mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 29 Jul 2025

322 papers

  1. A2H-MAS: An Algorithm-to-HLS Multi-Agent System for Automated and Reliable FPGA ImplementationLLM agents and tool use → Software engineering coding agents
  2. Multimodal Video Emotion Recognition with Reliable Reasoning PriorsLLM reasoning → Audio-language model reasoning
  3. Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  4. Knowledge Editing for Multi-Hop Question Answering Using Semantic AnalysisLLM reasoning → Knowledge- and tool-augmented reasoning
  5. Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length EstimationLLM reasoning → Test-time compute and efficient thinking
  6. Cyber-Zero: Training Cybersecurity Agents without RuntimeLLM agents and tool use → Agent threats, guardrails and governance
  7. CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State ExamMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. CoEx -- Co-evolving World-model and ExplorationWorld models → World models for language agents +1
  9. Weighted Conditional Flow MatchingDiffusion models → Flow matching, time series and science
  10. RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  11. Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice BiometricsLLM safety and security → Machine unlearning
  12. Toward Trusted Onboard AI: Advancing Small Satellite Operations using Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  13. Strategic Deflection: Defending LLMs from Logit ManipulationLLM safety and security → Jailbreaking
  14. When Truthful Representations Flip Under Deceptive Instructions?Mechanistic interpretability → Probing deception, bias and beliefs
  15. Prompt Optimization and Evaluation for LLM Automated Red TeamingLLM safety and security → Prompt injection and agent security
  16. Meta CLIP 2: A Worldwide Scaling RecipeMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  17. X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great AgainDeep reinforcement learning methods → RL with diffusion and flow models
  18. DeepSieve: Information Sieving via LLM-as-a-Knowledge-RouterLLM reasoning → Knowledge- and tool-augmented reasoning +1
  19. Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel PredictionsLLM agents and tool use → Social simulation and multi-agent debate
  20. Structure-Informed Deep Reinforcement Learning for Inventory ManagementDeep reinforcement learning methods → RL for energy, networks and operations
  21. Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model SecurityMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  22. UserBench: An Interactive Gym Environment for User-Centric AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time GroundingLLM reasoning → Multimodal reasoning +2
  24. See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMsLLM reasoning → Hallucination detection and mitigation +1
  25. Teach Me to Trick: Exploring Adversarial Transferability via Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
  26. ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical KnowledgeLLM reasoning → Clinical and biomedical applications
  27. Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding VectorsRetrieval-augmented generation → Vector search and ANN indexes
  28. ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned ModelsLLM safety and security → Machine unlearning
  29. Improving Generative Ad Text on Facebook using Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  30. Compression Strategies for Efficient Multimodal LLMs in Medical ContextsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  31. Reasoning Language Models for Root Cause Analysis in 5G Wireless NetworksLLM reasoning → Reasoning for agents, planning and code
  32. Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe AdaptationRetrieval-augmented generation → Generation and context integration
  34. Post-Training Large Language Models via Reinforcement Learning from Self-FeedbackLLM reasoning → Test-time compute and efficient thinking +1
  35. MMAT-1M: A Large Reasoning Dataset for Multimodal Agent TuningLLM reasoning → Reasoning for agents, planning and code +1
  36. ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrievalLLM reasoning → Multimodal reasoning
  37. Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement LearningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  38. EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage DiversityLLM reasoning → Reinforcement learning for reasoning
  39. Cross-Architecture Distillation Made Simple with Redundancy SuppressionKnowledge distillation → General knowledge distillation methods
  40. AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  41. An Agentic AI for a New Paradigm in Business Process DevelopmentLLM agents and tool use → Software engineering coding agents
  42. Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2IsLLM safety and security → Jailbreaking
  43. Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object DetectionDiffusion models → Image generation, text-to-image and editing
  44. MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEDiffusion models → Diffusion and flow policies for robotics +1
  45. Distribution-Based Masked Medical Vision-Language Model Using Structured ReportsMultimodal LLMs / vision-language models → Medical vision-language models
  46. MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  47. Towards a rigorous evaluation of RAG systems: the challenge of due diligenceRetrieval-augmented generation → RAG pipeline design and evaluation
  48. Few-Shot Vision-Language Reasoning for Satellite Imagery via Verifiable RewardsLLM reasoning → Spatial and embodied reasoning +1
  49. Zero-Shot Machine Unlearning with Proxy Adversarial Data GenerationLLM safety and security → Machine unlearning
  50. A Multi-Agent Generative AI Framework for IC Module-Level Verification AutomationLLM agents and tool use → Software engineering coding agents
  51. APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path TracingDiffusion models → Diffusion foundations and sampling
