mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 9 Jul 2025

323 papers

  1. Diffusion-Assisted Frequency Attention Model for Whole-body Low-field MRI ReconstructionDiffusion models → Medical imaging and segmentation
  2. Agentic AI with Orchestrator-Agent Trust: A Modular Visual Classification Framework with Trust-Aware Orchestration and RAG-Based ReasoningLLM agents and tool use → Multimodal and embodied agents
  3. RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG +1
  4. DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra ElucidationDiffusion models → Flow matching, time series and science
  5. Towards Evaluating Robustness of Prompt Adherence in Text to Image ModelsDiffusion models → Image generation, text-to-image and editing
  6. AblationBench: Evaluating Automated Planning of Ablations in Empirical AI ResearchLLM agents and tool use → Web, search, and research agents
  7. CRISP: Complex Reasoning with Interpretable Step-based PlansLLM reasoning → Prompting and chain-of-thought reasoning
  8. On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI AlignmentLLM safety and security → Safety alignment, refusal and guardrails
  9. Entity Re-identification in Visual Storytelling via Contrastive Reinforcement LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  10. Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and DiscoveryLLM reasoning → Clinical and biomedical applications
  11. Optimizing Model Splitting and Device Task Assignment for Deceptive Signal Assisted Private Multi-hop Split LearningDeep reinforcement learning methods → RL for energy, networks and operations
  12. Generating Moving 3D Soundscapes with Latent Diffusion ModelsDiffusion models → Audio, speech and music
  13. Frontier LLMs Still Struggle with Simple Reasoning TasksLLM reasoning → Mathematical reasoning
  14. Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health MisinformationRetrieval-augmented generation → Medical and biomedical RAG +1
  15. ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented ReasoningLLM reasoning → Multimodal reasoning +1
  16. MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. MagiC: Evaluating Multimodal Cognition Toward Grounded Visual ReasoningLLM reasoning → Multimodal reasoning +1
  18. LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based EvaluationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  19. Open Source Planning & Control System with Language Agents for Autonomous Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  20. Attentions Under the Microscope: A Comparative Study of Resource Utilization for Variants of Self-AttentionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  21. MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular GenerationDiffusion models → Flow matching, time series and science
  22. Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  23. Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow MatchingDiffusion models → Flow matching, time series and science
  24. Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in AstrophysicsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  25. Robust Multimodal Large Language Models Against Modality ConflictMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  26. Weighted Multi-Prompt Learning with Description-free Large Language Model DistillationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  27. Attention-Aware GNN-based Input Defense against Multi-Turn LLM JailbreakLLM safety and security → Jailbreaking
  28. Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model UnlearningDiffusion models → Robustness, privacy and adversarial aspects +1
  29. Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World KnowledgeDiffusion models → Robustness, privacy and adversarial aspects +1
  30. Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature ExtractorMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  31. Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  32. Comprehensive Evaluation of Large Multimodal Models for Nutrition Analysis: A New Benchmark Enriched with Contextual MetadataMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. FlexOlmo: Open Language Models for Flexible Data UseMixture-of-experts → MoE large language models
  34. First Return, Entropy-Eliciting ExploreLLM reasoning → Reinforcement learning for reasoning
  35. MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge DistillationKnowledge distillation → Multimodal distillation
  36. Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data DistributionsDiffusion models → Inverse problems and image restoration
  37. Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  38. Are They All Good? Evaluating the Quality of CoTs in LLM-based Code GenerationLLM reasoning → Reasoning for agents, planning and code
  39. Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EMMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  40. CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual RationaleMultimodal LLMs / vision-language models → Medical vision-language models +1
