mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 8 Nov 2024

222 papers

  1. Using Spatial Diffusions for Optoacoustic Tomography Image ReconstructionDiffusion models → Medical imaging and segmentation
  2. A Modular Conditional Diffusion Framework for Image ReconstructionDiffusion models → Inverse problems and image restoration
  3. Game-theoretic LLM: Agent Workflow for Negotiation GamesLLM agents and tool use → Social simulation and multi-agent debate
  4. Fine-Grained Reward Optimization for Machine Translation using Error Severity MappingsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  6. NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language ModelMixture-of-experts → Multimodal MoE models
  7. Mitigating Hallucination with ZeroG: An Advanced Knowledge Management EngineKnowledge distillation → Knowledge distillation for LLMs
  8. Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem SolvingLLM agents and tool use → Tool learning and function calling
  9. Autonomous Industrial Control using an Agentic Framework with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving AgentMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  11. SSSD: Simply-Scalable Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  12. RefreshKV: Updating Small KV Cache During Long-form GenerationEfficient LLM inference and serving → KV cache optimization
  13. Safe Reinforcement Learning of Robot Trajectories in the Presence of Moving ObstaclesDeep reinforcement learning methods → Safe and constrained RL
  14. End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-AnsweringLLM reasoning → Spatial and embodied reasoning +1
  15. Free Record-Level Privacy Risk Evaluation Through Artifact-Based MethodsLLM safety and security → Membership inference attacks
  16. Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  17. Improving Molecular Graph Generation with Flow Matching and Optimal TransportDiffusion models → Flow matching, time series and science
  18. The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agentLLM agents and tool use → Social simulation and multi-agent debate
  19. LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and ExecutionLLM agents and tool use → Multimodal and embodied agents
  20. Evaluating Large Language Model Capability in Vietnamese Fact-Checking Data GenerationLLM reasoning → Reasoning benchmarks and evaluation
  21. WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-makingWorld models → World models for navigation
  22. Knowledge Distillation Neural Network for Predicting Car-following Behaviour of Human-driven and Autonomous VehiclesKnowledge distillation → Multimodal distillation
  23. Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A SurveyDeep reinforcement learning methods → Deep RL algorithms and representations
  24. Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVsDeep reinforcement learning methods → RL for robot navigation and UAV control
  25. Assessing the Answerability of Queries in Retrieval-Augmented Code GenerationRetrieval-augmented generation → RAG for code
  26. Towards Lifelong Few-Shot Customization of Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing +1
  27. Towards Active Flow Control Strategies Through Deep Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  28. Improving image synthesis with diffusion-negative samplingDiffusion models → Image generation, text-to-image and editing
  29. Bridging the Gap between Learning and Inference for Diffusion-Based Molecule GenerationDiffusion models → Flow matching, time series and science
  30. WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language ModelsLLM agents and tool use → Software engineering coding agents
  31. IntellBot: Retrieval Augmented LLM Chatbot for Cyber Threat Knowledge DeliveryRetrieval-augmented generation → Privacy and security of RAG
  32. Gap-Filling Prompting Enhances Code-Assisted Mathematical ReasoningLLM reasoning → Mathematical reasoning
  33. Benchmarking Distributional Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  34. Enhancing Visual Classification using Comparative DescriptorsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  35. RED: Residual Estimation Diffusion for Low-Dose PET Sinogram ReconstructionDiffusion models → Medical imaging and segmentation
  36. Enhancing Cluster Resilience: LLM-agent Based Autonomous Intelligent Cluster Diagnosis System and Evaluation FrameworkRetrieval-augmented generation → Agentic RAG, agents and memory +1
  37. Reinforcement Learning for Adaptive Resource Scheduling in Complex System EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
  38. Reasoning Robustness of LLMs to Adversarial Typographical ErrorsLLM reasoning → Reasoning benchmarks and evaluation
  39. Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  40. Aligning Large Language Models and Geometric Deep Models for Protein RepresentationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
  41. Adaptive Whole-Body PET Image Denoising Using 3D Diffusion Models with ControlNetDiffusion models → Medical imaging and segmentation
  42. SpecHub: Provable Acceleration to Multi-Draft Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  43. AgentOps: Enabling Observability of LLM AgentsLLM agents and tool use → Software engineering coding agents
