mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 5 Mar 2025

338 papers

  1. Human Preferences for Constructive Interactions in Language Model AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  2. BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease IdentificationMixture-of-experts → Medical and biomedical MoE
  3. Mixture of Experts Made Intrinsically InterpretableMixture-of-experts → MoE large language models
  4. Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware DemonstrationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. E2AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  6. Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid QuantizationKnowledge distillation → General knowledge distillation methods
  7. Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-AgentsLLM agents and tool use → Social simulation and multi-agent debate
  8. Preserving Cultural Identity with Context-Aware Translation Through Multi-Agent AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. ProReflow: Progressive Reflow with Decomposed VelocityDiffusion models → Flow matching, time series and science
  10. All-atom Diffusion Transformers: Unified generative modelling of molecules and materialsDiffusion models → Flow matching, time series and science
  11. Enhancing Autonomous Driving Safety with Collision Scenario IntegrationEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
  12. GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective BackdoorsDiffusion models → Robustness, privacy and adversarial aspects +1
  13. LensDFF: Language-enhanced Sparse Feature Distillation for Efficient Few-Shot Dexterous ManipulationKnowledge distillation → Multimodal distillation
  14. Seldonian Reinforcement Learning for Ad Hoc TeamworkOffline RL and imitation learning from data → Offline RL algorithms +1
  15. Vision-Language Models Struggle to Align Entities across ModalitiesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  16. Decoupling the components of geometric understanding in Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Multi-Agent Systems Powered by Large Language Models: Applications in Swarm IntelligenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. VoiceGRPO: Modern MoE Transformers with Group Relative Policy Optimization GRPO for AI Voice Health Care Applications on Voice Pathology DetectionMixture-of-experts → Multimodal MoE models
  19. Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV SwarmLLM agents and tool use → Reinforcement learning for LLM agents +1
  20. Positive-Unlabeled Diffusion Models for Preventing Sensitive Data GenerationDiffusion models → Robustness, privacy and adversarial aspects
  21. Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion ModelDiffusion models → Inverse problems and image restoration
  22. The MASK Benchmark: Disentangling Honesty From Accuracy in AI SystemsLLM agents and tool use → Social simulation and multi-agent debate
  23. Process-based Self-Rewarding Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
  24. OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature ExtractionVision-language-action models → Generalist VLA models and benchmarks
  25. Towards Understanding Distilled Reasoning Models: A Representational ApproachLLM reasoning → Prompting and chain-of-thought reasoning +1
  26. Improving LLM Safety Alignment with Dual-Objective OptimizationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  27. Rethinking Video Tokenization: A Conditioned Diffusion-based ApproachDiffusion models → Video generation
  28. Memory Injection Attacks on LLM Agents via Query-Only InteractionLLM agents and tool use → Agent threats, guardrails and governance
  29. ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArXLLM reasoning → Test-time compute and efficient thinking
  30. DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward GuidanceDiffusion models → Diffusion and flow policies for robotics
  31. MAS-GPT: Training LLMs to Build LLM-based Multi-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
  32. Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  33. Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of AbstractionLLM reasoning → Reasoning benchmarks and evaluation
  34. Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step ReturnsDeep reinforcement learning methods → RL theory and sample complexity
  35. Psy-Copilot: Visual Chain of Thought for CounselingLLM reasoning → Clinical and biomedical applications
  36. Feature-Level Insights into Artificial Text Detection with Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  37. Towards Understanding Text Hallucination of Diffusion Models via Local Generation BiasDiffusion models → Medical imaging and segmentation
  38. Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code RepositoriesLLM agents and tool use → Agent threats, guardrails and governance
