mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 5 Sep 2025

248 papers

  1. Pre-Forgettable Models: Prompt Learning as a Native Mechanism for UnlearningLLM safety and security → Machine unlearning
  2. DualAlign: Generating Clinically Grounded Synthetic DataSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  3. FinXplore: An Adaptive Deep Reinforcement Learning Framework for Balancing and Discovering Investment OpportunitiesDeep reinforcement learning methods → Adversarial robustness and RL in finance
  4. Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of ExpertsMixture-of-experts → Expert routing strategies
  5. CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation BackdoorLLM safety and security → Watermarking generated content and models
  6. Learning-Based Planning for Improving Science Return of Earth Observation SatellitesOffline RL and imitation learning from data → Imitation learning methods
  7. DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model TrainingLLM reasoning → Reinforcement learning for reasoning +1
  8. OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  9. Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG)Retrieval-augmented generation → Medical and biomedical RAG
  10. Self-Aligned Reward: Towards Effective and Efficient ReasonersLLM reasoning → Reinforcement learning for reasoning
  11. MambaLite-Micro: Memory-Optimized Mamba Inference on MCUsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  12. Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language ModelsLLM safety and security → Jailbreaking
  13. Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern AnalysisLLM safety and security → Membership inference attacks
  14. RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  15. Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent DebateLLM reasoning → Reasoning for agents, planning and code +1
  16. Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at PinterestDeep reinforcement learning methods → RL training of language and agent models
  17. Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari BenchmarksDeep reinforcement learning methods → RL for energy, networks and operations
  18. LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World GenerationWorld models → Video-generation world models and simulators +1
  19. COGITAO: A Visual Reasoning Framework To Study Compositionality & GeneralizationLLM reasoning → Multimodal reasoning
  20. CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language ModelsLLM safety and security → Machine unlearning
  21. Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought DistillationLLM reasoning → Test-time compute and efficient thinking
  22. Robust Model Predictive Control Design for Autonomous Vehicles with Perception-based ObserversEnd-to-end autonomous driving → End-to-end system architecture
  23. Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
  24. AI Agents for Web Testing: A Case Study in the WildLLM agents and tool use → Web, search, and research agents
  25. Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  26. KVCompose: Efficient Structured KV Cache Compression with Composite TokensEfficient LLM inference and serving → KV cache optimization
  27. VLSM-Ensemble: Ensembling CLIP-based Vision-Language Models for Enhanced Medical Image SegmentationMultimodal LLMs / vision-language models → Medical vision-language models
  28. Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts LayersMixture-of-experts → Vision mixture-of-experts
  29. Masked Diffusion Language Models with Frequency-Informed TrainingDiffusion models → Discrete and text diffusion
  30. Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling FrameworkLLM reasoning → Test-time compute and efficient thinking
  31. FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow PoliciesVision-language-action models → Generalist VLA models and benchmarks
  32. LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal CollaborationLLM agents and tool use → Agentic AI for wireless networks
  33. Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking AgentsLLM reasoning → Reasoning for agents, planning and code +1
  34. Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  35. DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  36. SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and ParsingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  37. Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learningDeep reinforcement learning methods → RL for clinical treatment and surgery
  38. OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Cloning a Conversational Voice AI Agent from Call,Recording Datasets for TelesalesLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain ImagingDiffusion models → Inverse problems and image restoration
  41. A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert RoutingDiffusion models → Diffusion and flow policies for robotics +2
  42. REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-ExpertsMixture-of-experts → Multimodal MoE models
  43. VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space RoutingEfficient LLM inference and serving → Serving systems and request scheduling
  44. Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-ResolutionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  45. AFD-SLU: Adaptive Feature Distillation for Spoken Language UnderstandingKnowledge distillation → Speech and audio distillation