  41. Investigating the Robustness of Retrieval-Augmented Generation at the Query LevelRetrieval-augmented generation → RAG robustness and adaptive retrieval
  42. What Has a Foundation Model Found? Using Inductive Bias to Probe for World ModelsWorld models → World models for language agents
  43. Rethinking Verification for LLM Code Generation: From Generation to TestingLLM reasoning → Reasoning for agents, planning and code
  44. MIND: A Multi-agent Framework for Zero-shot Harmful Meme DetectionLLM safety and security → Safety alignment, refusal and guardrails
  45. Designing Adaptive Algorithms Based on Reinforcement Learning for Dynamic Optimization of Sliding Window Size in Multi-Dimensional Data StreamsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  46. VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding ManipulationLLM agents and tool use → Agent threats, guardrails and governance +1
  47. Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language ModelLLM reasoning → Reinforcement learning for reasoning
  48. DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion ModelsDiffusion models → Flow matching, time series and science
  49. The Dark Side of LLMs: Agent-based Attack Vectors for System-level CompromiseLLM agents and tool use → Agent threats, guardrails and governance +1
  50. Shifting from Ranking to Set Selection for Retrieval Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  51. Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided FrameworkLLM reasoning → Test-time compute and efficient thinking
  52. Artificial Generals Intelligence: Mastering Generals.io with Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  53. Hierarchical Reinforcement Learning for Articulated Tool Manipulation with Multifingered HandDeep reinforcement learning methods → RL for robot locomotion and manipulation
  54. Learning safe, constrained policies via imitation learning: Connection to Probabilistic Inference and a Naive AlgorithmOffline RL and imitation learning from data → Imitation learning methods +1
  55. Finetuning Vision-Language Models as OCR Systems for Low-Resource Languages: A Case Study of ManchuMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  56. DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion EnhancementState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  57. A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual GroundingLLM reasoning → Spatial and embodied reasoning
  58. CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMsRetrieval-augmented generation → Medical and biomedical RAG
  59. Spatial-Temporal Aware Visuomotor Diffusion Policy LearningDiffusion models → Diffusion and flow policies for robotics +1
  60. Value from Observations: Towards Large-Scale Imitation Learning via Self-ImprovementOffline RL and imitation learning from data → Imitation learning methods +1
  61. Spatial-Temporal Graph Mamba for Music-Guided Dance Video SynthesisState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  62. Text-promptable Object Counting via Quantity Awareness EnhancementMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  63. Exploring State-Space-Model based Language Model in Music GenerationState-space sequence models (S4, Mamba) → Speech and audio SSMs
  64. Enhancing Diffusion Model Stability for Image Restoration via Gradient ManagementDiffusion models → Inverse problems and image restoration
  65. Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion PriorDiffusion models → 3D, point cloud and scene generation
  66. Efficient Multi-Task Reinforcement Learning with Cross-Task Policy GuidanceDeep reinforcement learning methods → Deep RL algorithms and representations
  67. Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  68. Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long GenerationLLM reasoning → Test-time compute and efficient thinking
  69. Generalization in Reinforcement Learning for Radio Access NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  70. MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf InteractionDiffusion models → Video generation
  71. From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive OptimizationLLM reasoning → Reinforcement learning for reasoning
  72. SlimCaching: Edge Caching of Mixture-of-Experts for Distributed InferenceMixture-of-experts → Efficient MoE training and inference systems
  73. SEARA: An Automated Approach for Obtaining Optimal RetrieversRetrieval-augmented generation → RAG pipeline design and evaluation
  74. Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attributionDiffusion models → Image generation, text-to-image and editing
  75. Direct Regret Optimization in Bayesian OptimizationOffline RL and imitation learning from data → Offline RL algorithms
  76. InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd BehaviorLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  77. Concept Unlearning by Modeling Key Steps of Diffusion ProcessDiffusion models → Robustness, privacy and adversarial aspects +1
