mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 15 May 2024

194 papers

  1. VisioBlend: Sketch and Stroke-Guided Denoising Diffusion Probabilistic Model for Realistic Image GenerationDiffusion models → Image generation, text-to-image and editing
  2. IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner MonologuesRetrieval-augmented generation → Conversational and speech RAG
  3. A Comprehensive Survey of Accelerated Generation Techniques in Large Language ModelsEfficient LLM inference and serving → Speculative decoding
  4. Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation ModelsLLM safety and security → Prompt injection and agent security
  5. Spectral Editing of Activations for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  6. SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World KnowledgeLLM reasoning → Multimodal reasoning
  7. Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  8. Detecting Continuous Integration Skip : A Reinforcement Learning-based ApproachDeep reinforcement learning methods → RL training of language and agent models
  9. Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language ModelsWorld models → World models for language agents
  10. MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal CancerDiffusion models → Medical imaging and segmentation
  11. Declarative Design of Neural Predicates in Neuro-Symbolic SystemsLLM reasoning → Reasoning benchmarks and evaluation
  12. M4oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of ExpertsMixture-of-experts → Medical and biomedical MoE
  13. Diffusion-based Contrastive Learning for Sequential RecommendationDiffusion models → Diffusion recommenders
  14. Prompting-based Synthetic Data Generation for Few-Shot Question AnsweringSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  15. A Mixture of Experts (MoE) model to improve AI-based computational pathology prediction performance under variable levels of histopathology image blurMixture-of-experts → Medical and biomedical MoE
  16. Word Alignment as Preference for Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  17. Xmodel-VLM: A Simple Baseline for Multimodal Vision Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. DVS-RG: Differential Variable Speed Limits Control using Deep Reinforcement Learning with Graph State RepresentationDeep reinforcement learning methods → RL for autonomous driving and traffic
  19. Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained OptimizationLLM safety and security → Jailbreaking
  20. CarDreamer: Open-Source Learning Platform for World Model based Autonomous DrivingWorld models → World models for autonomous driving +1
  21. Chaos-based reinforcement learning with TD3Deep reinforcement learning methods → RL theory and sample complexity
  22. RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image DehazingDiffusion models → Inverse problems and image restoration
  23. Naturalistic Music Decoding from EEG Data via Latent Diffusion ModelsDiffusion models → Audio, speech and music
  24. CTS: A Consistency-Based Medical Image Segmentation ModelDiffusion models → Medical imaging and segmentation
  25. A safety realignment framework via subspace-oriented model fusion for large language modelsLLM safety and security → Safety alignment, refusal and guardrails
  26. Combining data from multiple sources for urban travel mode choice modelling
  27. Trustworthy AI in practice: an analysis of practitioners' needs and challenges
  28. Data-driven Nucleus Subclassification on Colon H&E using Style-transferred Digital Pathology
  29. Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
  30. Towards Unstructured Unlabeled Optical Mocap: A Video Helps!
  31. Sensing technologies and machine learning methods for emotion recognition in autism: Systematic review
  32. f-GAN: A frequency-domain-constrained generative adversarial network for PPG to ECG synthesis
  33. Coronary Artery Disease Classification Using One-dimensional Convolutional Neural Network
  34. An Initial Study of Human-Scale Blockage in sub-THz Radio Propagation with Application to Indoor Passive Localization
  35. A Survey of Transformer-based Language Models with Focus on Efficiency
  36. Optimizing Sales Forecasts through Automated Integration of Market Indicators
  37. Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts
  38. A survey on fairness of large language models in e-commerce: progress, application, and challenge
  39. Intelligent Tutor: Leveraging ChatGPT and Microsoft Copilot Studio to Deliver a Generative AI Student Support and Feedback System within Teams
  40. LLMs can learn self-restraint through iterative self-reflection
  41. Using Combinatorial Optimization to Design a High quality LLM Solution
  42. Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings
  43. A Systematic Analysis on the Temporal Generalization of Language Models in Social Media
  44. Fully Distributed Fog Load Balancing with Multi-Agent Reinforcement Learning
  45. UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
  46. Comparative Analysis of Predicting Subsequent Steps in H'enon Map
  47. SCI 3.0: A Web-based Schema Curation Interface for Graphical Event Representations
  48. From NeRFs to Gaussian Splats, and Back
  49. Illumination Histogram Consistency Metric for Quantitative Assessment of Video Sequences