  46. Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented GenerationRetrieval-augmented generation → Legal and financial RAG
  47. Extracting Uncertainty Estimates from Mixtures of Experts for Semantic SegmentationMixture-of-experts → Vision mixture-of-experts
  48. An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  49. TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  50. SemSteDiff: Generative Diffusion Model-based Coverless Semantic Steganography CommunicationDiffusion models → Robustness, privacy and adversarial aspects
  51. Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action GraphsLLM agents and tool use → Agent threats, guardrails and governance +1
  52. Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic TrainingSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  53. Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream EffectsLLM agents and tool use → Social simulation and multi-agent debate
  54. What-If Analysis of Large Language Models: Explore the Game World Using Proactive ThinkingLLM reasoning → Reasoning for agents, planning and code
  55. SePA: A Search-enhanced Predictive Agent for Personalized Health CoachingRetrieval-augmented generation → Medical and biomedical RAG +1
  56. WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music ReasoningLLM reasoning → Audio-language model reasoning +1
  57. Imitation Learning Based on Disentangled Representation Learning of Behavioral CharacteristicsOffline RL and imitation learning from data → Robot manipulation imitation learning
  58. Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied AgentsWorld models → World models for language agents +1
  59. CD-Mamba: Cloud detection with long-range spatial dependency modelingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  60. Spatio-Temporal Parallelism for Diffusion Model Inference on Heterogeneous Multi-GPU SystemsDiffusion models → Diffusion foundations and sampling
  61. KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  62. A Comparison of Surrogate Constitutive Models for Viscoplastic Creep Simulation of HT-9 Steel
  63. Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui fires
  64. An Analytical and AI-discovered Stable, Accurate, and Generalizable Subgrid-scale Closure for Geophysical Turbulence
  65. Graph-Based Spatio-temporal Attention and Multi-Scale Fusion for Clinically Interpretable, High-Fidelity Fetal ECG Extraction
  66. A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks
  67. Discovering Software Parallelization Points Using Deep Neural Networks
  68. TripOptimizer: Generative 3D Shape Optimization and Drag Prediction using Triplane VAE Networks
  69. Ratio1 -- AI meta-OS
  70. Accelerating Privacy-Preserving Federated Learning in Large-Scale LEO Satellite Systems
  71. On Using Large-Batches in Federated Learning
  72. Contextuality, Holonomy and Discrete Fiber Bundles in Group-Valued Boltzmann Machines
  73. Semantic-guided LoRA Parameters Generation
  74. Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings
  75. Crystal Systems Classification of Phosphate-Based Cathode Materials Using Machine Learning for Lithium-Ion Battery
  76. LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm
  77. Differential Robustness in Transformer Language Models: Empirical Evaluation Under Adversarial Text Attacks
  78. The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks
  79. Temporal Preferences in Language Models for Long-Horizon Assistance
  80. Creativity Benchmark: A benchmark for marketing creativity for large language models
  81. Bilingual Word Level Language Identification for Omotic Languages
  82. veScale: Consistent and Efficient Tensor Programming with Eager-Mode SPMD
  83. DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation
  84. Cryo-EM as a Stochastic Inverse Problem
  85. Combining TSL and LLM to Automate REST API Testing: A Comparative Study
  86. Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting
  87. Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
  88. Causal Multi-fidelity Surrogate Forward and Inverse Models for ICF Implosions
  89. Real-time autonomous magnetic microrobot navigation across dynamic and biologically relevant environments
  90. An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures
  91. The Token Tax: Systematic Bias in Multilingual Tokenization
  92. Prior Distribution and Model Confidence
  93. From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics
  94. Veriserum: A dual-plane fluoroscopic dataset with knee implant phantoms for deep learning in medical imaging
  95. STL-based Optimization of Biomolecular Neural Networks for Regression and Control
  96. PLanTS: Periodicity-aware Latent-state Representation Learning for Multivariate Time Series
  97. Learning Tool-Aware Adaptive Compliant Control for Autonomous Regolith Excavation
  98. From Vision to Validation: A Theory- and Data-Driven Construction of a GCC-Specific AI Adoption Index
  99. From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation
  100. Calibrated Recommendations with Contextual Bandits
All 248
  1. Newton to Einstein: Axiom-Based Discovery via Game Design
  2. Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks (Journal Version)
  3. Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's