  78. FIFA: Unified Faithfulness Evaluation Framework for Text-to-Video and Video-to-Text GenerationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  79. Gradientsys: A Multi-Agent LLM Scheduler with ReAct OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  80. SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep LayersEfficient LLM inference and serving → KV cache optimization
  81. Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  82. GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language ModelsLLM reasoning → LLM reasoning for recommendation
  83. Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings for CLEF JOKER 2025 Task 2LLM agents and tool use → General LLM agent frameworks and benchmarks
  84. MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting ModelsMixture-of-experts → MoE for time series and graphs
  85. Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video ReasoningLLM reasoning → Multimodal reasoning
  86. 3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D WorldsLLM reasoning → Spatial and embodied reasoning +1
  87. Animating Language Practice: Engagement with Stylized Conversational Agents in Japanese LearningLLM agents and tool use → Educational agents and math problem solving
  88. FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated LearningDiffusion models → Robustness, privacy and adversarial aspects
  89. Generative Lagrangian data assimilation for ocean dynamics under extreme sparsityDiffusion models → Flow matching, time series and science
  90. Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation ModelsSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  91. From Rattle to Roar: Optimizer Showdown for MambaStock on S&P 500
  92. Cognitive Exoskeleton: Augmenting Human Cognition with an AI-Mediated Intelligent Visual Feedback
  93. A Survey of Classification Tasks and Approaches for Legal Contracts
  94. You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
  95. Attention-Based Fusion of IQ and FFT Spectrograms with AoA Features for GNSS Jammer Localization
  96. VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation
  97. Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
  98. Next-Generation Travel Demand Modeling with a Generative Framework for Household Activity Coordination
  99. GUIDE: Towards Scalable Advising for Research Ideas
  100. Mind the Gap: Navigating Inference with Optimal Transport Maps
All 323
  1. Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond
  2. Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale
  3. Privacy-Utility-Fairness: A Balanced Approach to Vehicular-Traffic Management System
  4. On the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition
  5. e-Profits: A Business-Aligned Evaluation Metric for Profit-Sensitive Customer Churn Prediction
  6. Foundation models for time series forecasting: Application in conformal prediction
  7. Multi-omic Prognosis of Alzheimer's Disease with Asymmetric Cross-Modal Cross-Attention Network
  8. Clio-X: AWeb3 Solution for Privacy-Preserving AI Access to Digital Archives
  9. ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints
  10. Barriers in Integrating Medical Visual Question Answering into Radiology Workflows: A Scoping Review and Clinicians' Insights
  11. Integrating External Tools with Large Language Models to Improve Accuracy
  12. Beyond Scale: Small Language Models are Comparable to GPT-4 in Mental Health Understanding
  13. Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset
  14. Bayesian Double Descent
  15. Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning
  16. Scalable and Realistic Virtual Try-on Application for Foundation Makeup with Kubelka-Munk Theory
  17. mmFlux: Crowd Flow Analytics with Commodity mmWave MIMO Radar
  18. Optimizing Communication and Device Clustering for Clustered Federated Learning with Differential Privacy
  19. ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation
  20. AdeptHEQ-FL: Adaptive Homomorphic Encryption for Federated Learning of Hybrid Classical-Quantum Models with Dynamic Layer Sparing
  21. Application of LLMs to Multi-Robot Path Planning and Task Allocation
  22. Multilayer GNN for Predictive Maintenance and Clustering in Power Grids
  23. Time Series Foundation Models for Multivariate Financial Time Series Forecasting
  24. Thermodynamic Prediction Enabled by Automatic Dataset Building and Machine Learning
  25. Discretization-independent operator learning for partial differential equations
  26. Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems
  27. Natural Evolutionary Search meets Probabilistic Numerics
  28. Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes
  29. The Impact of Background Speech on Interruption Detection in Collaborative Groups
  30. TRIP: A Nonparametric Test to Diagnose Biased Feature Importance Scores
  31. Beyond the ATE: Interpretable Modelling of Treatment Effects over Dose and Time
  32. DisenQ: Disentangling Q-Former for Activity-Biometrics
  33. Robust Multimodal Learning Framework For Intake Gesture Detection Using Contactless Radar and Wearable IMU Sensors