  44. Real-World Offline Reinforcement Learning from Vision Language Model FeedbackMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  45. Hierarchical Visual Feature Aggregation for OCR-Free Document UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  46. Benefits and Risks of Using ChatGPT4 as a Teaching Assistant for Computer Science Students
  47. ProteinWeaver: A Divide-and-Assembly Approach for Protein Backbone Design
  48. Adaptive Sensor Placement Inspired by Bee Foraging: Towards Efficient Environment Monitoring
  49. HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis
  50. Beyond object identification: How train drivers evaluate the risk of collision
  51. Multi-Document Financial Question Answering using LLMs
  52. Analysis, forecasting and system identification of a floating offshore wind turbine using dynamic mode decomposition
  53. Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection
  54. Acoustic-based 3D Human Pose Estimation Robust to Human Position
  55. A Comprehensive Guide to Enhancing Antibiotic Discovery Using Machine Learning Derived Bio-computation
  56. The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
  57. Filling in Missing FX Implied Volatilities with Uncertainties: Improving VAE-Based Volatility Imputation
  58. GUIDEQ: Framework for Guided Questioning for progressive informational collection and classification
  59. Generating Fearful Images: Investigating Potential Emotional Biases in Image-Generation Models
  60. Longitudinal Ensemble Integration for sequential classification with multimodal data
  61. Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM
  62. FactLens: Benchmarking Fine-Grained Fact Verification
  63. Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits
  64. The Empirical Impact of Data Sanitization on Language Models
  65. Toward Transdisciplinary Approaches to Audio Deepfake Discernment
  66. Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation
  67. Utilisation of Vision Systems and Digital Twin for Maintaining Cleanliness in Public Spaces
  68. Assessing Foundational Medical 'Segment Anything' (Med-SAM1, Med-SAM2) Deep Learning Models for Left Atrial Segmentation in 3D LGE MRI
  69. A method based on Generative Adversarial Networks for disentangling physical and chemical properties of stars in astronomical spectra
  70. Efficient Self-Supervised Barlow Twins from Limited Tissue Slide Cohorts for Colonic Pathology Diagnostics
  71. Sentiment Analysis of Cyberbullying Data in Social Media
  72. Tackling extreme urban heat: a machine learning approach to assess the impacts of climate change and the efficacy of climate adaptation strategies in urban microclimates
  73. Querying Perception Streams with Spatial Regular Expressions
  74. Quantifying artificial intelligence through algorithmic generalization
  75. GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise
  76. The effect of different feature selection methods on models created with XGBoost
  77. BERTrend: Neural Topic Modeling for Emerging Trends Detection
  78. Reducing Distraction in Long-Context Language Models by Focused Learning
  79. Moving Off-the-Grid: Scene-Grounded Video Representations
  80. DNAMite: Interpretable Calibrated Survival Analysis with Discretized Additive Models
  81. Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model
  82. Autoregressive Models in Vision: A Survey
  83. ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification
  84. Enhancing Cardiovascular Disease Prediction through Multi-Modal Self-Supervised Learning
  85. Streaming Bayes GFlowNets
  86. Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators
  87. One Small and One Large for Document-level Event Argument Extraction
  88. Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models
  89. A Comparative Analysis of Machine Learning Models for DDoS Detection in IoT Networks
  90. Sdn Intrusion Detection Using Machine Learning Method
  91. Predictive Digital Twin for Condition Monitoring Using Thermal Imaging
  92. UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors
  93. Alternative Learning Paradigms for Image Quality Transfer
  94. Untrained Perceptual Loss for image denoising of line-like structures in MR images
  95. Benchmarking 3D multi-coil NC-PDNet MRI reconstruction
  96. When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
  97. Towards Equitable ASD Diagnostics: A Comparative Study of Machine and Deep Learning Models Using Behavioral and Facial Data
  98. Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors
  99. Joint-Optimized Unsupervised Adversarial Domain Adaptation in Remote Sensing Segmentation with Prompted Foundation Model
  100. Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
All 222
  1. ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articles
  2. Using Language Models to Disambiguate Lexical Choices in Translation
  3. GazeSearch: Radiology Findings Search Benchmark
  4. Curriculum Learning for Few-Shot Domain Adaptation in CT-based Airway Tree Segmentation
  5. LLMs as Method Actors: A Model for Prompt Engineering and Architecture
  6. Quantitative Assessment of Intersectional Empathetic Bias and Understanding
  7. Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?