  50. STAR: A Benchmark for Situated Reasoning in Real-World Videos
  51. No More Mumbles: Enhancing Robot Intelligibility through Speech Adaptation
  52. Point2SSM++: Self-Supervised Learning of Anatomical Shape Models from Point Clouds
  53. Weakly Supervised Bayesian Shape Modeling from Unsegmented Medical Images
  54. Enhancing Saliency Prediction in Monitoring Tasks: The Role of Visual Highlights
  55. Modeling User Preferences via Brain-Computer Interfacing
  56. Generalized Holographic Reduced Representations
  57. A Theory of Synaptic Neural Balance: From Local to Global Order
  58. UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation
  59. Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulation
  60. The radius of statistical efficiency
  61. LoRA Learns Less and Forgets Less
  62. Learning 3-Manifold Triangulations
  63. Improving Label Error Detection and Elimination with Uncertainty Quantification
  64. Fully Automated OCT-based Tissue Screening System
  65. Aggregate Representation Measure for Predictive Model Reusability
  66. Properties that allow or prohibit transferability of adversarial attacks among quantized networks
  67. When AI Eats Itself: On the Caveats of AI Autophagy
  68. Enhancing Maritime Trajectory Forecasting via H3 Index and Causal Language Modelling (CLM)
  69. Simplicity within biological complexity
  70. Learning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
  71. SQL-to-Schema Enhances Schema Linking in Text-to-SQL
  72. A Survey of Generative Techniques for Spatial-Temporal Data Mining
  73. A Comprehensive Survey on Data Augmentation
  74. A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models
  75. Training Deep Learning Models with Hybrid Datasets for Robust Automatic Target Detection on real SAR images
  76. Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation
  77. An Embarrassingly Simple Approach to Enhance Transformer Performance in Genomic Selection for Crop Breeding
  78. Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System
  79. AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning
  80. BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation
  81. Classifying geospatial objects from multiview aerial imagery using semantic meshes
  82. Spectral complexity of deep neural networks
  83. Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning
  84. Restoring balance: principled under/oversampling of data for optimal classification
  85. Energy-Efficient Sleep Mode Optimization of 5G mmWave Networks Using Deep Contextual MAB
  86. Improved classical shadows from local symmetries in the Schur basis
  87. ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations
  88. Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis
  89. Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck
  90. Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming
  91. QueryNER: Segmentation of E-commerce Queries
  92. ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata
  93. C-Learner: Constrained Learning for Causal Inference
  94. MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning
  95. Color Space Learning for Cross-Color Person Re-Identification
  96. DemOpts: Fairness corrections in COVID-19 case prediction models
  97. Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts
  98. Harmonizing Human Insights and AI Precision: Hand in Hand for Advancing Knowledge Graph Task
  99. Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment
  100. Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
All 194
  1. Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening
  2. Fourier Boundary Features Network with Wider Catchers for Glass Segmentation
  3. Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models
  4. Kuramoto Oscillators and Swarms on Manifolds for Geometry Informed Machine Learning
  5. Desk-AId: Humanitarian Aid Desk Assessment with Geospatial AI for Predicting Landmine Areas
  6. Facilitating Opinion Diversity through Hybrid NLP Approaches
  7. A Survey On Text-to-3D Contents Generation In The Wild
  8. Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images
  9. On the Correspondence of Non-flat Assumption-based Argumentation and Logic Programming with Negation as Failure in the Head
  10. Distinguishing Tor From Other Encrypted Network Traffic Through Character Analysis
  11. Real-World Federated Learning in Radiology: Hurdles to overcome and Benefits to gain
  12. Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
  13. Identity Overlap Between Face Recognition Train/Test Data: Causing Optimistic Bias in Accuracy Measurement
  14. O2 is a multiple context-free grammar: an implementation-, formalisation-friendly proof
  15. Matching domain experts by training from scratch on domain knowledge
  16. SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning
  17. PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
  18. SARATR-X: Toward Building A Foundation Model for SAR Target Recognition
  19. On the Saturation Effect of Kernel Ridge Regression
  20. When fairness metrics fail: A utility-based perspective on varepsilon-fairness
  21. Vision-Based Neurosurgical Guidance: Unsupervised Localization and Camera-Pose Prediction
  22. Large coordinate kernel attention network for lightweight image super-resolution
  23. Progressive Depth Decoupling and Modulating for Flexible Depth Completion