  34. Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
  35. FedP3E: Privacy-Preserving Prototype Exchange for Non-IID IoT Malware Detection in Cross-Silo Federated Learning
  36. Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
  37. A Language-Driven Framework for Improving Personalized Recommendations: Merging LLMs with Traditional Algorithms
  38. MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings
  39. Automated Video Segmentation Machine Learning Pipeline
  40. Towards Robust Surrogate Models: Benchmarking Machine Learning Approaches to Expediting Phase Field Simulations of Brittle Fracture
  41. Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification
  42. Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
  43. SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains
  44. Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
  45. Neurosymbolic Feature Extraction for Identifying Forced Labor in Supply Chains
  46. Bias-Aware Mislabeling Detection via Decoupled Confident Learning
  47. Scaling can lead to compositional generalization
  48. State-Inference-Based Prompting for Natural Language Trading with Game NPCs
  49. A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
  50. Prompt Perturbations Reveal Human-Like Biases in Large Language Model Survey Responses
  51. Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
  52. Large-scale portfolio optimization with variational neural annealing
  53. Interpretable EEG-to-Image Generation with Semantic Prompts
  54. Unreduced Persistence Diagrams for Topological Machine Learning
  55. CL-Polyp: A Contrastive Learning-Enhanced Network for Accurate Polyp Segmentation
  56. Aerial Maritime Vessel Detection and Identification
  57. Class conditional conformal prediction for multiple inputs by p-value aggregation
  58. DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
  59. Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey
  60. CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs
  61. Understanding Malware Propagation Dynamics through Scientific Machine Learning
  62. Str-GCL: Structural Commonsense Driven Graph Contrastive Learning
  63. Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
  64. GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
  65. LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
  66. 4KAgent: Agentic Any Image to 4K Super-Resolution
  67. Does Data Scaling Lead to Visual Compositional Generalization?
  68. Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
  69. Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
  70. Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
  71. Evaluating Attribute Confusion in Fashion Text-to-Image Generation
  72. RulerNet: Learning Perspective-Invariant Ruler Representations for Robust Image Scale Estimation
  73. An AI Approach for Learning the Spectrum of the Laplace-Beltrami Operator
  74. How to Bridge the Sim-to-Real Gap in Digital Twin-Aided Telecommunication Networks
  75. A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering
  76. Non-Asymptotic Analysis of Online Local Private Learning with SGD
  77. Surrogate Model for Heat Transfer Prediction in Impinging Jet Arrays using Dynamic Inlet/Outlet and Flow Rate Control
  78. Self-Supervised Learning at the Edge: The Cost of Labeling
  79. ZKTorch: Compiling ML Inference to Zero-Knowledge Proofs via Parallel Proof Accumulation
  80. UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
  81. Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices
  82. On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence
  83. Integrating Pathology Foundation Models and Spatial Transcriptomics for Cellular Decomposition from Histology Images
  84. When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior
  85. Deep Brain Net: An Optimized Deep Learning Model for Brain tumor Detection in MRI Images Using EfficientNetB0 and ResNet50 with Transfer Learning
  86. GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
  87. Enhancing non-Rigid 3D Model Deformations Using Mesh-based Gaussian Splatting
  88. Federated Learning-based MARL for Strengthening Physical-Layer Security in B5G Networks
  89. Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
  90. Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patients
  91. IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence
  92. MCA-RG: Enhancing LLMs with Medical Concept Alignment for Radiology Report Generation
  93. A Principled Framework for Multi-View Contrastive Learning
  94. DenoiseCP-Net: Efficient Collective Perception in Adverse Weather via Joint LiDAR-Based 3D Object Detection and Denoising
  95. FRaN-X: FRaming and Narratives-eXplorer
  96. A multi-modal dataset for insect biodiversity with imagery and DNA at the trap and individual level
  97. Hallucinating 360deg: Panoramic Street-View Generation via Local Scenes Diffusion and Probabilistic Prompting
  98. Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
  99. Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report