  52. UnsafeChain: Enhancing Reasoning Model Safety via Hard CasesLLM reasoning → Reasoning for agents, planning and code +1
  53. Libra: Assessing and Improving Reward Model by Learning to ThinkLLM reasoning → Reinforcement learning for reasoning +1
  54. Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  55. StaffPro: an LLM Agent for Joint Staffing and ProfilingLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. GuidPaint: Class-Guided Image Inpainting with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  57. EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOLLM reasoning → Chain-of-thought reasoning for driving
  58. Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving CompetitionEnd-to-end autonomous driving → Cooperative and V2X driving
  59. Locally Controlled Face Aging with Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  60. SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  61. TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  62. Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource LanguagesKnowledge distillation → Knowledge distillation for LLMs
  63. MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  64. On Policy Stochasticity in Mutual Information Optimal Control of Linear SystemsDeep reinforcement learning methods → RL theory and sample complexity
  65. PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM JailbreakingLLM reasoning → Reasoning for agents, planning and code +3
  66. Model Predictive Adversarial Imitation Learning for Planning from ObservationOffline RL and imitation learning from data → Imitation learning methods
  67. Chain-of-Cooking:Cooking Process Visualization via Bidirectional Chain-of-Thought GuidanceLLM reasoning → Multimodal reasoning
  68. Model-free Speculative Decoding for Transformer-based ASR with Token Map DraftingEfficient LLM inference and serving → Speculative decoding
  69. Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty CalibrationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  70. What Does it Mean for a Neural Network to Learn a "World Model"?World models → World models for language agents
  71. Decision Transformer-Based Drone Trajectory Planning with Dynamic Safety-Efficiency Trade-OffsOffline RL and imitation learning from data → Decision transformers and sequence modeling
  72. Evaluation and Benchmarking of LLM Agents: A SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  73. MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual QuestionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  74. Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  75. Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBenchLLM reasoning → Multimodal reasoning
  76. Validating Pharmacogenomics Generative Artificial Intelligence Query Prompts Using Retrieval-Augmented Generation (RAG)Retrieval-augmented generation → Medical and biomedical RAG
  77. Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional TrainingDiffusion models → Diffusion and flow policies for robotics +1
  78. ReasonCache: Accelerating Large Reasoning Model Serving through KV Cache SharingLLM reasoning → Test-time compute and efficient thinking +1
  79. MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn ConversationsLLM agents and tool use → Tool learning and function calling
  80. ReGATE: Learning Faster and Better with Fewer Tokens in MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  81. Cascading and Proxy Membership Inference AttacksLLM safety and security → Membership inference attacks
  82. Graph-Augmented Large Language Model Agents: Current Progress and Future ProspectsLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. Shapley Uncertainty in Natural Language GenerationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  84. Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic ApproachDeep reinforcement learning methods → RL for games and combinatorial optimization
  85. Systolic Array-based Accelerator for Structured State-Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  86. A Transparent Fairness Evaluation Protocol for Open-Source Language Model Benchmarking on the Blockchain
  87. OpenFPL: An open-source forecasting method rivaling state-of-the-art Fantasy Premier League services
  88. Bayesian-Driven Graph Reasoning for Active Radio Map Construction
  89. emg2tendon: From sEMG Signals to Tendon Control in Musculoskeletal Hands
  90. Evaluating Imputation Techniques for Short-Term Gaps in Heart Rate Data
  91. Do Streetscapes Still Matter for Customer Ratings of Eating and Drinking Establishments in Car-Dependent Cities?
  92. DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation
  93. Comparison of Information Retrieval Techniques Applied to IT Support Tickets
  94. From Waveforms to Pixels: A Survey on Audio-Visual Segmentation
  95. Technical specification of a framework for the collection of clinical images and data
  96. Measuring Dependencies between Biological Signals with Self-supervision, and its Limitations
  97. Evaluating Transfer Learning Methods on Real-World Data Streams: A Case Study in Financial Fraud Detection
  98. A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
  99. Accelerating Fleet Upgrade Decisions with Machine-Learning Enhanced Optimization
  100. TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
All 322
  1. NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detection
  2. Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling
  3. LLM-Assisted Cheating Detection in Korean Language via Keystrokes
  4. LLMs Between the Nodes: Community Discovery Beyond Vectors
  5. Neural Autoregressive Modeling of Brain Aging
  6. CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography
  7. Automated Label Placement on Maps via Large Language Models
  8. Unifying Post-hoc Explanations of Knowledge Graph Completions
  9. AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
  10. Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
  11. Meaning-infused grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs
  12. HOG-CNN: Integrating Histogram of Oriented Gradients with Convolutional Neural Networks for Retinal Image Classification