  8. Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems
  9. FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents
  10. Multi-hop Evidence Pursuit Meets the Web: Team Papelo at FEVER 2024
  11. Tract-RLFormer: A Tract-Specific RL policy based Decoder-only Transformer Network
  12. FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information
  13. On Differentially Private String Distances
  14. Multi-Dimensional Reconfigurable, Physically Composable Hybrid Diffractive Optical Neural Network
  15. WavShadow: Wavelet Based Shadow Segmentation and Removal
  16. Continuous-Time Analysis of Adaptive Optimization and Normalization
  17. Topology-aware Reinforcement Feature Space Reconstruction for Graph Data
  18. StdGEN: Semantic-Decomposed 3D Character Generation from Single Images
  19. Aioli: A Unified Optimization Framework for Language Model Data Mixing
  20. Poze: Sports Technique Feedback under Data Constraints
  21. Differential Privacy Under Class Imbalance: Methods and Empirical Insights
  22. PEP-GS: Perceptually-Enhanced Precise Structured 3D Gaussians for View-Adaptive Rendering
  23. Learning Subsystem Dynamics in Nonlinear Systems via Port-Hamiltonian Neural Networks
  24. Graph-Dictionary Signal Model for Sparse Representations of Multivariate Data
  25. A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
  26. STARS: Sensor-agnostic Transformer Architecture for Remote Sensing
  27. Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
  28. Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
  29. Image inpainting enhancement by replacing the original mask with a self-attended region from the input image
  30. Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
  31. IPMN Risk Assessment under Federated Learning Paradigm
  32. YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training
  33. Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition
  34. Asterisk*: Keep it Simple
  35. Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning
  36. Tell What You Hear From What You See -- Video to Audio Generation Through Text
  37. Relationships between the degrees of freedom in the affine Gaussian derivative model for visual receptive fields and 2-D affine image transformations, with application to covariance properties of simple cells in the primary visual cortex
  38. Exploring the Limits of Large Language Models: A Systematic Evaluation of Masked Text Processing Ability through MskQA and MskCal
  39. Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation
  40. Multi-armed Bandits with Missing Outcome
  41. Enhancing Model Fairness and Accuracy with Similarity Networks: A Methodological Approach
  42. Assessing Open-Source Large Language Models on Argumentation Mining Subtasks
  43. Impact of Fake News on Social Media Towards Public Users of Different Age Groups
  44. Video RWKV:Video Action Recognition Based RWKV
  45. SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection
  46. Physics-constrained coupled neural differential equations for one dimensional blood flow modeling
  47. Cross-validating causal discovery via Leave-One-Variable-Out
  48. A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis
  49. Efficient Audio-Visual Fusion for Video Classification
  50. Expectation vs. Reality: Towards Verification of Psychological Games
  51. Predicting Stroke through Retinal Graphs and Multimodal Self-supervised Learning
  52. Machine learning-driven Anomaly Detection and Forecasting for Euclid Space Telescope Operations
  53. Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages
  54. Decentralized EM Algorithm for Gaussian Mixtures under Data Heterogeneity and Partial Labeling
  55. Towards a Real-Time Simulation of Elastoplastic Deformation Using Multi-Task Neural Networks
  56. Solving 7x7 Killall-Go with Seki Database
  57. Open-set object detection: towards unified problem formulation and benchmarking
  58. Objective drives the consistency of representational similarity across datasets
  59. A Nerf-Based Color Consistency Method for Remote Sensing Images
  60. DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions
  61. CRepair: CVAE-based Automatic Vulnerability Repair Technology
  62. How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP
  63. Alignment of 3D woodblock geometrical models and 2D orthographic projection image
  64. SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
  65. Towards Scalable Foundation Models for Digital Dermatology