  100. Noisy PDE Training Requires Bigger PINNs
  101. Segmentation Regularized Training for Multi-Domain Deep Learning Registration applied to MR-Guided Prostate Cancer Radiotherapy
  102. Off-Policy Evaluation Under Nonignorable Missing Data
  103. SimCortex: Collision-free Simultaneous Cortical Surfaces Reconstruction
  104. Ecological Legacies of Pre-Columbian Settlements Evident in Palm Clusters of Neotropical Mountain Forests
  105. MCCD: A Multi-Attribute Chinese Calligraphy Character Dataset Annotated with Script Styles, Dynasties, and Calligraphers
  106. DICE: Data Influence Cascade in Decentralized Learning
  107. Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy
  108. Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
  109. Distribution-free inference for LightGBM and GLM with Tweedie loss
  110. Beyond Connectivity: An Open Architecture for AI-RAN Convergence in 6G
  111. Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
  112. MultiJustice: A Chinese Dataset for Multi-Party, Multi-Charge Legal Prediction
  113. Robust and Safe Traffic Sign Recognition using N-version with Weighted Voting
  114. SemRaFiner: Panoptic Segmentation in Sparse and Noisy Radar Point Clouds
  115. SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN
  116. Developing and Maintaining an Open-Source Repository of AI Evaluations: Challenges and Insights
  117. A Single-Point Measurement Framework for Robust Cyber-Attack Diagnosis in Smart Microgrids Using Dual Fractional-Order Feature Analysis
  118. Horizontal and Vertical Federated Causal Structure Learning via Higher-order Cumulants
  119. Winning and losing with Artificial Intelligence: What public discourse about ChatGPT tells us about how societies make sense of technological change
  120. Conformal Prediction for Long-Tailed Classification
  121. Episodic Contextual Bandits with Knapsacks under Conversion Models
  122. Longitudinal Study of Facial Biometrics at the BEZ: Temporal Variance Analysis
  123. IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization
  124. SCC-recursiveness in infinite argumentation (extended version)
  125. OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
  126. Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation
  127. Adaptive collaboration for online personalized distributed learning with heterogeneous clients
  128. Scalable Gaussian Processes: Advances in Iterative Methods and Pathwise Conditioning
  129. Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation
  130. Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data
  131. HeLo: Heterogeneous Multi-Modal Fusion with Label Correlation for Emotion Distribution Learning
  132. Comprehensive Evaluation of Prototype Neural Networks
  133. Designing Robust Software Sensors for Nonlinear Systems via Neural Networks and Adaptive Sliding Mode Control
  134. HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement
  135. Intrinsic Training Signals for Federated Learning Aggregation
  136. Democratizing High-Fidelity Co-Speech Gesture Video Generation
  137. GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction
  138. Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams
  139. Speech Tokenizer is Key to Consistent Representation
  140. Comparing Dialectical Systems: Contradiction and Counterexample in Belief Change (Extended Version)
  141. Unlocking Thermal Aerial Imaging: Synthetic Enhancement of UAV Datasets
  142. ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining
  143. Temporal Information Retrieval via Time-Specifier Model Merging
  144. Tailoring deep learning for real-time brain-computer interfaces: From offline models to calibration-free online decoding
  145. Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
  146. Checklist Engineering Empowers Multilingual LLM Judges
  147. Robust Deep Network Learning of Nonlinear Regression Tasks by Parametric Leaky Exponential Linear Units (LELUs) and a Diffusion Metric
  148. Fast Equivariant Imaging: Accelerating Unsupervised Learning and Model Adaptation via Inexact Splitting
  149. FOLC-Net: A Federated-Optimized Lightweight Architecture for Enhanced MRI Disease Diagnosis across Axial, Coronal, and Sagittal Views
  150. KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
  151. Mathematical artificial data for operator learning
  152. LOVON: Legged Open-Vocabulary Object Navigator
  153. Dual-Granularity Cross-Modal Identity Association for Weakly-Supervised Text-to-Person Image Matching
  154. PromptTea: Let Prompts Tell TeaCache the Optimal Threshold
  155. Residual Prior-driven Frequency-aware Network for Image Fusion
  156. Civil Society in the Loop: Feedback-Driven Adaptation of (L)LM-Assisted Classification in an Open-Source Telegram Monitoring Tool
  157. MADPOT: Medical Anomaly Detection with CLIP Adaptation and Partial Optimal Transport
  158. Hierarchical Feature Alignment for Gloss-Free Sign Language Translation
  159. stCEG: An R Package for Modelling Events over Spatial Areas Using Chain Event Graphs