  13. Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items
  14. Promoting Online Safety by Simulating Unsafe Conversations with LLMs
  15. SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
  16. Spatiodynamic inference using vision-based generative modelling
  17. Agent-centric learning: from external reward maximization to internal knowledge curation
  18. Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
  19. Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems
  20. Understanding Concept Drift with Deprecated Permissions in Android Malware Detection
  21. TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction
  22. Explainability-Driven Feature Engineering for Mid-Term Electricity Load Forecasting in ERCOT's SCENT Region
  23. Representation biases: will we achieve complete understanding by analyzing representations?
  24. Intent-Aware Neural Query Reformulation for Behavior-Aligned Product Search
  25. How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
  26. Better Together: Cross and Joint Covariances Enhance Signal Detectability in Undersampled Data
  27. CTG-Insight: A Multi-Agent Interpretable LLM Framework for Cardiotocography Analysis and Classification
  28. The role of media memorability in facilitating startups' access to venture capital funding
  29. Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligence
  30. Temporally Consistent Unsupervised Segmentation for Mobile Robot Perception
  31. Measuring Time-Series Dataset Similarity using Wasserstein Distance
  32. A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models
  33. SourceSplice: Source Selection for Machine Learning Tasks
  34. Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration
  35. Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles
  36. IndoPref: A Multi-Domain Pairwise Preference Dataset for Indonesian
  37. Tiny Noise-Robust Voice Activity Detector for Voice Assistants
  38. Enhancing efficiency in paediatric brain tumour segmentation using a pathologically diverse single-center clinical dataset
  39. Color as the Impetus: Transforming Few-Shot Learner
  40. AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock
  41. Trade-offs in Image Generation: How Do Different Dimensions Interact?
  42. Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?
  43. Posterior Bayesian Neural Networks with Dependent Weights
  44. Scaling and Distilling Transformer Models for sEMG
  45. Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss
  46. Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization
  47. Principled Curriculum Learning using Parameter Continuation Methods
  48. MOVE: Motion-Guided Few-Shot Video Object Segmentation
  49. StepAL: Step-aware Active Learning for Cataract Surgical Videos
  50. MetaLab: Few-Shot Game Changer for Image Recognition
  51. Foundation Models for Demand Forecasting via Dual-Strategy Ensembling
  52. Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
  53. The Interspeech 2025 Speech Accessibility Project Challenge
  54. Weight-Parameterization in Continuous Time Deep Neural Networks for Surrogate Modeling
  55. Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learning
  56. Analysis of Quantum Image Representations for Supervised Classification
  57. Classification of Honey Botanical and Geographical Sources using Mineral Profiles and Machine Learning
  58. ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports
  59. From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
  60. Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images
  61. XAI for Point Cloud Data using Perturbations based on Meaningful Segmentation
  62. Cyst-X: A Multi-Center MRI Benchmark and Federated Learning Framework for Malignancy-Risk Stratification of Pancreatic Cystic Neoplasm
  63. Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform
  64. PHAX: A Structured Argumentation Framework for User-Centered Explainable AI in Public Health and Biomedical Sciences
  65. VeS: Teaching Pixels to Listen Without Supervision
  66. Horseshoe Forests for High-Dimensional Causal Survival Analysis
  67. Bridging Synthetic and Real-World Domains: A Human-in-the-Loop Weakly-Supervised Framework for Industrial Toxic Emission Segmentation
  68. Staining and locking computer vision models without retraining
  69. Higher-Order Kuramoto Oscillator Network for Dense Associative Memory
  70. Preconditioned Discrete-HAMS: A Second-order Irreversible Discrete Sampler
  71. Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models
  72. Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition
  73. EIFNet: Leveraging Event-Image Fusion for Robust Semantic Segmentation
  74. Knowledge Augmentation via Synthetic Data: A Framework for Real-World ECG Image Classification
  75. Thou Shalt Not Prompt: Zero-Shot Human Activity Recognition in Smart Homes via Language Modeling of Sensor Data & Activities
  76. SLA-Centric Automated Algorithm Selection Framework for Cloud Environments
  77. PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction
  78. Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization
  79. Fine-Tuning Code Language Models to Detect Cross-Language Bugs
  80. MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
  81. DeepGo: Predictive Directed Greybox Fuzzing
  82. Contrast-Prior Enhanced Duality for Mask-Free Shadow Removal
  83. Enhancing Generalization in Data-free Quantization via Mixup-class Prompting
  84. Attention-Driven Multimodal Alignment for Long-term Action Quality Assessment
  85. Multi-state Protein Design with DynamicMPNN
  86. Libra: Large Chinese-based Safeguard for AI Content
  87. Vibe Coding as a Reconfiguration of Intent Mediation in Software Development: Definition, Implications, and Research Agenda