  66. An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking
  67. LBPE: Long-token-first Tokenization to Improve Large Language Models
  68. KyrgyzNLP: Challenges, Progress, and Future
  69. FGGP: Fixed-Rate Gradient-First Gradual Pruning
  70. Tightly-Coupled, Speed-aided Monocular Visual-Inertial Localization in Topological Map
  71. Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Study
  72. Handling geometrical variability in nonlinear reduced order modeling through Continuous Geometry-Aware DL-ROMs
  73. The Limits of Differential Privacy in Online Learning
  74. EUREKHA: Enhancing User Representation for Key Hackers Identification in Underground Forums
  75. Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
  76. Supporting Automated Fact-checking across Topics: Similarity-driven Gradual Topic Learning for Claim Detection
  77. Comparative Study of Probabilistic Atlas and Deep Learning Approaches for Automatic Brain Tissue Segmentation from MRI Using N4 Bias Field Correction and Anisotropic Diffusion Pre-processing Techniques
  78. The sampling complexity of learning invertible residual neural networks
  79. ClusterGraph: a new tool for visualization and compression of multidimensional data
  80. ICE-T: A Multi-Faceted Concept for Teaching Machine Learning
  81. VISTA: Visual Integrated System for Tailored Automation in Math Problem Generation Using LLM
  82. Learning the rules of peptide self-assembly through data mining with large language models
  83. WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning
  84. POC-SLT: Partial Object Completion with SDF Latent Transformers
  85. Web Archives Metadata Generation with GPT-4o: Challenges and Insights
  86. Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields
  87. AuthFormer: Adaptive Multimodal biometric authentication transformer for middle-aged and elderly people
  88. Advancing Meteorological Forecasting: AI-based Approach to Synoptic Weather Map Analysis
  89. Towards Low-Resource Harmful Meme Detection with LMM Agents
  90. Word reuse and combination support efficient communication of emerging concepts
  91. Machine learning for prediction of dose-volume histograms of organs-at-risk in prostate cancer from simple structure volume parameters
  92. Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking
  93. From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuS
  94. Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
  95. Agricultural Landscape Understanding At Country-Scale
  96. Controlling Grokking with Nonlinearity and Data Symmetry
  97. LLM-PySC2: Starcraft II learning environment for Large Language Models
  98. SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers
  99. A Quality-Centric Framework for Generic Deepfake Detection
  100. Discovering Latent Causal Graphs from Spatiotemporal Data
  101. Inversion-based Latent Bayesian Optimization
  102. SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation
  103. Rate-aware Compression for NeRF-based Volumetric Video
  104. Fairness in Monotone k-submodular Maximization: Algorithms and Applications
  105. Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization
  106. A Real-time Face Mask Detection and Social Distancing System for COVID-19 using Attention-InceptionV3 Model
  107. ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
  108. Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
  109. On Training of Kolmogorov-Arnold Networks
  110. SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection
  111. MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
  112. Fox-1: Open Small Language Model for Cloud and Edge
  113. Revisiting the Robustness of Watermarking to Paraphrasing Attacks
  114. GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching
  115. Distributed-Order Fractional Graph Operating Network
  116. Seeing Through the Fog: A Cost-Effectiveness Analysis of Hallucination Detection Systems
  117. Cancer-Net SCa-Synth: An Open Access Synthetically Generated 2D Skin Lesion Dataset for Skin Cancer Classification
  118. Image Decomposition: Theory, Numerical Schemes, and Performance Evaluation
  119. Minimal Conditions for Beneficial Neighbourhood Search and Local Descent
  120. Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation
  121. QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning
  122. What talking you?: Translating Code-Mixed Messaging Texts to English