Medical Image Restoration
  43. Deep Adversarial Defense Against Multilevel-Lp Attacks
  44. FedsLLM: Federated Split Learning for Large Language Models over Communication Networks
  45. Graph Neural Networks with Model-based Reinforcement Learning for Multi-agent Systems
  46. Semantic UV mapping to improve texture inpainting for indoor scenes
  47. The Sociolinguistic Foundations of Language Modeling
  48. FedVAE: Trajectory privacy preserving based on Federated Variational AutoEncoder
  49. Modelling the Human Intuition to Complete the Missing Information in Images for Convolutional Neural Networks
  50. Surgical Text-to-Image Generation
  51. Evaluating AI Evaluation: Perils and Prospects
  52. A Fair Ranking and New Model for Panoptic Scene Graph Generation
  53. HUP-3D: A 3D multi-view synthetic dataset for assisted-egocentric hand-ultrasound pose estimation
  54. Generating SROI^- Ontologies via Knowledge Graph Query Embedding Learning
  55. A Chatbot for Asylum-Seeking Migrants in Europe
  56. From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation
  57. Segmenting Medical Images with Limited Data
  58. Enhancing Depressive Post Detection in Bangla: A Comparative Study of TF-IDF, BERT and FastText Embeddings
  59. Variational Inference via Smoothed Particle Hydrodynamics
  60. Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers
  61. Exploring the Effectiveness of Methods for Persona Extraction
  62. DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model Training
  63. Conformal Inductive Graph Neural Networks
  64. Machine Apophenia: The Kaleidoscopic Generation of Architectural Images
  65. SE(3)-bi-equivariant Transformers for Point Cloud Assembly
  66. Robust Yet Efficient Conformal Prediction Sets
  67. Exploring State Space and Reasoning by Elimination in Tsetlin Machines
  68. Weakly-supervised Autism Severity Assessment in Long Videos
  69. Movie Recommendation with Poster Attention via Multi-modal Transformer Feature Fusion
  70. The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs
  71. Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off
  72. Accuracy is Not All You Need
  73. A Look Into News Avoidance Through AWRS: An Avoidance-Aware Recommender System
  74. Robustness of Explainable Artificial Intelligence in Industrial Process Modelling
  75. Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network
  76. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
  77. URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
  78. Layer-Wise Relevance Propagation with Conservation Property for ResNet
  79. Inference Optimization of Foundation Models on AI Accelerators
  80. Enhancing Training Efficiency Using Packing with Flash Attention
  81. UserBoost: Generating User-specific Synthetic Data for Faster Enrolment into Behavioural Biometric Systems
  82. DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents
  83. Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context
  84. STD-PLM: Understanding Both Spatial and Temporal Properties of Spatial-Temporal Data with PLM
  85. Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer
  86. On Exact Bit-level Reversible Transformers Without Changing Architectures
  87. FD-SOS: Vision-Language Open-Set Detectors for Bone Fenestration and Dehiscence Detection from Intraoral Images
  88. On the Role of Discrete Tokenization in Visual Representation Learning
  89. Multi-Modal Dataset Creation for Federated Learning with DICOM Structured Reports
  90. Spectral Self-supervised Feature Selection
  91. Domain-adaptive Video Deblurring via Test-time Blurring
  92. PersonificationNet: Making customized subject act like a person
  93. Advanced Graph Clustering Methods: A Comprehensive and In-Depth Analysis
  94. From MIDI to Rich Tablatures: an Automatic Generative System incorporating Lead Guitarists' Fingering and Stylistic choices
  95. DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects
  96. KUNPENG: An Embodied Large Model for Intelligent Maritime
  97. Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation
  98. Time-Frequency Analysis of Variable-Length WiFi CSI Signals for Person Re-Identification
  99. Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach
  100. GPC: Generative and General Pathology Image Classifier
  101. DRM Revisited: A Complete Error Analysis
  102. CAMP: Continuous and Adaptive Learning Model in Pathology
  103. Enhancing Emotion Recognition in Incomplete Data: A Novel Cross-Modal Alignment, Reconstruction, and Refinement Framework
  104. HPC: Hierarchical Progressive Coding Framework for Volumetric Video
  105. SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
  106. Heterogeneous Subgraph Network with Prompt Learning for Interpretable Depression Detection on Social Media
  107. AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Security
  108. Static Analysis of Logic Programs via Boolean Networks
  109. Procedural Content Generation via Generative Artificial Intelligence
  110. One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning
  111. Benchmarking Language Model Creativity: A Case Study on Code Generation
  112. Introducing VaDA: Novel Image Segmentation Model for Maritime Object Segmentation Using New Dataset
  113. Enhancing Few-Shot Stock Trend Prediction with Large Language Models
  114. Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
  115. Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation
  116. Task-driven single-image super-resolution reconstruction of document scans
  117. Emotion Talk: Emotional Support via Audio Messages for Psychological Assistance
  118. Optimization of DNN-based speaker verification model through efficient quantization technique
  119. Dynamic neural network with memristive CIM and CAM for 2D and 3D vision
  120. Robustness of Large Language Models to Perturbations in Text
  121. Parameter inference from a non-stationary unknown process
  122. Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
  123. Towards Chapter-to-Chapter Context-Aware Literary Translation via Large Language Models
  124. Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier Features
  125. Topology-enhanced machine learning model (Top-ML) for anticancer peptide prediction
  126. Integrating White and Black Box Techniques for Interpretable Machine Learning
  127. Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness
  128. Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
  129. Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Models
  130. Lite-SAM Is Actually What You Need for Segment Everything
  131. Local Optima in Diversity Optimization: Non-trivial Offspring Population is Essential
  132. Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT
  133. Attribution Methods in Asset Pricing: Do They Account for Risk?
  134. Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection
  135. Exploring Richer and More Accurate Information via Frequency Selection for Image Restoration
  136. One-Shot Pose-Driving Face Animation Platform
  137. Symmetry Awareness Encoded Deep Learning Framework for Brain Imaging Analysis
  138. Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
  139. A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model
  140. Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
  141. Compositional Structures in Neural Embedding and Interaction Decompositions
  142. Machine Learning in High Volume Media Manufacturing
  143. Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection
  144. Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?
  145. Exploring Knowledge Transfer in Evolutionary Many-task Optimization: A Complex Network Perspective
  146. Transforming Movie Recommendations with Advanced Machine Learning: A Study of NMF, SVD,and K-Means Clustering
  147. KGpose: Keypoint-Graph Driven End-to-End Multi-Object 6D Pose Estimation via Point-Wise Pose Voting
  148. Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval
  149. TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing
  150. Application of Artificial Intelligence in Supporting Healthcare Professionals and Caregivers in Treatment of Autistic Children
  151. IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents