mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 24 Apr 2024

229 papers

  1. MatFusion: A Generative Diffusion Model for SVBRDF CaptureDiffusion models → 3D, point cloud and scene generation
  2. Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question AnsweringMultimodal LLMs / vision-language models → Medical vision-language models
  3. AFU: Actor-Free critic Updates in off-policy RL for continuous controlDeep reinforcement learning methods → RL theory and sample complexity
  4. Logic Learning from Demonstrations for Multi-step Manipulation Tasks in Dynamic EnvironmentsOffline RL and imitation learning from data → Robot learning from demonstration
  5. From Local to Global: A Graph RAG Approach to Query-Focused SummarizationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  6. FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset DeduplicationMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  7. Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and ChallengesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  8. Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic PerspectiveWorld models → World models for language agents +1
  9. CompilerDream: Learning a Compiler World Model for General Code OptimizationWorld models → World models for language agents
  10. Cantor: Inspiring Multimodal Chain-of-Thought of MLLMLLM reasoning → Multimodal reasoning
  11. Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real DocumentsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  12. Editable Image Elements for Controllable SynthesisDiffusion models → Image generation, text-to-image and editing
  13. Investigating Adversarial Trigger Transfer in Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  14. The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  15. Improving Dictionary Learning with Gated Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  16. MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few ExamplesLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. A Survey on Visual MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  19. CORM: Cache Optimization with Recent Message for Large Language Model InferenceEfficient LLM inference and serving → KV cache optimization
  20. Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for TelecommunicationsRetrieval-augmented generation → RAG pipeline design and evaluation
  21. ST-MambaSync: The Complement of Mamba and Transformers for Spatial-Temporal in Traffic Flow PredictionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  22. Recursive Backwards Q-Learning in Deterministic EnvironmentsDeep reinforcement learning methods → RL theory and sample complexity
  23. MotionMaster: Training-free Camera Motion Transfer For Video GenerationDiffusion models → Video generation
  24. Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language ExplainerMultimodal LLMs / vision-language models → Video understanding with MLLMs
  25. BASS: Batched Attention-optimized Speculative SamplingEfficient LLM inference and serving → Speculative decoding
  26. Bi-Mamba+: Bidirectional Mamba for Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  27. Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential EquationsDiffusion models → Diffusion foundations and sampling
  28. Debiasing Machine Unlearning with Counterfactual ExamplesLLM safety and security → Machine unlearning
  29. Let's Think Dot by Dot: Hidden Computation in Transformer Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  30. AnoFPDM: Anomaly Segmentation with Forward Process of Diffusion Models for Brain MRIDiffusion models → Medical imaging and segmentation
  31. CharacterFactory: Sampling Consistent Characters with GANs for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  32. Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  33. CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of CodeLLM safety and security → Watermarking generated content and models
  34. Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion ModelsDiffusion models → Flow matching, time series and science
  35. A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  36. A Differential and Pointwise Control Approach to Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  37. ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value ExtractionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  38. Using Artificial Intelligence to Unlock Crowdfunding Success for Small Businesses
  39. Leveraging AI for Climate Resilience in Africa: Challenges, Opportunities, and the Need for Collaboration
  40. Sign Language Recognition based on YOLOv5 Algorithm for the Telugu Sign Language
  41. Gated Low-rank Adaptation for personalized Code-Switching Automatic Speech Recognition on the low-spec devices
  42. BERT vs GPT for financial engineering
  43. Integrating LSTM and BERT for Long-Sequence Data Analysis in Intelligent Tutoring Systems
  44. Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks
  45. Homonym Sense Disambiguation in the Georgian Language
  46. A Hybrid Probabilistic Battery Health Management Approach for Robust Inspection Drone Operations
  47. Autonomous LLM-driven research from data to human-verifiable research papers
  48. Automatic AI controller that can drive with confidence: steering vehicle with uncertainty knowledge
  49. Attacks on Third-Party APIs of Large Language Models
  50. Layer Collapse Can be Induced by Unstructured Pruning
  51. Anomaly Detection for Incident Response at Scale
  52. Review of Data-centric Time Series Analysis from Sample, Feature, and Period
  53. Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryption
  54. Prompt Leakage effect and defense strategies for multi-turn LLM interactions
  55. Semgrex and Ssurgeon, Searching and Manipulating Dependency Graphs
  56. URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
  57. AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
  58. Computational analysis of the language of pain: a systematic review
  59. Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
  60. Step Differences in Instructional Video
  61. NeRF-XL: Scaling NeRFs with Multiple GPUs
  62. Efficient NAS with FaDE on Hierarchical Spaces
  63. ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modeling
  64. An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