  24. Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
  25. Content-Based Image Retrieval for Multi-Class Volumetric Radiology Images: A Benchmark Study
  26. Application of Gated Recurrent Units for CT Trajectory Optimization
  27. Multi-Source Conformal Inference Under Distribution Shift
  28. Learning Coarse-Grained Dynamics on Graph
  29. ReconBoost: Boosting Can Achieve Modality Reconcilement
  30. Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls
  31. Agnostic Active Learning of Single Index Models with Linear Sample Complexity
  32. TimeX++: Learning Time-Series Explanations with Information Bottleneck
  33. Gradient Boosted Filters For Signal Processing
  34. Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support
  35. Tight Bounds for Online Convex Optimization with Adversarial Constraints
  36. Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology
  37. Attribute reduction algorithm of rough sets based on spatial optimization
  38. Sensitivity Decouple Learning for Image Compression Artifacts Reduction
  39. DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations
  40. MVBIND: Self-Supervised Music Recommendation For Videos Via Embedding Space Binding
  41. Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
  42. Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection
  43. Dual-Segment Clustering Strategy for Hierarchical Federated Learning in Heterogeneous Wireless Environments
  44. Dynamic Activation Pitfalls in LLaMA Models: An Empirical Study
  45. Fair Generalized Linear Mixed Models
  46. Dance Any Beat: Blending Beats with Visuals in Dance Video Generation
  47. Measuring Model-Induced Discrimination via Efficient Fairness Approximation
  48. New Textual Corpora for Serbian Language Modeling
  49. Graph Neural Network based Handwritten Trajectories Recognition
  50. NeuralCMS: A deep learning approach to study Jupiter's interior
  51. Perception-Inspired Graph Convolution for Music Understanding Tasks
  52. Bridging the gap in online hate speech detection: a comparative analysis of BERT and traditional models for homophobic content identification on X/Twitter
  53. ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models
  54. SOMTP: Self-Supervised Learning-Based Optimizer for MPC-Based Safe Trajectory Planning Problems in Robotics
  55. Lens functions for exploring UMAP Projections with Domain Knowledge
  56. Flexible image analysis for law enforcement agencies with deep neural networks to determine: where, who and what
  57. Advancing Explainable AI with Causal Analysis in Large-Scale Fuzzy Cognitive Maps
  58. HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants
  59. Cross-Input Certified Training for Universal Perturbations
  60. Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parser
  61. Scalable Image Coding for Humans and Machines Using Feature Fusion Network
  62. Curriculum Dataset Distillation
  63. A Hierarchically Feature Reconstructed Autoencoder for Unsupervised Anomaly Detection
  64. OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality
  65. Overcoming Domain Drift in Online Continual Learning
  66. RobustMVS: Single Domain Generalized Deep Multi-view Stereo
  67. HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition
  68. BonnBot-I Plus: A Bio-diversity Aware Precise Weed Management Robotic Platform
  69. SOEDiff: Efficient Distillation for Small Object Editing
  70. Motion Prediction with Gaussian Processes for Safe Human-Robot Interaction in Virtual Environments
  71. Minimisation of Polyak-Lojasewicz Functions Using Random Zeroth-Order Oracles
  72. Optimizing Sensor Network Design for Multiple Coverage
  73. Explainable AI for Ship Collision Avoidance: Decoding Decision-Making Processes and Behavioral Intentions
  74. Compressive Feature Selection for Remote Visual Multi-Task Inference
  75. Enhancing Airline Customer Satisfaction: A Machine Learning and Causal Analysis Approach
  76. Improving Transformers using Faithful Positional Encoding
  77. Task-adaptive Q-Face
  78. Response Matching for generating materials and molecules
  79. Dim Small Target Detection and Tracking: A Novel Method Based on Temporal Energy Selective Scaling and Trajectory Association
  80. Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential
  81. 3D Shape Augmentation with Content-Aware Shape Resizing
  82. Perception Without Vision for Trajectory Prediction: Ego Vehicle Dynamics as Scene Representation for Efficient Active Learning in Autonomous Driving
  83. AMSNet: Netlist Dataset for AMS Circuits
  84. Learning from Partial Label Proportions for Whole Slide Image Segmentation
  85. SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
  86. SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
  87. ICAL: Implicit Character-Aided Learning for Enhanced Handwritten Mathematical Expression Recognition
  88. Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels
  89. Deep Learning in Earthquake Engineering: A Comprehensive Review
  90. A Japanese-Chinese Parallel Corpus Using Crowdsourcing for Web Mining
  91. Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy
  92. Spatial Semantic Recurrent Mining for Referring Image Segmentation
  93. Cons-training Tensor Networks: Embedding and Optimization Over Discrete Linear Constraints
  94. Improving Sequential Market Coordination via Value-oriented Renewable Energy Forecasting