  39. Efficiency of Parallel and Restart Exploration Strategies in Model Free Stochastic SimulationsDeep reinforcement learning methods → RL theory and sample complexity
  40. Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented ManipulationLLM reasoning → Spatial and embodied reasoning
  41. DO-IQS: Dynamics-Aware Offline Inverse Q-Learning for Optimal Stopping with Unknown Gain FunctionsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  42. Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in MinecraftLLM agents and tool use → Reinforcement learning for LLM agents
  43. Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic DimensionLLM safety and security → Jailbreaking
  44. SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained LearningVision-language-action models → Safety and adversarial attacks +2
  45. Continuous Control of Diverse Skills in Quadruped Robots Without Complete Expert DatasetsOffline RL and imitation learning from data → Imitation learning methods
  46. Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  47. Unified Mind Model: Reimagining Autonomous Agents in the LLM EraLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. Data Poisoning Attacks to Locally Differentially Private Range Query ProtocolsLLM safety and security → Membership inference attacks
  49. JamMa: Ultra-lightweight Local Feature Matching with Joint MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  50. RASD: Retrieval-Augmented Speculative DecodingRetrieval-augmented generation → Generation and context integration +1
  51. Rethinking Video Super-Resolution: Towards Diffusion-Based Methods without Motion AlignmentDiffusion models → Inverse problems and image restoration
  52. EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity StatesLLM reasoning → Reasoning benchmarks and evaluation
  53. Navigating Intelligence: A Survey of Google OR-Tools and Machine Learning for Global Path Planning in Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  54. See What You Are Told: Visual Attention Sink in Large Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  55. The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine TranslationLLM reasoning → Reasoning benchmarks and evaluation
  56. Enhancing Abnormality Grounding for Vision Language Models with Knowledge DescriptionsMultimodal LLMs / vision-language models → Medical vision-language models
  57. Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  58. Optimizing for the Shortest Path in Denoising Diffusion ModelDiffusion models → Diffusion foundations and sampling
  59. Less is more? Rewards in RL for Cyber DefenceDeep reinforcement learning methods → Adversarial robustness and RL in finance
  60. FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4LLM reasoning → Mathematical reasoning
  61. COSINT-Agent: A Knowledge-Driven Multimodal Agent for Chinese Open Source IntelligenceLLM agents and tool use → Multimodal and embodied agents
  62. Convergence Rates for Softmax Gating Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
  63. Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow EnvironmentDeep reinforcement learning methods → RL for robot locomotion and manipulation
  64. An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  65. MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem ProvingLLM reasoning → Mathematical reasoning
  66. Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data SettingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  67. SpiritSight Agent: Advanced GUI Agent with One LookLLM agents and tool use → GUI and mobile agents
  68. Position: Model Collapse Does Not Mean What You ThinkSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  69. Causality-Based Reinforcement Learning Method for Multi-Stage Robotic TasksDeep reinforcement learning methods → Deep RL algorithms and representations
  70. Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural NetworksKnowledge distillation → Distillation for spiking neural networks
  71. Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and GeneralizabilityLLM reasoning → Reasoning benchmarks and evaluation
  72. Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  73. The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  74. WarmFed: Federated Learning with Warm-Start for Globalization and Personalization Via Personalized Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  75. From Architectural Sketch to Conceptual Representation: Using Structure-Aware Diffusion Model to Generate Renderings of School BuildingsDiffusion models → 3D, point cloud and scene generation
  76. AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost ExoskeletonsOffline RL and imitation learning from data → Robot manipulation imitation learning
  77. BEVDriver: Leveraging BEV Maps in LLMs for Robust Closed-Loop DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  78. Joint Group Profiling and Recommendation via Deep Neural Network-based Multi-Task Learning