  160. On the Effect of Uncertainty on Layer-wise Inference Dynamics
  161. PINN-Obs: Physics-Informed Neural Network-Based Observer for Nonlinear Dynamical Systems
  162. Heterogeneous Graph Neural Networks for Short-term State Forecasting in Power Systems across Domains and Time Scales: A Hydroelectric Power Plant Case Study
  163. StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception
  164. Photometric Stereo using Gaussian Splatting and inverse rendering
  165. Fast Gaussian Processes under Monotonicity Constraints
  166. FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
  167. MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning
  168. Elite Polarization in European Parliamentary Speeches: a Novel Measurement Approach Using Large Language Models
  169. Non-asymptotic confidence regions on RKHS. The Paley-Wiener and standard Sobolev space cases
  170. MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
  171. Federated Learning Inspired Fuzzy Systems: Decentralized Rule Updating for Privacy and Scalable Decision Making
  172. Deep Disentangled Representation Network for Treatment Effect Estimation
  173. ClipGS: Clippable Gaussian Splatting for Interactive Cinematic Visualization of Volumetric Medical Data
  174. Learning from Sparse Point Labels for Dense Carcinosis Localization in Advanced Ovarian Cancer Assessment
  175. EXAONE Path 2.0: Pathology Foundation Model with End-to-End Supervision
  176. Adaptively Truncated Signature-based Logistic Regression for Semi-parametric Functional Classification
  177. Prevention of Overfitting on Mesh-Structured Data Regressions with a Modified Laplace Operator
  178. Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
  179. Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior
  180. UniOD: A Universal Model for Outlier Detection across Diverse Domains
  181. Expediting data extraction using a large language model (LLM) and scoping review protocol: a methodological study within a complex scoping review
  182. FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation
  183. Steps Adaptive Decay DPSGD: Enhancing Performance on Imbalanced Datasets with Differential Privacy with HAM10000
  184. PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentation
  185. Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation
  186. Omni-Fusion of Spatial and Spectral for Hyperspectral Image Segmentation
  187. Cross-Modal Dual-Causal Learning for Long-Term Action Recognition
  188. Capturing Stable HDR Videos Using a Dual-Camera System
  189. Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning
  190. Learning controllable dynamics through informative exploration
  191. Airway Segmentation Network for Enhanced Tubular Feature Extraction
  192. Enhancing Food-Domain Question Answering with a Multimodal Knowledge Graph: Hybrid QA Generation and Diversity Analysis
  193. Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection
  194. A Mathematical Theory of Discursive Networks
  195. SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments
  196. DS@GT at CheckThat! 2025: Exploring Retrieval and Reranking Pipelines for Scientific Claim Source Retrieval on Social Media Discourse
  197. Divergence-Based Similarity Function for Multi-View Contrastive Learning
  198. The Primacy of Magnitude in Low-Rank Adaptation
  199. On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
  200. Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs
  201. Token Bottleneck: One Token to Remember Dynamics
  202. On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning
  203. Graph-based Fake Account Detection: A Survey
  204. Large Language Model for Extracting Complex Contract Information in Industrial Scenes
  205. Few-shot Learning on AMS Circuits and Its Application to Parasitic Capacitance Prediction
  206. A model-agnostic active learning approach for animal detection from camera traps
  207. Transferable Parasitic Estimation via Graph Contrastive Learning and Label Rebalancing in AMS Circuits
  208. From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions
  209. ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture
  210. Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animation
  211. AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
  212. Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies
  213. Instance-Wise Monotonic Calibration by Constrained Transformation
  214. What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies
  215. Towards LLM-based Root Cause Analysis of Hardware Design Failures
  216. Prediction-Augmented Mechanism Design for Weighted Facility Location
  217. On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
  218. Mask6D: Masked Pose Priors For 6D Object Pose Estimation
  219. Stochastic Alignments: Matching an Observed Trace to Stochastic Process Models
  220. Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning
  221. SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam
  222. Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm
  223. EA: An Event Autoencoder for High-Speed Vision Sensing