mlsanityData to 7 Oct 2026

Papers

New on arXiv

Tue 13 Aug 2024

219 papers

  1. PEARL: Parallel Speculative Decoding with Adaptive Draft LengthEfficient LLM inference and serving → Speculative decoding
  2. What should I wear to a party in a Greek taverna? Evaluation for Conversational Agents in the Fashion DomainLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. Can Large Language Models Reason? A Characterization via 3-SATLLM reasoning → Reasoning benchmarks and evaluation
  4. Agent Q: Advanced Reasoning and Learning for Autonomous AI AgentsLLM reasoning → Reasoning for agents, planning and code +1
  5. SeLoRA: Self-Expanding Low-Rank Adaptation of Latent Diffusion Model for Medical Image SynthesisDiffusion models → Image generation, text-to-image and editing
  6. Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse WorkplacesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  7. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  8. Imagen 3Diffusion models → Image generation, text-to-image and editing
  9. Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  10. DyG-Mamba: Continuous State Space Modeling on Dynamic GraphsState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  11. Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge PerspectivesLLM reasoning → Prompting and chain-of-thought reasoning
  12. Prompt-to-Slate: Diffusion Models for Prompt-Conditioned Slate GenerationDiffusion models → Diffusion recommenders
  13. Causal Agent based on Large Language ModelLLM agents and tool use → Medical and scientific domain agents
  14. Membership Inference Attack Against Masked Image ModelingLLM safety and security → Membership inference attacks
  15. Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
  16. Token Compensator: Altering Inference Cost of Vision Transformer without Re-TuningEfficient LLM inference and serving → Token pruning and merging for ViTs
  17. Layerwise Recurrent Router for Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  18. Do Vision-Language Foundational models show Robust Visual Perception?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with DiffusionDiffusion models → Image generation, text-to-image and editing
  20. Response Wide Shut: Surprising Observations in Basic Vision Language Model CapabilitiesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  21. DiffSG: A Generative Solver for Network Optimization with Diffusion ModelDiffusion models → Diffusion foundations and sampling
  22. DC3DO: Diffusion Classifier for 3D ObjectsDiffusion models → 3D, point cloud and scene generation
  23. TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series GenerationDiffusion models → Flow matching, time series and science
  24. Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  25. IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  26. Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMsLLM reasoning → Reasoning for agents, planning and code +1
  27. CROME: Cross-Modal Adapters for Efficient Multimodal LLMMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  28. Prompt Tuning as User Inherent Profile Inference MachineLLM reasoning → LLM reasoning for recommendation
  29. SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language ModelRetrieval-augmented generation → Agentic RAG, agents and memory
  30. Social Debiasing for Fair Multi-modal LLMsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  31. AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out StrategiesMixture-of-experts → MoE large language models
  32. A Comparison of Imitation Learning Algorithms for Bimanual ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  33. Many-Worlds Inverse Rendering
  34. Meta-Learning for Federated Face Recognition in Imbalanced Data Regimes
  35. A Survey of Deep Learning for Group-level Emotion Recognition
  36. Automated Software Tool for Compressing Optical Images with Required Output Quality
  37. Uncertainty Quantification in Alzheimer's Disease Progression Modeling
  38. Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation
  39. MGH Radiology Llama: A Llama 3 70B Model for Radiology
  40. Contrastive Learning on Medical Intents for Sequential Prescription Recommendation
  41. NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild
  42. Why Do Experts Favor Solar and Wind as Renewable Energies Despite their Intermittency?
  43. An Adaptive Differential Privacy Method Based on Federated Learning
  44. Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning
  45. Introduction to Reinforcement Learning
  46. Beyond Mimicry to Contextual Guidance: Knowledge Distillation for Interactive AI
  47. A semantic embedding space based on large language models for modelling human beliefs
  48. Direction of Arrival Correction through Speech Quality Feedback
  49. Pan-cancer gene set discovery via scRNA-seq for optimal deep learning based downstream tasks
  50. Play Me Something Icy: Practical Challenges, Explainability and the Semantic Gap in Generative AI Music
  51. A Review of Pseudo-Labeling for Computer Vision
  52. Causal Effect Estimation using identifiable Variational AutoEncoder with Latent Confounders and Post-Treatment Variables
  53. Deep Index Policy for Multi-Resource Restless Matching Bandit and Its Application in Multi-Channel Scheduling
  54. Quantification of total uncertainty in the physics-informed reconstruction of CVSim-6 physiology
  55. Massive Dimensions Reduction and Hybridization with Meta-heuristics in Deep Learning
  56. Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning
  57. Joint Graph Rewiring and Feature Denoising via Spectral Resonance
  58. BERT's Conceptual Cartography: Mapping the Landscapes of Meaning
  59. A New Dataset, Notation Software, and Representation for Computational Schenkerian Analysis
  60. VulCatch: Enhancing Binary Vulnerability Detection through CodeT5 Decompilation and KAN Advanced Feature Extraction
  61. Unlocking Efficiency: Adaptive Masking for Gene Transformer Models
  62. BVI-UGC: A Video Quality Database for User-Generated Content Transcoding