  79. CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation
  80. Qieemo: Speech Is All You Need in the Emotion Recognition in Conversations
  81. Identifying Ising and percolation phase transitions based on KAN method
  82. LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool
  83. WVEmbs with its Masking: A Method For Radar Signal Sorting
  84. Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processing
  85. Towards Resilient and Sustainable Global Industrial Systems: An Evolutionary-Based Approach
  86. Review of Machine Learning for Micro-Electronic Design Verification
  87. Multimodal Stock Price Prediction: A Case Study of the Russian Securities Market
  88. Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory
  89. Leveraging Taxonomy Similarity for Next Activity Prediction in Patient Treatment
  90. Is Pre-training Applicable to the Decoder for Dense Prediction?
  91. An Optimization Algorithm for Multimodal Data Alignment
  92. Cross-modal Causal Relation Alignment for Video Question Grounding
  93. Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety
  94. Beyond H&E: Unlocking Pathological Insights with Polarization Imaging
  95. Market-based Architectures in RL and Beyond
  96. Introduction to Artificial Consciousness: History, Current Trends and Ethical Challenges
  97. The impact of AI and peer feedback on research writing skills: a study using the CGScholar platform among Kazakhstani scholars
  98. Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
  99. Three tiers of computation in transformers and in brain architectures
  100. Role of Databases in GenAI Applications
All 338
  1. Narrative Context Protocol: An Open-Source Storytelling Framework for Generative AI
  2. Self-Supervised Z-Slice Augmentation for 3D Bio-Imaging via Knowledge Distillation
  3. Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model
  4. Framing the Game: How Context Shapes LLM Decision-Making
  5. Combined Physics and Event Camera Simulator for Slip Detection
  6. FedPalm: A General Federated Learning Framework for Closed- and Open-Set Palmprint Verification
  7. PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis
  8. Distilling Dataset into Neural Field
  9. Extrapolation Merging: Keep Improving With Extrapolation and Merging
  10. "Only ChatGPT gets me": An Empirical Analysis of GPT versus other Large Language Models for Emotion Detection in Text
  11. StickMotion: Generating 3D Human Motions by Drawing a Stickman
  12. Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications
  13. Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching
  14. DA-STGCN: 4D Trajectory Prediction Based on Spatiotemporal Feature Extraction
  15. HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs
  16. RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments
  17. Data-driven identification of nonlinear dynamical systems with LSTM autoencoders and Normalizing Flows
  18. Preliminary Report: Enhancing Role Differentiation in Conversational HCI Through Chromostereopsis
  19. Generative Learning of Densities on Manifolds
  20. On the Acquisition of Shared Grammatical Representations in Bilingual Language Models
  21. A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
  22. Performance Comparison of Large Language Models on Advanced Calculus Problems
  23. Improving the Temporal Resolution of SOHO/MDI Magnetograms of Solar Active Regions Using a Deep Generative Model
  24. Dyads: Artist-Centric, AI-Generated Dance Duets
  25. WIP: Assessing the Effectiveness of ChatGPT in Preparatory Testing Activities
  26. COARSE: Collaborative Pseudo-Labeling with Coarse Real Labels for Off-Road Semantic Segmentation
  27. SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection
  28. LLM-Powered Prediction of Hyperglycemia and Discovery of Behavioral Treatment Pathways from Wearables and Diet
  29. Tec-Habilidad: Skill Classification for Bridging Education and Employment
  30. "Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications
  31. De-skilling, Cognitive Offloading, and Misplaced Responsibilities: Potential Ironies of AI-Assisted Design
  32. Improved Robust Estimation for ErdHos-R'enyi Graphs: The Sparse Regime and Optimal Breakdown Point
  33. CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance
  34. Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
  35. Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
  36. On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness
  37. Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial Patches
  38. The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks
  39. Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line
  40. IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction
  41. LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach
  42. Learning to Negotiate via Voluntary Commitment
  43. Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
  44. Nexar Dashcam Collision Prediction Dataset and Challenge
  45. Task-Agnostic Attacks Against Vision Foundation Models
  46. The Optical and Infrared Are Connected
  47. Non-Gaussianities in Collider Metric Binning
  48. EgoLife: Towards Egocentric Life Assistant
  49. RiskAgent: Synergizing Language Models with Validated Tools for Evidence-Based Risk Prediction
  50. DeepGrav: Anomalous Gravitational-Wave Detection Through Deep Latent Features
  51. Synthetic Data Augmentation for Enhancing Harmful Algal Bloom Detection with Machine Learning
  52. Rebalanced Multimodal Learning with Data-aware Unimodal Sampling
  53. Predicting Team Performance from Communications in Simulated Search-and-Rescue
  54. Sarcasm Detection as a Catalyst: Improving Stance Detection with Cross-Target Capabilities
  55. Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning
  56. Neural Models of Task Adaptation: A Tutorial on Spiking Networks for Executive Control
  57. GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
  58. PacketCLIP: Multi-Modal Embedding of Network Traffic and Language for Cybersecurity Reasoning
  59. Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices
  60. CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning
  61. Opportunistic Routing in Wireless Communications via Learnable State-Augmented Policies
  62. Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need
  63. Graph-Augmented LSTM for Forecasting Sparse Anomalies in Graph-Structured Time Series
  64. Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames
  65. Deep Causal Behavioral Policy Learning: Applications to Healthcare
  66. Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements
  67. Handling Uncertainty in Health Data using Generative Algorithms
  68. Curating Demonstrations using Online Experience
  69. Enhancing LLM Knowledge Learning through Generalization
  70. SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
  71. Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
  72. Towards Trustworthy Federated Learning
  73. Quantification of Tenseness in English and Japanese Tense-Lax Vowels: A Lagrangian Model with Indicator θ1 and Force of Tenseness Ftense(t)
