mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 22 Apr 2025

275 papers

  1. DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion AlignmentWorld models → World models for autonomous driving +1
  2. WASP: Benchmarking Web Agent Security Against Prompt Injection AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  3. DIFFRACT: Diffusion-based Restoration via Adaptive Control and Thresholding for Diffraction ImagingDiffusion models → Inverse problems and image restoration
  4. Improving Automated Secure Code Reviews: A Synthetic Dataset for Code Vulnerability FlawsSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  5. Learning Explainable Dense Reward Shapes via Bayesian OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. A Geometric Approach to Problems in Optimization and Data ScienceLLM safety and security → Backdoor and data poisoning attacks
  7. PRIMETIME : Limits of LLMs in Temporal PrimitivesLLM reasoning → Knowledge- and tool-augmented reasoning
  8. TTRL: Test-Time Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  9. MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse AttentionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  10. Survey of Video Diffusion Models: Foundations, Implementations, and ApplicationsDiffusion models → Video generation
  11. From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection TuningDiffusion models → Image generation, text-to-image and editing
  12. LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making AbilitiesLLM agents and tool use → Reinforcement learning for LLM agents
  13. PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  14. Guiding VLM Agents with Process Rewards at Inference Time for GUI NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  15. Describe Anything: Detailed Localized Image and Video CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  16. Boosting Generative Image Modeling via Joint Image-Feature SynthesisDiffusion models → Diffusion foundations and sampling
  17. Vision language models are unreliable at trivial spatial cognitionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  18. Vision-Language Models Are Not Pragmatically Competent in Referring Expression GenerationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and ExplainabilityKnowledge distillation → Knowledge distillation for LLMs
  20. π0.5: a Vision-Language-Action Model with Open-World GeneralizationVision-language-action models → Generalist VLA models and benchmarks
  21. LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field EnlargementState-space sequence models (S4, Mamba) → Core SSM architectures for language
  22. Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  23. Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical FrameworkDiffusion models → Video generation
  24. MVQA: Mamba with Unified Sampling for Efficient Video Quality AssessmentState-space sequence models (S4, Mamba) → Vision Mamba backbones
  25. Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning EfficiencyLLM reasoning → Reasoning for agents, planning and code
  26. Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement LearningLLM reasoning → Multimodal reasoning
  27. Meta-Entity Driven Triplet Mining for Aligning Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  28. Towards Test Generation from Task Description for Mobile Testing with Multi-modal ReasoningLLM reasoning → Multimodal reasoning
  29. Synergizing RAG and Reasoning: A Systematic ReviewLLM reasoning → Knowledge- and tool-augmented reasoning +1
  30. Impact of Noise on LLM-Models Performance in Abstraction and Reasoning Corpus (ARC) Tasks with Model Temperature ConsiderationsLLM reasoning → Reasoning benchmarks and evaluation
  31. SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement LearningLLM reasoning → Audio-language model reasoning
  32. Dynamic Early Exit in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  33. Bidirectional Task-Motion Planning Based on Hierarchical Reinforcement Learning for Strategic ConfrontationDeep reinforcement learning methods → RL for robot navigation and UAV control
  34. Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference ModelLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  35. Text-based Animatable 3D Avatars with Morphable Model AlignmentDiffusion models → 3D, point cloud and scene generation
  36. DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual OptimizersLLM safety and security → Machine unlearning
  37. Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench FeedbackLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  38. A closer look at how large language models trust humans: patterns and biasesLLM agents and tool use → Social simulation and multi-agent debate
  39. FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented GenerationRetrieval-augmented generation → Legal and financial RAG
  40. WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM AgentsWorld models → World models for language agents +1