  4. Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details
  5. Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too
  6. Advanced Brain Tumor Segmentation Using EMCAD: Efficient Multi-scale Convolutional Attention Decoding
  7. Safeguarding Graph Neural Networks against Topology Inference Attacks
  8. No Text Needed: Forecasting MT Quality and Inequity from Fertility and Metadata
  9. Graph Connectionist Temporal Classification for Phoneme Recognition
  10. Unmasking COVID-19 Vulnerability in Nigeria: Mapping Risks Beyond Urban Hotspots
  11. Reverse Browser: Vector-Image-to-Code Generator
  12. Inferring Prerequisite Knowledge Concepts in Educational Knowledge Graphs: A Multi-criteria Approach
  13. An Optimized Pipeline for Automatic Educational Knowledge Graph Construction
  14. Authorship Without Writing: Large Language Models and the Senior Author Analogy
  15. Augmented Structure Preserving Neural Networks for cell biomechanics
  16. A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs
  17. User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies
  18. FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
  19. WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
  20. Non-Termination Proving: 100 Million LoC and Beyond
  21. Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
  22. Beyond Linearity and Time-Homogeneity: Relational Hyper Event Models with Time-Varying Non-Linear Effects
  23. Learning to accelerate distributed ADMM using graph neural networks
  24. Elucidating the Design Space of Decay in Linear Attention
  25. Dual-Branch Convolutional Framework for Spatial and Frequency-Based Image Forgery Detection
  26. SpikingBrain: Spiking Brain-inspired Large Models
  27. On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
  28. Glass-Box Deep Learning for FDIA Detection in Nonlinear Automatic Generation Control: A Kolmogorov-Arnold Network Approach
  29. Scaling Performance of Large Language Model Pretraining
  30. Recomposer: Event-roll-guided generative audio editing
  31. Uniform Information Density and Syntactic Reduction: Revisiting textitthat-Mentioning in English Complement Clauses
  32. Deep Learning-Enhanced for Amine Emission Monitoring and Performance Analysis in Industrial Carbon Capture Plants
  33. Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
  34. HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models
  35. BEDTime: A Unified Benchmark for Automatically Describing Time Series
  36. An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
  37. Hunyuan-MT Technical Report
  38. Symbolic Graphics Programming with Large Language Models
  39. RapidGNN: Energy and Communication-Efficient Distributed Training on Large-Scale Graph Neural Networks
  40. Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
  41. Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
  42. SSL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
  43. Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
  44. Room-acoustic simulations as an alternative to measurements for audio-algorithm evaluation
  45. PRIM: Towards Practical In-Image Multilingual Machine Translation
  46. Exploring Situated Stabilities of a Rhythm Generation System through Variational Cross-Examination
  47. SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
  48. Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
  49. Evaluation and Comparison Semantics for ODRL
  50. On the Learnability of Distribution Classes with Adaptive Adversaries
  51. A Scalable Attention-Based Approach for Image-to-3D Texture Mapping
  52. The Advantage of Fine-Grained Training
  53. Efficient Exact Resistance Distance Computation on Small-Treewidth Graphs: a Labelling Approach
  54. HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
  55. GenAI-based test case generation and execution in SDV platform
  56. Spectral Algorithms in Misspecified Regression: Convergence under Covariate Shift
  57. ICR: Iterative Clarification and Rewriting for Conversational Search
  58. Semi-supervised Deep Transfer for Regression without Domain Alignment
  59. ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
  60. Recurrent State Encoders for Efficient Neural Combinatorial Optimization
  61. Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
  62. Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
  63. GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting
  64. Finding your MUSE: Mining Unexpected Solutions Engine
  65. Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction
  66. ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions
  67. Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
  68. QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
  69. Dynamical Learning in Deep Asymmetric Recurrent Neural Networks
  70. ModalSurv: Investigating opportunities and limitations of multimodal deep survival learning in prostate and bladder cancer
  71. Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization
  72. Pointing-Guided Target Estimation via Transformer-Based Attention
  73. LUIVITON: Learned Universal Interoperable VIrtual Try-ON
  74. Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition
  75. Depth-Aware Initialization for Stable and Efficient Neural Network Training
  76. On approximating the f-divergence between two Ising models
  77. A biologically inspired separable learning vision model for real-time traffic object perception in Dark