  88. SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention
  89. Training language models to be warm and empathetic makes them less reliable and more sycophantic
  90. Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
  91. Predict Patient Self-reported Race from Skin Histological Images
  92. Evaluating Deepfake Detectors in the Wild
  93. Who's important? -- SUnSET: Synergistic Understanding of Stakeholder, Events and Time for Timeline Generation
  94. Reducing Data Requirements for Sequence-Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning
  95. LLM-based Content Classification Approach for GitHub Repositories by the README Files
  96. Cardiovascular Disease Prediction using Machine Learning: A Comparative Analysis
  97. Aether Weaver: Multimodal Affective Narrative Co-Generation with Dynamic Scene Graphs
  98. Data-driven quantum Koopman method for simulating nonlinear dynamics
  99. CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding
  100. Efficient Pain Recognition via Respiration Signals: A Single Cross-Attention Transformer Multi-Window Fusion Pipeline
  101. The Impact of Foundational Models on Patient-Centric e-Health Systems
  102. Multi-Representation Diagrams for Pain Recognition: Integrating Various Electrodermal Activity Signals into a Single Image
  103. Tiny-BioMoE: a Lightweight Embedding Model for Biosignal Analysis
  104. A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data
  105. MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priors
  106. Representations in vision and language converge in a shared, multidimensional space of perceived similarities
  107. VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
  108. Low-Cost Test-Time Adaptation for Robust Video Editing
  109. Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detection
  110. Probabilistic Active Goal Recognition
  111. Discovering Interpretable Ordinary Differential Equations from Noisy Data
  112. Against racing to AGI: Cooperation, deterrence, and catastrophic risks
  113. Analysis of Fourier Neural Operators via Effective Field Theory
  114. Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences
  115. DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework
  116. Modelling Adjectival Modification Effects on Semantic Plausibility
  117. HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs
  118. Overview of ADoBo at IberLEF 2025: Automatic Detection of Anglicisms in Spanish
  119. ChartMark: A Structured Grammar for Chart Annotation
  120. HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
  121. MIBoost: A gradient boosting algorithm for variable selection after multiple imputation
  122. Bayesian Neural Network Surrogates for Bayesian Optimization of Carbon Capture and Storage Operations
  123. Towards White-Box Deep Wireless Sensing
  124. MoDeSuite: Robot Learning Task Suite for Benchmarking Mobile Manipulation with Deformable Objects
  125. Hybrid Causal Identification and Causal Mechanism Clustering
  126. Can large language models assist choice modelling? Insights into prompting strategies and current models' capabilities
  127. Domain Generalization and Adaptation in Intensive Care with Anchor Regression
  128. The Problem with Safety Classification is not just the Models
  129. AU-LLM: Micro-Expression Action Unit Detection via Enhanced LLM-Based Feature Fusion
  130. AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
  131. Proposing a Semantic Movie Recommendation System Enhanced by ChatGPT's NLP Results
  132. Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networks
  133. TempRe: Template generation for single and direct multi-step retrosynthesis
  134. IMC-Net: A Lightweight Content-Conditioned Encoder with Multi-Pass Processing for Image Classification
  135. Unified machine-learning framework for property prediction and time-evolution simulation of strained alloy microstructure
  136. LiteFat: Lightweight Spatio-Temporal Graph Learning for Real-Time Driver Fatigue Detection
  137. SAT-Based Bounded Fitting for the Description Logic ALC
  138. Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
  139. Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
  140. evoxels: A differentiable physics framework for voxel-based microstructure simulations
  141. Adversarial Reconstruction Feedback for Robust Fine-grained Generalization
  142. MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces
  143. SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking
  144. Generalized few-shot transfer learning architecture for modeling the EDFA gain spectrum
  145. GDAIP: A Graph-Based Domain Adaptive Framework for Individual Brain Parcellation
  146. Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning
  147. Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations
  148. Data-Driven Extended Corresponding State Approach for Residual Property Prediction of Hydrofluoroolefins
  149. Impact of Underwater Image Enhancement on Feature Matching
  150. An Equal-Probability Partition of the Sample Space: A Non-parametric Inference from Finite Samples
  151. PREIG: Physics-informed and Reinforcement-driven Interpretable GRU for Commodity Demand Forecasting
  152. EnTao-GPM: DNA Foundation Model for Predicting the Germline Pathogenic Mutations
  153. Unrolling Dynamic Programming via Graph Filters
  154. Towards a Large Physics Benchmark
  155. MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios
  156. diffSPH: Differentiable Smoothed Particle Hydrodynamics for Adjoint Optimization and Machine Learning
  157. Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantification
  158. Automated Detection of Antarctic Benthic Organisms in High-Resolution In Situ Imagery to Aid Biodiversity Monitoring