  41. TrustGeoGen: Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem SolvingLLM reasoning → Spatial and embodied reasoning
  42. Tina: Tiny Reasoning Models via LoRALLM reasoning → Test-time compute and efficient thinking
  43. Clifford Group Equivariant Diffusion Models for 3D Molecular GenerationDiffusion models → Flow matching, time series and science
  44. Observability conditions for neural state-space models with eigenvalues and their roots of unityState-space sequence models (S4, Mamba) → Core SSM architectures for language
  45. CaRoSaC: A Reinforcement Learning-Based Kinematic Control of Cable-Driven Parallel Robots by Addressing Cable Sag through SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  46. Structure-Preserving Zero-Shot Image Editing via Stage-Wise Latent Injection in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  47. Implementing Rational Choice Functions with LLMs and Measuring their Alignment with User PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  48. DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  49. Advancing Embodied Agent Security: From Safety Benchmarks to Input ModerationLLM agents and tool use → Agent threats, guardrails and governance
  50. The Viability of Crowdsourcing for RAG EvaluationRetrieval-augmented generation → RAG pipeline design and evaluation
  51. Vidi: Large Multimodal Models for Video Understanding and EditingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  52. Policy-Based Radiative Transfer: Solving the 2-Level Atom Non-LTE Problem using Soft Actor-Critic Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  53. UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  54. DiTPainter: Efficient Video Inpainting with Diffusion TransformersDiffusion models → 3D, point cloud and scene generation
  55. Enhancing Reinforcement learning in 3-Dimensional Hydrophobic-Polar Protein Folding Model with Attention-based layersDeep reinforcement learning methods → RL for energy, networks and operations
  56. CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation CorrectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  57. ZeroSlide: Is Zero-Shot Classification Adequate for Lifelong Learning in Whole-Slide Image Analysis in the Era of Pathology Vision-Language Foundation Models?Multimodal LLMs / vision-language models → Medical vision-language models
  58. FaceInsight: A Multimodal Large Language Model for Face PerceptionMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  59. RadioDiff-k2: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map ConstructionDiffusion models → Diffusion for compression and wireless
  60. AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  61. HS-Mamba: Full-Field Interaction Multi-Groups Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  62. Grasping Deformable Objects via Reinforcement Learning with Cross-Modal Attention to Visuo-Tactile InputsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  63. A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and DeploymentLLM reasoning → Reasoning for agents, planning and code +2
  64. Instruction-Tuning Data Synthesis from Scratch via Web ReconstructionSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  65. SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  66. A Multi-Agent Framework for Automated Qinqiang Opera Script Generation Using Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
  67. LLM-based Semantic Augmentation for Harmful Content DetectionLLM safety and security → Safety alignment, refusal and guardrails
  68. Compass-V2 Technical ReportMixture-of-experts → MoE large language models
  69. Few-Shot Vision-Language Action-Incremental Policy LearningVision-language-action models → Reinforcement learning and post-training
  70. InstaRevive: One-Step Image Enhancement via Dynamic Score MatchingDiffusion models → Diffusion foundations and sampling
  71. T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video ModelsLLM safety and security → Vision-language and text-to-image safety
  72. Understanding Financial Reasoning in AI: A Multimodal Benchmark and Error Learning Approach
  73. Sentiment Analysis in Software Engineering: Evaluating Generative Pre-trained Transformers
  74. Cryptogenic stroke and migraine: using probabilistic independence and machine learning to uncover latent sources of disease from the electronic health record
  75. Enhancing TCR-Peptide Interaction Prediction with Pretrained Language Models and Molecular Representations
  76. Manifold-Constrained Sentence Embeddings via Triplet Loss: Projecting Semantics onto Spheres, Tori, and M"obius Strips
  77. Performance Evaluation of Emotion Classification in Japanese Using RoBERTa and DeBERTa
  78. ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees
  79. Context-Enhanced Contrastive Search for Improved LLM Text Generation
  80. Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations
  81. Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
  82. BELL: Benchmarking the Explainability of Large Language Models
  83. Intelligent Detection of Non-Essential IoT Traffic on the Home Gateway
  84. Residual-Evasive Attacks on ADMM in Distributed Optimization
  85. Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes
  86. CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss
  87. Object Learning and Robust 3D Reconstruction
  88. OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
  89. SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos
  90. Research on Cloud Platform Network Traffic Monitoring and Anomaly Detection System based on Large Language Models
  91. GeneMamba: An Efficient and Effective Foundation Model on Single Cell Data
  92. PCF-Grasp: Converting Point Completion to Geometry Feature to Enhance 6-DoF Grasp
  93. Semantics at an Angle: When Cosine Similarity Works Until It Doesn't
  94. On the Consistency of GNN Explanations for Malware Detection
  95. SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space
  96. Capturing Symmetry and Antisymmetry in Language Models through Symmetry-Aware Training Objectives
  97. Regularizing Differentiable Architecture Search with Smooth Activation
  98. MetaHarm: Harmful YouTube Video Dataset Annotated by Domain Experts, GPT-4-Turbo, and Crowdworkers
  99. Naturally Computed Scale Invariance in the Residual Stream of ResNet18
  100. The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translation
All 275
  1. Affect Models Have Weak Generalizability to Atypical Speech
  2. DataS^3: Dataset Subset Selection for Specialization
  3. An Automated Pipeline for Few-Shot Bird Call Classification: A Case Study with the Tooth-Billed Pigeon
  4. Quantum Doubly Stochastic Transformers
  5. From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage
  6. The Language of Attachment: Modeling Attachment Dynamics in Psychotherapy
  7. COBRA: Algorithm-Architecture Co-optimized Binary Transformer Accelerator for Edge Inference
  8. Boosting KNNClassifier Performance with Opposition-Based Data Transformation
  9. TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs
  10. CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents
  11. Gradient-Optimized Fuzzy Classifier: A Benchmark Study Against State-of-the-Art Models
  12. Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching
  13. FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness
  14. DeepCS-TRD, a Deep Learning-based Cross-Section Tree Ring Detector
  15. General Post-Processing Framework for Fairness Adjustment of Machine Learning Models
  16. Comprehensive Evaluation of Quantitative Measurements from Automated Deep Segmentations of PSMA PET/CT Images
  17. Using Phonemes in cascaded S2S translation pipeline
  18. Towards a Distributed Federated Learning Aggregation Placement using Particle Swarm Intelligence
  19. Blockchain Meets Adaptive Honeypots: A Trust-Aware Approach to Next-Gen IoT Security
  20. Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs
  21. TinyML for Speech Recognition
  22. HTN Plan Repair Algorithms Compared: Strengths and Weaknesses of Different Methods
  23. Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Design
  24. Quality of explanation of xAI from the prespective of Italian end-users: Italian version of System Causability Scale (SCS)
  25. Probabilistic Emulation of the Community Radiative Transfer Model Using Machine Learning
  26. FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking
  27. Behavior of prediction performance metrics with rare events
  28. CLIP-IT: CLIP-based Pairing for Histology Images Classification
  29. FPGA-Based Neural Network Accelerators for Space Applications: A Survey
  30. Physics-Informed Inference Time Scaling for Solving High-Dimensional PDE via Defect Correction
  31. A detection-task-specific deep-learning method to improve the quality of sparse-view myocardial perfusion SPECT images
  32. Leveraging Social Media Analytics for Sustainability Trend Detection in Saudi Arabias Evolving Market
  33. Heterogeneous networks in drug-target interaction prediction
  34. Classification of Firn Data via Topological Features
  35. Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room
  36. Progressive Language-guided Visual Learning for Multi-Task Visual Grounding
  37. Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs
  38. A Statistical Approach for Synthetic EEG Data Generation
  39. A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation
  40. Deep Learning Meets Process-Based Models: A Hybrid Approach to Agricultural Challenges
  41. SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures
  42. Enhancing Trust Through Standards: A Comparative Risk-Impact Framework for Aligning ISO AI Standards with Global Ethical and Regulatory Contexts
  43. MR. Video: "MapReduce" is the Principle for Long Video Understanding
  44. Explainable Unsupervised Anomaly Detection with Random Forest