  78. Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
  79. Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study
  80. Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
  81. Adversarial Augmentation and Active Sampling for Robust Cyber Anomaly Detection
  82. Directed Evolution of Proteins via Bayesian Optimization in Embedding Space
  83. A Mechanism-Coupled Split Window Network for Medium- to High-Resolution Land Surface Temperature Retrieval
  84. Exploring an implementation of quantum learning pipeline for support vector machines
  85. Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
  86. MAIA: An Inpainting-Based Approach for Music Adversarial Attacks
  87. Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
  88. Classification of kinetic-related injury in hospital triage data using NLP
  89. Neuro-Spectral Architectures for Causal Physics-Informed Networks
  90. On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
  91. Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
  92. Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
  93. Towards an Accurate and Effective Robot Vision (The Problem of Topological Localization for Mobile Robots)
  94. Ontology-Aligned Embeddings for Data-Driven Labour Market Analytics
  95. UniView: Enhancing Novel View Synthesis From A Single Image By Unifying Reference Features
  96. Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts
  97. A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection
  98. Artificial intelligence for representing and characterizing quantum systems
  99. Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
  100. Optimal Variance and Covariance Estimation under Differential Privacy in the Add-Remove Model and Beyond
  101. RobQFL: Robust Quantum Federated Learning in Adversarial Environment
  102. Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
  103. ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
  104. Encoding of musical structures in hidden units of restricted Boltzmann machines
  105. PLaMo 2 Technical Report
  106. Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
  107. SynGen-Vision: Synthetic Data Generation for training industrial vision models
  108. SpiderNets: Vision Models Predict Human Fear From Aversive Images
  109. L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
  110. Multi-modal Uncertainty Robust Tree Cover Segmentation For High-Resolution Remote Sensing Images
  111. Using LLMs for Multilingual Clinical Entity Linking to ICD-10
  112. Filtering with Randomised Observations: Sequential Learning of Relevant Subspace Properties and Accuracy Analysis
  113. Memorization neq Understanding: Do Large Language Models Have the Ability of Scenario Cognition?
  114. CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
  115. The Paradox of Doom: Acknowledging Extinction Risk Reduces the Incentive to Prevent It
  116. Diffusion Secant Alignment for Score-Based Density Ratio Estimation
  117. Histogram Driven Amplitude Embedding for Qubit Efficient Quantum Image Compression
  118. Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
  119. Collaboration and Conflict between Humans and Language Models through the Lens of Game Theory
  120. TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
  121. PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
  122. Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media
  123. AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representations
  124. Analyzing Finnish Inflectional Classes through Discriminative Lexicon and Deep Learning Models
  125. Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation
  126. AI-Driven Fronthaul Link Compression in Wireless Communication Systems: Review and Method Design
  127. Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
  128. Graph Unlearning: Efficient Node Removal in Graph Neural Networks
  129. Post-training Large Language Models for Diverse High-Quality Responses
  130. VARMA-Enhanced Transformer for Time Series Forecasting
  131. The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
  132. Decoders Laugh as Loud as Encoders
  133. Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
  134. Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
  135. Knowledge-Guided Vision-Language Inference for Image-Based Urban Flood Depth Estimation
  136. Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
  137. Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
  138. MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment Using UAV Imagery
  139. A Study of Large Language Models for Patient Information Extraction: Model Architecture, Fine-Tuning Strategy, and Multi-task Instruction Tuning
  140. Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
  141. Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
  142. WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
  143. Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
  144. Beyond I-Con: Exploring New Dimension of Distance Measures in Representation Learning
  145. CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction
  146. Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation
  147. Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
  148. Natural Spectral Fusion: p-Exponent Cyclic Scheduling and Early Decision-Boundary Alignment in First-Order Optimization