  63. A POD-TANN approach for the multiscale modeling of materials and macroelement derivation in geomechanics
  64. Flexible 3D Lane Detection by Hierarchical Shape MatchingFlexible 3D Lane Detection by Hierarchical Shape Matching
  65. Integration of Genetic Algorithms and Deep Learning for the Generation and Bioactivity Prediction of Novel Tyrosine Kinase Inhibitors
  66. Self-folding Self-replication
  67. Alpha-Trimming: Locally Adaptive Tree Pruning for Random Forests
  68. Controlling the World by Sleight of Hand
  69. Language Models as Models of Language
  70. ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice
  71. Generative Photomontage
  72. Investigation of unsupervised and supervised hyperspectral anomaly detection
  73. A Theory-Based Explainable Deep Learning Architecture for Music Emotion
  74. Physics-informed graph neural networks for flow field estimation in carotid arteries
  75. Efficient Deep Model-Based Optoacoustic Image Reconstruction
  76. A Self-Supervised Paradigm for Data-Efficient Medical Foundation Model Pre-training: V-information Optimization Framework
  77. "You still have to study" -- On the Security of LLM generated code
  78. Model Based and Physics Informed Deep Learning Neural Network Structures
  79. Approaches for enhancing extrapolability in process-based and data-driven models in hydrology
  80. Fingerspelling within Sign Language Translation
  81. Model Counting in the Wild
  82. A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
  83. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
  84. The News Comment Gap and Algorithmic Agenda Setting in Online Forums
  85. PSM: Learning Probabilistic Embeddings for Multi-scale Zero-Shot Soundscape Mapping
  86. TableGuard -- Securing Structured & Unstructured Data
  87. KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
  88. PathInsight: Instruction Tuning of Multimodal Datasets and Models for Intelligence Assisted Diagnosis in Histopathology
  89. Efficient Human-Object-Interaction (EHOI) Detection via Interaction Label Coding and Conditional Decision
  90. Rethinking Disentanglement under Dependent Factors of Variation
  91. Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models
  92. Generative AI for automatic topic labelling
  93. Faster Private Minimum Spanning Trees
  94. Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds
  95. LLMs can Schedule
  96. SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis
  97. Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2
  98. IRS-Assisted Lossy Communications Under Correlated Rayleigh Fading: Outage Probability Analysis and Optimization
  99. Event-Stream Super Resolution using Sigma-Delta Neural Network
  100. Stabilizer bootstrapping: A recipe for efficient agnostic tomography and magic estimation
All 219
  1. Measuring User Understanding in Dialogue-based XAI Systems
  2. AuToMATo: An Out-Of-The-Box Persistence-Based Clustering Algorithm
  3. Neural Speech and Audio Coding: Modern AI Technology Meets Traditional Codecs
  4. Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation
  5. Towards Holistic Disease Risk Prediction using Small Language Models
  6. The advantages of context specific language models: the case of the Erasmian Language Model
  7. Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification
  8. Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas
  9. Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
  10. SceneGPT: A Language Model for 3D Scene Understanding
  11. Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge
  12. Multi-Agent Continuous Control with Generative Flow Networks
  13. Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancement
  14. VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders
  15. Heterogeneity: An Open Challenge for Federated On-board Machine Learning
  16. Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries
  17. Entendre, a Social Bot Detection Tool for Niche, Fringe, and Extreme Social Media
  18. EEPPR: Event-based Estimation of Periodic Phenomena Rate using Correlation in 3D
  19. Automatic Feature Recognition and Dimensional Attributes Extraction From CAD Models for Hybrid Additive-Subtractive Manufacturing
  20. BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
  21. PBIR-NIE: Glossy Object Capture under Non-Distant Lighting
  22. Decision-Focused Learning to Predict Action Costs for Planning
  23. Advancing Interactive Explainable AI via Belief Change Theory
  24. Leveraging Language Models for Emotion and Behavior Analysis in Education
  25. Generative AI Tools in Academic Research: Applications and Implications for Qualitative and Quantitative Research Methodologies
  26. A Comprehensive Survey on Synthetic Infrared Image synthesis
  27. Optimal Bound for PCA with Outliers using Higher-Degree Voronoi Diagrams
  28. LoRA2 : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models
  29. BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding
  30. AI Research is not Magic, it has to be Reproducible and Responsible: Challenges in the AI field from the Perspective of its PhD Students
  31. Dynamic and Compressive Adaptation of Transformers From Images to Videos
  32. GLGait: A Global-Local Temporal Receptive Field Network for Gait Recognition in the Wild
  33. FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving
  34. PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization
  35. PRESENT: Zero-Shot Text-to-Prosody Control
  36. Efficient Search for Customized Activation Functions with Gradient Descent
  37. Enhancing Multiview Synergy: Robust Learning by Exploiting the Wave Loss Function with Consensus and Complementarity Principles
  38. MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
  39. Structure-preserving Planar Simplification for Indoor Environments
  40. Oracle Bone Script Similiar Character Screening Approach Based on Simsiam Contrastive Learning and Supervised Learning
  41. Unmasking the Uniqueness: A Glimpse into Age-Invariant Face Recognition of Indigenous African Faces