  45. High-performance training and inference for deep equivariant interatomic potentials
  46. Free Access to World News: Reconstructing Full-Text Articles from GDELT
  47. ForesightNav: Learning Scene Imagination for Efficient Exploration
  48. Certified Mitigation of Worst-Case LLM Copyright Infringement
  49. Approximate matrices of systems of max-min fuzzy relational equations
  50. Muon Optimizer Accelerates Grokking
  51. LLMs meet Federated Learning for Scalable and Secure IoT Management
  52. LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
  53. Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3
  54. Trends in AI Supercomputers
  55. PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
  56. Navigating the State of Cognitive Flow: Context-Aware AI Interventions for Effective Reasoning Support
  57. AlphaGrad: Non-Linear Gradient Normalization Optimizer
  58. The Formation of Production Networks: How Supply Chains Arise from Simple Learning with Minimal Information
  59. Methods for Recognizing Nested Terms
  60. CAPO: Cost-Aware Prompt Optimization
  61. How Private is Your Attention? Bridging Privacy with In-Context Learning
  62. OPUS-VFL: Incentivizing Optimal Privacy-Utility Tradeoffs in Vertical Federated Learning
  63. Benchmarking machine learning models for predicting aerofoil performance
  64. Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications
  65. Few-shot Hate Speech Detection Based on the MindSpore Framework
  66. W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
  67. Efficient Discovery of Motif Transition Process for Large-Scale Temporal Graphs
  68. A New Graph Grammar Formalism for Robust Syntactic Pattern Recognition
  69. Bug Destiny Prediction in Large Open-Source Software Repositories through Sentiment Analysis and BERT Topic Modeling
  70. Recent Advances and Future Directions in Extended Reality (XR): Exploring AI-Powered Spatial Intelligence
  71. FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
  72. Universal Approximation with Softmax Attention
  73. Visual Place Cell Encoding: A Computational Model for Spatial Representation and Cognitive Mapping
  74. Adversarial Observations in Weather Forecasting
  75. FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity
  76. Low-Rank Adaptation of Neural Fields
  77. Benchmarking the Reproducibility of Brain MRI Segmentation Across Scanners and Time
  78. StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
  79. Clinician-Friendly Foundation Models for Ophthalmic Image Diagnostics without Fine-Tuning or Technical Barriers
  80. New Recipe for Semi-supervised Community Detection: Clique Annealing under Crystallization Kinetics
  81. Achieving Distributive Justice in Federated Learning via Uncertainty Quantification
  82. ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting
  83. ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
  84. Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions
  85. Automated Bug Report Prioritization in Large Open-Source Projects
  86. GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network
  87. RaSCL: Radar to Satellite Crossview Localization
  88. SUPRA: Subspace Parameterized Attention for Neural Operator on General Domains
  89. Supporting Data-Frame Dynamics in AI-assisted Decision Making
  90. MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction
  91. Integrating Non-Linear Radon Transformation for Diabetic Retinopathy Grading
  92. MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search
  93. DERD-Net: Learning Depth from Event-based Ray Densities
  94. Consistent Causal Inference of Group Effects in Non-Targeted Trials with Finitely Many Effect Levels
  95. Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis
  96. CARE: Compatibility-Aware Incentive Mechanisms for Federated Learning with Budgeted Requesters
  97. Adaptive PCA-Based Outlier Detection for Multi-Feature Time Series in Space Missions
  98. Generative AI for Research Data Processing: Lessons Learnt From Three Use Cases
  99. Full waveform inversion with CNN-based velocity representation extension
  100. Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models
  101. What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns
  102. Fusing Reward and Dueling Feedback in Stochastic Bandits
  103. DAE-KAN: A Kolmogorov-Arnold Network Model for High-Index Differential-Algebraic Equations
  104. Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness
  105. Development and evaluation of a deep learning algorithm for German word recognition from lip movements
  106. Crisp complexity of fuzzy classifiers
  107. Satellite to GroundScape -- Large-scale Consistent Ground View Generation from Satellite Views
  108. Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach
  109. Towards prediction of morphological heart age from computed tomography angiography
  110. Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos
  111. Shannon invariants: A scalable approach to information decomposition
  112. Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering
  113. ORION Grounded in Context: Retrieval-Based Method for Hallucination Detection
  114. Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection
  115. Dynamic Intent Queries for Motion Transformer-based Trajectory Prediction
  116. DSDNet: Raw Domain Demoir'eing via Dual Color-Space Synergy
  117. Markov Kernels, Distances and Optimal Control: A Parable of Linear Quadratic Non-Gaussian Distribution Steering
  118. GADS: A Super Lightweight Model for Head Pose Estimation
  119. iMedic: Towards Smartphone-based Self-Auscultation Tool for AI-Powered Pediatric Respiratory Assessment
  120. Riemannian Neural Geodesic Interpolant
  121. SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems
  122. Collaborative Split Federated Learning with Parallel Training and Aggregation
  123. From predictions to confidence intervals: an empirical study of conformal prediction methods for in-context learning
  124. RePOPE: Impact of Annotation Errors on the POPE Benchmark
  125. You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection
  126. Transfer Learning for High-dimensional Reduced Rank Time Series Models
  127. Subject islands do not reduce to construction-specific discourse function
  128. Invariant Learning with Annotation-free Environments
  129. FinTextSim: Enhancing Financial Text Analysis with BERTopic
  130. TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  131. Preprint: Exploring Inevitable Waypoints for Unsolvability Explanation in Hybrid Planning Problems
  132. Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg
  133. Motion-Enhanced Nonlocal Similarity Implicit Neural Representation for Infrared Dim and Small Target Detection
  134. An XAI-based Analysis of Shortcut Learning in Neural Networks
  135. FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning
  136. VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
  137. Neural Kinematic Bases for Fluids
  138. A Vision-Enabled Prosthetic Hand for Children with Upper Limb Disabilities
  139. AffordanceSAM: Segment Anything Once More in Affordance Grounding
  140. RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
  141. Computational Typology
  142. Cequel: Cost-Effective Querying of Large Language Models for Text Clustering
  143. DR.FIX: Automatically Fixing Data Races at Industry Scale
  144. A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection
  145. Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement
  146. SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
  147. Dimension-Free Decision Calibration for Nonlinear Loss Functions
  148. Learning Dynamic Graphs via Tensorized and Lightweight Graph Convolutional Networks
  149. Fine-Tuning a 7B Advisor on Free-Tier GPUs: An Adapter-Handoff Recipe and a Synthetic-Data Reliability Caution
  150. SonarT165: A Large-scale Benchmark and STFTrack Framework for Acoustic Object Tracking
  151. Exploring Next Token Prediction in Theory of Mind (ToM) Tasks: Comparative Experiments with GPT-2 and LLaMA-2 AI Models
  152. Multi-Modal Fusion of In-Situ Video Data and Process Parameters for Online Forecasting of Cookie Drying Readiness
  153. Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
  154. MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design
  155. Smooth Calibration and Decision Making
  156. On the Price of Differential Privacy for Hierarchical Clustering
  157. Real-Time Optimal Design of Experiment for Parameter Identification of Li-Ion Cell Electrochemical Model
  158. State-Aware IoT Scheduling Using Deep Q-Networks and Edge-Based Coordination
  159. OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research
  160. Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis
  161. Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
  162. A Framework for Testing and Adapting REST APIs as LLM Tools
  163. VLM-based Prompts as the Optimal Assistant for Unpaired Histopathology Virtual Staining
  164. llm-jp-modernbert: A ModernBERT Model Trained on a Large-Scale Japanese Corpus with Long Context Length
  165. Bayesian model-averaging stochastic item selection for adaptive testing
  166. RiskNet: Interaction-Aware Risk Forecasting for Autonomous Driving in Long-Tail Scenarios
  167. Interpretable Deep Learning for Polar Mechanistic Reaction Prediction
  168. Federated Latent Factor Learning for Recovering Wireless Sensor Networks Signal with Privacy-Preserving
  169. IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property
  170. The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks
  171. Transport f divergences
  172. SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
  173. Guillotine: Hypervisors for Isolating Malicious AIs
  174. Scalable APT Malware Classification via Parallel Feature Extraction and GPU-Accelerated Learning
  175. Fluorescence Reference Target Quantitative Analysis Library