  65. GPU-RANC: A CUDA Accelerated Simulation Framework for Neuromorphic Architectures
  66. Knowledge Graph Completion using Structural and Textual Embeddings
  67. AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results
  68. Towards Efficient Patient Recruitment for Clinical Trials: Application of a Prompt-Based Learning Model
  69. ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees
  70. Improving Multi-label Recognition using Class Co-Occurrence Probabilities
  71. Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
  72. ABCD: Trust enhanced Attention based Convolutional Autoencoder for Risk Assessment
  73. Blind Federated Learning without initial model
  74. S2DEVFMAP: Self-Supervised Learning Framework with Dual Ensemble Voting Fusion for Maximizing Anomaly Prediction in Timeseries
  75. Advancing Recommender Systems by mitigating Shilling attacks
  76. MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models
  77. The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms
  78. Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
  79. Scaling Lifelong Multi-Agent Path Finding to More Realistic Settings: Research Challenges and Opportunities
  80. Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
  81. The Feasibility of Implementing Large-Scale Transformers on Multi-FPGA Platforms
  82. Guardians of the Quantum GAN
  83. Does SAM dream of EIG? Characterizing Interactive Segmenter Performance using Expected Information Gain
  84. A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models
  85. Machine-Learned Closure of URANS for Stably Stratified Turbulence: Connecting Physical Timescales & Data Hyperparameters of Deep Time-Series Models
  86. A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges
  87. Learned Pulse Shaping Design for PAPR Reduction in DFT-s-OFDM
  88. 3D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN Refinement
  89. Power Failure Cascade Prediction using Graph Neural Networks
  90. Quantitative Characterization of Retinal Features in Translated OCTA
  91. Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better
  92. Comparison of static and dynamic random forests models for EHR data in the presence of competing risks: predicting central line-associated bloodstream infection
  93. Classifying Human-Generated and AI-Generated Election Claims in Social Media
  94. Online Personalizing White-box LLMs Generation with Neural Bandits
  95. zkLLM: Zero Knowledge Proofs for Large Language Models
  96. Evolution of Voices in French Audiovisual Media Across Genders and Age in a Diachronic Perspective
  97. Enhancing Diagnosis through AI-driven Analysis of Reflectance Confocal Microscopy
  98. Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
  99. MaGGIe: Masked Guided Gradual Human Instance Matting
  100. MoDE: CLIP Data Experts via Clustering
All 229
  1. Learning Car-Following Behaviors Using Bayesian Matrix Normal Mixture Regression
  2. PuLID: Pure and Lightning ID Customization via Contrastive Alignment
  3. RetinaRegNet: A Zero-Shot Approach for Retinal Image Registration
  4. Neural Operators Learn the Local Physics of Magnetohydrodynamics
  5. GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting
  6. Unimodal and Multimodal Sensor Fusion for Wearable Activity Recognition
  7. A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
  8. BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation
  9. Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
  10. GAN-HA: A generative adversarial network with a novel heterogeneous dual-discriminator network and a new attention-based fusion strategy for infrared and visible image fusion
  11. On the Fourier analysis in the SO(3) space : EquiLoPO Network
  12. Interpretable Clustering with the Distinguishability Criterion
  13. Soil analysis with machine-learning-based processing of stepped-frequency GPR field measurements: Preliminary study
  14. Explainable AI models for predicting liquefaction-induced lateral spreading
  15. Beyond Deepfake Images: Detecting AI-Generated Videos
  16. Mixed Supervised Graph Contrastive Learning for Recommendation
  17. Mammo-CLIP: Leveraging Contrastive Language-Image Pre-training (CLIP) for Enhanced Breast Cancer Diagnosis with Multi-view Mammography
  18. Decentralized Personalized Federated Learning based on a Conditional Sparse-to-Sparser Scheme
  19. Generalization Measures for Zero-Shot Cross-Lingual Transfer
  20. Inside the echo chamber: Linguistic underpinnings of misinformation on Twitter
  21. KGValidator: A Framework for Automatic Validation of Knowledge Graph Construction
  22. An Element-Wise Weights Aggregation Method for Federated Learning
  23. Perception and Localization of Macular Degeneration Applying Convolutional Neural Network, ResNet and Grad-CAM
  24. Learning Long-form Video Prior via Generative Pre-Training
  25. Drawing the Line: Deep Segmentation for Extracting Art from Ancient Etruscan Mirrors
  26. Assessing The Potential Of Mid-Sized Language Models For Clinical QA
  27. OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation
  28. Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Control
  29. Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains
  30. Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
  31. Machine Learning for Pre/Post Flight UAV Rotor Defect Detection Using Vibration Analysis
  32. Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection
  33. Effective Unsupervised Constrained Text Generation based on Perturbed Masking
  34. Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration
  35. CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning
  36. QOPTLib: a Quantum Computing Oriented Benchmark for Combinatorial Optimization Problems
  37. Porting Large Language Models to Mobile Devices for Question Answering
  38. Detecting Conceptual Abstraction in LLMs
  39. 3D Freehand Ultrasound using Visual Inertial and Deep Inertial Odometry for Measuring Patellar Tracking
  40. From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
  41. Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation
  42. Constructive Interpolation and Concept-Based Beth Definability for Description Logics via Sequents
  43. Employing Two-Dimensional Word Embedding for Difficult Tabular Data Stream Classification
  44. OpTC -- A Toolchain for Deployment of Neural Networks on AURIX TC3xx Microcontrollers