  159. Can the current trends of AI handle a full course of mathematics?
  160. AI Literacy as a Key Driver of User Experience in AI-Powered Assessment: Insights from Socratic Mind
  161. DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs
  162. The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
  163. Hyperbolic Genome Embeddings
  164. Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
  165. GUARD-CAN: Graph-Understanding and Recurrent Architecture for CAN Anomaly Detection
  166. Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics
  167. "Teammates, Am I Clear?": Analysing Legible Behaviours in Teams
  168. Edge Selection for the Effective use of Piecewise-Constant Distributions as Neural Network Outputs for Event Prediction
  169. Wind Turbine Feature Detection Using Deep Learning and Synthetic Data
  170. Multilingual JobBERT for Cross-Lingual Job Title Matching
  171. Semantic Segmentation of iPS Cells: Case Study on Model Complexity in Biomedical Imaging
  172. Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking
  173. Hierarchical Graph Neural Network for Compressed Speech Steganalysis
  174. Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems
  175. Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
  176. Emerging Trends in Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation with Image-Level Supervision
  177. LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation
  178. Finding Uncommon Ground: A Human-Centered Model for Extrospective Explanations
  179. Structured quantum learning via em algorithm for Boltzmann machines
  180. RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors
  181. VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
  182. Transformers over-extend what humans underlearn: the case of Spanish L-shaped morphome
  183. Multi-View Reconstruction with Global Context for 3D Anomaly Detection
  184. Sun sensor calibration algorithms: A systematic mapping and survey
  185. Construction and educational application of a linguistically grounded dependency treebank for Uyghur
  186. Automatic Classification of User Requirements from Online Feedback -- A Replication Study
  187. Hierarchical Stochastic Differential Equation Models for Latent Manifold Learning in Neural Time Series
  188. Suppressing Gradient Conflict for Generalizable Deepfake Detection
  189. Accelerating Prefilling via Decoding-time Contribution Sparsity
  190. Large Language Models for Wireless Communications: From Adaptation to Autonomy
  191. ST-GDance: Long-Term and Collision-Free Group Choreography from Music
  192. ST-DAI: Single-shot 2.5D Spatial Transcriptomics with Intra-Sample Domain Adaptive Imputation for Cost-efficient 3D Reconstruction
  193. Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  194. VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding
  195. Large Language Models for Supply Chain Decisions
  196. VN-MTEB: Vietnamese Massive Text Embedding Benchmark
  197. Multifunctional physical reservoir computing in soft tensegrity robots
  198. Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval
  199. Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess
  200. Stochastic forest transition model dynamics and parameter estimation via deep learning
  201. HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions
  202. NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples
  203. Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
  204. Capacity-Constrained Continual Learning
  205. Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
  206. LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning
  207. An Angular-Temporal Interaction Network for Light Field Object Tracking in Low-Light Scenes
  208. Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation
  209. Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation
  210. From Global to Local: A Scalable Benchmark for Local Posterior Sampling
  211. Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations
  212. Dual Cross-image Semantic Consistency with Self-aware Pseudo Labeling for Semi-supervised Medical Image Segmentation
  213. Evo-DKD: Dual-Knowledge Decoding for Autonomous Ontology Evolution in Large Language Models
  214. PVD-ONet: A Multi-scale Neural Operator Method for Singularly Perturbed Boundary Layer Problems
  215. Copula Discrepancy: Benchmarking Dependence Structure
  216. Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviour
  217. From Sublinear to Linear: Local Convergence in Finite-Width Networks via Locally Polyak-Lojasiewicz Regions
  218. MapDiffusion: Generative Diffusion for Vectorized Online HD Map Construction and Uncertainty Estimation in Autonomous Driving
  219. GraphTorque: Torque-Driven Rewiring Graph Neural Network
  220. GovRelBench:A Benchmark for Government Domain Relevance
  221. Data Leakage and Redundancy in the LIT-PCBA Benchmark
  222. Sync-TVA: A Graph-Attention Framework for Multimodal Emotion Recognition with Cross-Modal Fusion