  42. Deep Learning for Speaker Identification: Architectural Insights from AB-1 Corpus Analysis and Performance Evaluation
  43. Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection
  44. On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga
  45. Stunned by Sleeping Beauty: How Prince Probability updates his forecast upon their fateful encounter
  46. Visual Neural Decoding via Improved Visual-EEG Semantic Consistency
  47. FLAME: Empowering Frozen LLMs for Knowledge Graph Completion
  48. Enhancing Diabetic Retinopathy Diagnosis: A Lightweight CNN Architecture for Efficient Exudate Detection in Retinal Fundus Images
  49. ED4: Explicit Data-level Debiasing for Deepfake Detection
  50. Fast-and-Frugal Text-Graph Transformers are Effective Link Predictors
  51. Robust Deep Reinforcement Learning for Inverter-based Volt-Var Control in Partially Observable Distribution Networks
  52. Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions
  53. Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage
  54. Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN
  55. Sumotosima: A Framework and Dataset for Classifying and Summarizing Otoscopic Images
  56. Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies
  57. Evaluating Research Quality with Large Language Models: An Analysis of ChatGPT's Effectiveness with Different Settings and Inputs
  58. ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
  59. Class-aware and Augmentation-free Contrastive Learning from Label Proportion
  60. Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
  61. Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective
  62. Multilingual Models for Check-Worthy Social Media Posts Detection
  63. Speculations on Uncertainty and Humane Algorithms
  64. Exploring the anatomy of articulation rate in spontaneous English speech: relationships between utterance length effects and social factors
  65. Large language models can consistently generate high-quality content for election disinformation operations
  66. Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations
  67. Adaptive Data Quality Scoring Operations Framework using Drift-Aware Mechanism for Industrial Applications
  68. Multimodal Analysis of White Blood Cell Differentiation in Acute Myeloid Leukemia Patients using a β-Variational Autoencoder
  69. Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
  70. Towards Cross-Domain Single Blood Cell Image Classification via Large-Scale LoRA-based Segment Anything Model
  71. Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Sampling
  72. Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method
  73. MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation
  74. Sparse Variational Student-t Processes for Heavy-tailed Modeling
  75. SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
  76. Masked Image Modeling: A Survey
  77. How to Best Combine Demosaicing and Denoising?
  78. Coherence Awareness in Diffractive Neural Networks
  79. Case-based Explainability for Random Forest: Prototypes, Critics, Counter-factuals and Semi-factuals
  80. Latin Treebanks in Review: An Evaluation of Morphological Tagging Across Time
  81. Pragmatic inference of scalar implicature by LLMs
  82. RW-NSGCN: A Robust Approach to Structural Attacks via Negative Sampling
  83. Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
  84. Bi-directional Contextual Attention for 3D Dense Captioning
  85. Physics Informed Deep Learning for Strain Gradient Continuum Plasticity
  86. Hierarchical Structured Neural Network: Efficient Retrieval Scaling for Large Scale Recommendation
  87. Specialized Change Detection using Segment Anything
  88. Quantifying uncertainty in climate projections with conformal ensembles
  89. Attention Based Feature Fusion Network for Monkeypox Skin Lesion Detection
  90. COD: Learning Conditional Invariant Representation for Domain Adaptation Regression
  91. Unified-IoU: For High-Quality Object Detection
  92. IDRetracor: Towards Visual Forensics Against Malicious Face Swapping
  93. Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach
  94. A lightweight YOLOv5-FFM model for occlusion pedestrian detection
  95. EditScribe: Non-Visual Image Editing with Natural Language Verification Loops
  96. Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning
  97. WorldScribe: Towards Context-Aware Live Visual Descriptions
  98. DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World
  99. ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding
  100. Unveiling the Flaws: A Critical Analysis of Initialization Effect on Time Series Anomaly Detection
  101. Generalized knowledge-enhanced framework for biomedical entity and relation extraction
  102. ViMo: Generating Motions from Casual Videos
  103. Learning Noise-Robust Stable Koopman Operator for Control with Hankel DMD
  104. MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers
  105. Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion
  106. Super-intelligence or Superstition? Exploring Psychological Factors Influencing Belief in AI Predictions about Personal Behavior
  107. Deep Inertia Lp Half-Quadratic Splitting Unrolling Network for Sparse View CT Reconstruction
  108. A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition
  109. GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
  110. ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection
  111. A Structure-aware Generative Model for Biomedical Event Extraction
  112. OpenEP: Open-Ended Future Event Prediction
  113. CTISum: A New Benchmark Dataset For Cyber Threat Intelligence Summarization
  114. Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning
  115. Variance-Reduced Cascade Q-learning: Algorithms and Sample Complexity
  116. HDRGS: High Dynamic Range Gaussian Splatting
  117. Value of Information and Reward Specification in Active Inference and POMDPs
  118. Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment
  119. Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data