  45. Accelerating Cavity Fault Prediction Using Deep Learning at Jefferson Laboratory
  46. A Configurable and Efficient Memory Hierarchy for Neural Network Hardware Accelerator
  47. SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data
  48. Vision Transformer-based Adversarial Domain Adaptation
  49. Single-View Scene Point Cloud Human Grasp Generation
  50. Fast Ensembling with Diffusion Schr"odinger Bridge
  51. Facilitating Advanced Sentinel-2 Analysis Through a Simplified Computation of Nadir BRDF Adjusted Reflectance
  52. One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion
  53. Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
  54. Beyond ESM2: Graph-Enhanced Protein Sequence Modeling with Efficient Clustering
  55. GeckOpt: LLM System Efficiency via Intent-Based Tool Selection
  56. Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
  57. Large Language Models as In-context AI Generators for Quality-Diversity
  58. Leveraging Large Language Models for Multimodal Search
  59. Rethinking model prototyping through the MedMNIST+ dataset collection
  60. An Empirical Study of Aegis
  61. Real-Time Compressed Sensing for Joint Hyperspectral Image Transmission and Restoration for CubeSat
  62. A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry
  63. Toward Physics-Aware Deep Learning Architectures for LiDAR Intensity Simulation
  64. DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines
  65. ChEX: Interactive Localization and Region Description in Chest X-rays
  66. 3D Face Morphing Attack Generation using Non-Rigid Registration
  67. Exploring Machine Learning Algorithms for Infection Detection Using GC-IMS Data: A Preliminary Study
  68. Guided-SPSA: Simultaneous Perturbation Stochastic Approximation assisted by the Parameter Shift Rule
  69. Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
  70. A General Black-box Adversarial Attack on Graph-based Fake News Detectors
  71. SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfer
  72. Generalizing the SINDy approach with nested neural networks
  73. No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement
  74. What Makes Multimodal In-Context Learning Work?
  75. ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Prediction
  76. MD-NOMAD: Mixture density nonlinear manifold decoder for emulating stochastic differential equations and uncertainty propagation
  77. Gradformer: Graph Transformer with Exponential Decay
  78. SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
  79. Annotator-Centric Active Learning for Subjective NLP Tasks
  80. HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
  81. Mitigating False Predictions In Unreasonable Body Regions
  82. Ada-DF: An Adaptive Label Distribution Fusion Network For Facial Expression Recognition
  83. ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos
  84. ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images
  85. Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning
  86. Nyonic Technical Report
  87. MAS-SAM: Segment Any Marine Animal with Aggregated Features
  88. DeepFeatureX Net: Deep Features eXtractors based Network for discriminating synthetic from real images
  89. Deep Learning for Accelerated and Robust MRI Reconstruction: a Review
  90. Long-term Off-Policy Evaluation and Learning
  91. Neural Proto-Language Reconstruction
  92. Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation
  93. Automated Creation of Source Code Variants of a Cryptographic Hash Function Implementation Using Generative Pre-Trained Transformer Models
  94. Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System
  95. Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twitter
  96. Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision
  97. The Promise and Challenges of Using LLMs to Accelerate the Screening Process of Systematic Reviews
  98. CWF: Consolidating Weak Features in High-quality Mesh Simplification
  99. KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering
  100. FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
  101. MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
  102. Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering
  103. CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
  104. Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
  105. Cross-Embodied Affordance Transfer through Learning Affordance Equivalences
  106. Building-PCC: Building Point Cloud Completion Benchmarks
  107. PriorNet: A Novel Lightweight Network with Multidimensional Interactive Attention for Efficient Image Dehazing
  108. A Real-time Evaluation Framework for Pedestrian's Potential Risk at Non-Signalized Intersections Based on Predicted Post-Encroachment Time
  109. Artificial Intelligence for Multi-Unit Auction design
  110. FR-NAS: Forward-and-Reverse Graph Predictor for Efficient Neural Architecture Search
  111. Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance
  112. Neural Operator induced Gaussian Process framework for probabilistic solution of parametric partial differential equations
  113. A Bi-directional Multi-solution Scalable Grover Search Algorithm
  114. M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognition
  115. Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
  116. Hybrid LLM/Rule-based Approaches to Business Insights Generation from Structured Data
  117. Deepfakes and Higher Education: A Research Agenda and Scoping Review of Synthetic Media
  118. Human-in-the-loop Learning for Dynamic Congestion Games
  119. Federated Learning with Only Positive Labels by Exploring Label Correlations
  120. GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL
  121. Variational Deep Survival Machines: Survival Regression with Censored Outcomes
  122. A Survey of Deep Long-Tail Classification Advancements
  123. Domain Adaptation for Learned Image Compression with Supervised Adapters
  124. Minimal Evidence Group Identification for Claim Verification
  125. Brain Storm Optimization Based Swarm Learning for Diabetic Retinopathy Image Classification
  126. Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems
  127. MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis
  128. Can Foundational Large Language Models Assist with Conducting Pharmaceuticals Manufacturing Investigations?
  129. Retrieval Head Mechanistically Explains Long-Context Factuality