  74. Optimally Installing Strict Equilibria
  75. A Generative Approach to High Fidelity 3D Reconstruction from Text Data
  76. LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant
  77. Conformal prediction of future insurance claims in the regression problem
  78. Robust Learning of Diverse Code Edits
  79. Improving 6D Object Pose Estimation of metallic Household and Industry Objects
  80. Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
  81. Token-Level Privacy in Large Language Models
  82. DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
  83. Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
  84. DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms
  85. An Adaptive Underwater Image Enhancement Framework via Multi-Domain Fusion and Color Compensation
  86. L2RDaS: Synthesizing 4D Radar Tensors for Model Generalization via Dataset Expansion
  87. Feature Matching Intervention: Leveraging Observational Data for Causal Representation Learning
  88. Deterministic Global Optimization of the Acquisition Function in Bayesian Optimization: To Do or Not To Do?
  89. It's My Data Too: Private ML for Datasets with Multi-User Training Examples
  90. CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
  91. Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling
  92. Decoupled Recommender Systems: Exploring Alternative Recommender Ecosystem Designs
  93. REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluation
  94. Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs
  95. English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance
  96. PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention
  97. Scaling Crowdsourced Election Monitoring: Construction and Evaluation of Classification Models for Multilingual and Cross-Domain Classification Settings
  98. Intent-Handover: Grounding Language in Human-Usage Regions for Trustworthy Robot-to-Human Handovers
  99. Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
  100. Olympus: A Jumping Quadruped for Planetary Exploration Utilizing Reinforcement Learning for In-Flight Attitude Control
  101. Domain Consistent Industrial Decarbonisation of Global Coal Power Plants
  102. A Conceptual Model for Attributions in Event-Centric Knowledge Graphs
  103. Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection
  104. Transformer-Based Power Optimization for Max-Min Fairness in Cell-Free Massive MIMO
  105. High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights
  106. Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case
  107. Revisiting the Role of Relearning in Semantic Dementia
  108. A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction
  109. A Criterion for Extending Continuous-Mixture Identifiability Results
  110. Unified Human Localization and Trajectory Prediction with Monocular Vision
  111. AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom Tracking
  112. AdaSin: Enhancing Hard Sample Metrics with Dual Adaptive Penalty for Face Recognition
  113. Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios
  114. O-RAN Xapps Conflict Prediction Using Graph Convolutional Networks
  115. Do ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalization
  116. An Aspect Extraction Framework using Different Embedding Types, Learning Models, and Dependency Structure
  117. NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection
  118. Mineral segmentation using electron microscope images and spectral sampling through multimodal graph neural networks
  119. Opinion: Revisiting synthetic data classifications from a privacy perspective
  120. Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization
  121. CarGait: Cross-Attention based Re-ranking for Gait recognition
  122. State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
  123. Deictic Codes, Demonstratives, and Reference: A Step Toward Solving the Grounding Problem
  124. Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
  125. Federated Learning for Predicting Mild Cognitive Impairment to Dementia Conversion
  126. Differentially Private Learners for Heterogeneous Treatment Effects
  127. TEDDY: A Family Of Foundation Models For Understanding Single Cell Biology
  128. Feature Point Extraction for Extra-Affine Image
  129. Bridging Synthetic-to-Real Gaps: Frequency-Aware Perturbation and Selection for Single-shot Multi-Parametric Mapping Reconstruction
  130. Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues
  131. DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing
  132. Open-Source Large Language Models as Multilingual Crowdworkers: Synthesizing Open-Domain Dialogues in Several Languages With No Examples in Targets and No Machine Translation
  133. Active Learning for Deep Learning-Based Hemodynamic Parameter Estimation
  134. Biased Heritage: How Datasets Shape Models in Facial Expression Recognition
  135. Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties
  136. Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty
  137. Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning
  138. CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization
  139. Privacy is All You Need: Revolutionizing Wearable Health Data with Advanced PETs
  140. Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression
  141. Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction
  142. Simplicial SMOTE: Oversampling Solution to the Imbalanced Learning Problem
  143. When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits
  144. Augmentation-Based Deep Learning for Identification of Circulating Tumor Cells
  145. Evolutionary Prediction Games
  146. Robust Predictive Modeling Under Unseen Data Distribution Shifts: A Methodological Commentary
  147. AI-Driven Multi-Stage Computer Vision System for Defect Detection in Laser-Engraved Industrial Nameplates
  148. Multi-Agent DRL for Queue-Aware Task Offloading in Hierarchical MEC-Enabled Air-Ground Networks
  149. GNNMerge: Merging of GNN Models Without Accessing Training Data
  150. Paths and Ambient Spaces in Neural Loss Landscapes
  151. The Serendipity of Claude AI: Case of the 13 Low-Resource National Languages of Mali
  152. A Novel Multi-Criteria Local Latin Hypercube Refinement System for Commutation Angle Improvement in IPMSMs
  153. AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images
  154. Top-K Maximum Intensity Projection Priors for 3D Liver Vessel Segmentation
  155. TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracy
  156. Concepts Learned Visually by Infants Can Contribute to Visual Learning and Understanding in AI Models
  157. Transformers for molecular property prediction: Domain adaptation efficiently improves performance
  158. Statistical Limits in Random Tensors with Multiple Correlated Spikes
  159. Leveraging Large Language Models to Develop Heuristics for Emerging Optimization Problems
  160. iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News
  161. Leap: Inductive Link Prediction via Learnable TopologyAugmentation
  162. Automated Attendee Recognition System for Large-Scale Social Events or Conference Gathering
  163. Deep Learning-Based Diffusion MRI Tractography: Integrating Spatial and Anatomical Information
  164. ScaleFusionNet: Transformer-Guided Multi-Scale Feature Fusion for Skin Lesion Segmentation
  165. Golden Cudgel Network for Real-Time Semantic Segmentation
  166. LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
  167. Full-DoF Egomotion Estimation for Event Cameras Using Geometric Solvers
  168. SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection
  169. Differential Machine Learning for Time Series Prediction
  170. Which books do I like?
  171. Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters
  172. Interactive Segmentation and Report Generation for CT Images
  173. Deep Understanding of Sign Language for Sign to Subtitle Alignment
  174. Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning
  175. Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations
  176. Gaussian highpass guided image filtering
  177. Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations
  178. BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation
  179. TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization
  180. Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
  181. Reduced Spatial Dependency for More General Video-level Deepfake Detection
  182. Conformal Transformations for Symmetric Power Transformers
  183. LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law
  184. Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
  185. Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions
  186. BANet: Bilateral Aggregation Network for Mobile Stereo Matching
  187. Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
  188. BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
  189. Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment
  190. Two-Stream Thermal Imaging Fusion for Enhanced Time of Birth Detection in Neonatal Care
  191. Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection
  192. PAIR: A Novel Large Language Model-Guided Selection Strategy for Evolutionary Algorithms
  193. Prediction of Halo Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and a Transformer Model
  194. GenColor: Generative Color-Concept Association in Visual Design
  195. Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints
  196. Targeted Distillation for Sentiment Analysis
  197. Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
  198. Rice Grain Size Measurement using Image Processing
  199. NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency
  200. Find Matching Faces Based On Face Parameters
  201. Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution
  202. Transformer-Based Spatio-Temporal Association of Apple Fruitlets
  203. Directly Follows Graphs Go Predictive Process Monitoring With Graph Neural Networks
  204. Online Bidding under RoS Constraints without Knowing the Value
  205. Structured Outputs Enable General-Purpose LLMs to be Medical Experts
  206. DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
  207. Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation
  208. PAC Learning with Improvements
  209. Active operator learning with predictive uncertainty quantification for partial differential equations
  210. Intermediate-Task Transfer Learning: Leveraging Sarcasm Detection for Stance Detection
  211. AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding
  212. A Predict-Then-Optimize Customer Allocation Framework for Online Fund Recommendation
  213. SpinML: Customized Synthetic Data Generation for Private Training of Specialized ML Models
  214. Dimensionality reduction for homological stability and global structure preservation
  215. DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
  216. Partial Convolution Meets Visual Attention
  217. A Survey of Foundation Models for Environmental Science
  218. Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
  219. Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions
  220. Convergence Analysis of Federated Learning Methods Using Backward Error Analysis
  221. Learning to Reduce Search Space for Generalizable Neural Routing Solver
  222. Bridging Molecular Graphs and Large Language Models
  223. Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis
  224. Exploring Neural Ordinary Differential Equations as Interpretable Healthcare classifiers
  225. NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics
  226. Predicting Space Tourism Demand Using Explainable AI
  227. A Multimodal Framework for Topic Propagation Classification in Social Networks
  228. An Improved Pure Fully Connected Neural Network for Rice Grain Classification
  229. OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting
  230. External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection
  231. Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
  232. RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition
  233. Fast Jet Tagging with MLP-Mixers on FPGAs
  234. MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion
  235. AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
  236. Hopfield Networks Meet Big Data: A Brain-Inspired Deep Learning Framework for Semantic Data Linking
  237. A Linear Theory of Multi-Winner Voting
  238. Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings