mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 12 Nov 2025

404 papers

  1. SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector DatabasesRetrieval-augmented generation → RAG pipeline design and evaluation
  2. ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use DatasetLLM reasoning → Reasoning for agents, planning and code
  3. Reasoning: From Reflection to SolutionLLM reasoning → Test-time compute and efficient thinking
  4. Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate ControlMechanistic interpretability → Sparse autoencoder training and evaluation
  5. Target-Balanced Score DistillationDiffusion models → 3D, point cloud and scene generation
  6. Simple Vision-Language Math Reasoning via Rendered TextLLM reasoning → Multimodal reasoning +1
  7. Enhancing Reinforcement Learning in 3D Environments through Semantic Segmentation: A Case Study in ViZDoomDeep reinforcement learning methods → RL for robot locomotion and manipulation
  8. Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +3
  9. Doubly Debiased Test-Time Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  10. Hierarchical Schedule Optimization for Fast and Robust Diffusion Model SamplingDiffusion models → Diffusion foundations and sampling
  11. MPCM-Net: Multi-scale network integrates partial attention convolution with Mamba for ground-based cloud image segmentationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  12. CARScenes: Semantic VLM Dataset for Safe Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  13. Modeling and Predicting Multi-Turn Answer Instability in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  14. Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  15. SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal PresentationsLLM agents and tool use → Multimodal and embodied agents
  16. Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  17. Evaluating Software Process Models for Multi-Agent Class-Level Code GenerationLLM agents and tool use → Software engineering coding agents
  18. A Robust Task-Level Control Architecture for Learned Dynamical SystemsOffline RL and imitation learning from data → Robot learning from demonstration
  19. Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPOLLM reasoning → Reinforcement learning for reasoning
  20. FlowCast: Advancing Precipitation Nowcasting with Conditional Flow MatchingDiffusion models → Flow matching, time series and science
  21. Baby Sophia: A Developmental Approach to Self-Exploration through Self-Touch and Hand RegardDeep reinforcement learning methods → RL for robot locomotion and manipulation
  22. Echoing: Identity Failures when LLM Agents Talk to Each OtherLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. Order Matters: Rethinking Prompt Construction in In-Context LearningLLM reasoning → Reasoning benchmarks and evaluation
  24. ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  25. Rebellion: Noise-Robust Reasoning Training for Audio Reasoning ModelsLLM reasoning → Audio-language model reasoning +1
  26. SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  27. Statistically Consistent Approximate Model Predictive ControlOffline RL and imitation learning from data → Imitation learning methods
  28. Optimistic Reinforcement Learning with Quantile ObjectivesDeep reinforcement learning methods → RL theory and sample complexity
  29. MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and GenerationDiffusion models → Image generation, text-to-image and editing
  30. Bridging the Data Gap: Spatially Conditioned Diffusion Model for Anomaly Generation in Photovoltaic Electroluminescence ImagesDiffusion models → Flow matching, time series and science
  31. Environment Scaling for Interactive Agentic Experience Collection: A SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. HeatGen: A Guided Diffusion Framework for Multiphysics Heat Sink Design OptimizationDiffusion models → Flow matching, time series and science
  33. Proceedings of the Second International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2025)LLM reasoning → Reasoning benchmarks and evaluation
  34. vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMsMultimodal LLMs / vision-language models → Medical vision-language models
  35. SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim VerificationSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  36. Digital Co-Founders: Transforming Imagination into Viable Solo Business via Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  37. MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  38. WMPO: World Model-based Policy Optimization for Vision-Language-Action ModelsWorld models → Embodied and robot world models +1
  39. Quasi-Newton Compatible Actor-Critic for Deterministic PoliciesDeep reinforcement learning methods → RL theory and sample complexity
  40. AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree SearchSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  41. CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  42. AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical RevisitingLLM reasoning → Reinforcement learning for reasoning +1
  43. Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video ModelsKnowledge distillation → General knowledge distillation methods
  44. Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and DeletionsDiffusion models → Flow matching, time series and science
  45. Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric DataMechanistic interpretability → Sparse autoencoder training and evaluation
  46. Probing then Editing: A Push-Pull Framework for Retain-Free Machine Unlearning in Industrial IoTLLM safety and security → Machine unlearning
  47. Spatio-Temporal Graph UnlearningLLM safety and security → Graph unlearning
  48. Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential PrivacyLLM safety and security → Backdoor and data poisoning attacks
  49. Multimodal Large Language Models for Low-Resource Languages: A Case Study for BasqueMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  50. EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in OphthalmologyLLM agents and tool use → Medical and scientific domain agents
  51. Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement ParadigmDeep reinforcement learning methods → RL training of language and agent models
  52. AMaPO: Adaptive Margin-attached Preference Optimization for Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  53. Self-Correcting Large Language Models: Generation vs. Multiple ChoiceLLM reasoning → Test-time compute and efficient thinking
  54. Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  55. mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  56. DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
  57. UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  58. Enriching Knowledge Distillation with Cross-Modal Teacher FusionKnowledge distillation → Multimodal distillation
  59. Decoding the Configuration of AI Coding Agents: Insights from Claude Code ProjectsLLM agents and tool use → Software engineering coding agents
  60. Taming Object Hallucinations with Verified Atomic Confidence EstimationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  61. Toward Honest Language Models for Deductive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  62. Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  63. Controllable protein design with particle-based Feynman-Kac steeringDiffusion models → Flow matching, time series and science
  64. Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic NarrativesMultimodal LLMs / vision-language models → Medical vision-language models
  65. DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?Diffusion models → Image generation, text-to-image and editing
  66. FSampler: Training Free Acceleration of Diffusion Sampling via Epsilon ExtrapolationDiffusion models → Diffusion foundations and sampling
  67. Perspectives on a Reliability Monitoring Framework for Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  68. Target-Aligned Fusion for Decision-Sequence Learning under Dynamics ShiftOffline RL and imitation learning from data → Decision transformers and sequence modeling
  69. Efficient Reasoning via Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
  70. ProBench: Benchmarking GUI Agents with Accurate Process InformationLLM agents and tool use → GUI and mobile agents
  71. Enabling Agents to Communicate Entirely in Latent SpaceLLM agents and tool use → General LLM agent frameworks and benchmarks
  72. History-Aware Reasoning for GUI AgentsLLM reasoning → Multimodal reasoning +2
  73. Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code GenerationLLM agents and tool use → Software engineering coding agents
  74. Towards a Generalisable Cyber Defence Agent for Real-World Computer NetworksDeep reinforcement learning methods → Adversarial robustness and RL in finance
  75. Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  76. Cost-Minimized Label-Flipping Poisoning Attack to LLM AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  77. Ultra-Light Test-Time Adaptation for Vision--Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  78. OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  79. Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music GenerationDiffusion models → Audio, speech and music
  80. Tele-LLM-Hub: Building Context-Aware Multi-Agent LLM Systems for Telecom NetworksLLM agents and tool use → Agentic AI for wireless networks
  81. MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal CritiqueMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  82. Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP InferenceMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  83. Human-Corrected Labels Learning: Enhancing Labels Quality via Human Correction of VLMs DiscrepanciesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  84. VietMEAgent: Culturally-Aware Few-Shot Multimodal Explanation for Vietnamese Visual Question AnsweringLLM reasoning → Multimodal reasoning
  85. PAN: A World Model for General, Actionable, and Long-Horizon World SimulationWorld models → World models for language agents
  86. 4KDehazeFlow: Ultra-High-Definition Image Dehazing via Flow MatchingDiffusion models → Inverse problems and image restoration
  87. Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  88. Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSsEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  89. FLAD: Federated Learning for LLM-based Autonomous Driving in Vehicle-Edge-Cloud NetworksLLM reasoning → Chain-of-thought reasoning for driving +1
  90. Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  91. UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous DrivingEnd-to-end autonomous driving → Cooperative and V2X driving +1
  92. AI Founding Fathers: A Case Study of GIS Search in Multi-Agent PipelinesLLM reasoning → Reasoning for agents, planning and code +1
  93. WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus ImagesDiffusion models → Medical imaging and segmentation
  94. DeepTracer: Tracing Stolen Model via Deep Coupled WatermarksLLM safety and security → Watermarking generated content and models
  95. SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent InterleavingLLM reasoning → Test-time compute and efficient thinking
  96. Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  97. Efficient and Effective In-context Demonstration Selection with CoresetMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  98. Selective Sinkhorn Routing for Improved Sparse Mixture of ExpertsMixture-of-experts → Expert routing strategies
  99. Bayesian Mixture of Experts For Large Language ModelsMixture-of-experts → MoE large language models
  100. AuthSig: Safeguarding Scanned Signatures Against Unauthorized Reuse in Paperless WorkflowsLLM safety and security → Watermarking generated content and models
All 404
  1. AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series ForecastingLLM reasoning → Time series reasoning
  2. Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered ReasoningLLM reasoning → Spatial and embodied reasoning +1
  3. From Structure to Detail: Hierarchical Distillation for Efficient Diffusion ModelDiffusion models → Diffusion foundations and sampling
  4. TiDAR: Think in Diffusion, Talk in AutoregressionLLM reasoning → Diffusion reasoning and test-time scaling +2
  5. Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  6. "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM QuantizationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  8. iSeal: Encrypted Fingerprinting for Reliable LLM Ownership VerificationLLM safety and security → Watermarking generated content and models
  9. Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic ConsistencyKnowledge distillation → Multimodal distillation
  10. Lumine: An Open Recipe for Building Generalist Agents in 3D Open WorldsLLM agents and tool use → Reinforcement learning for LLM agents
  11. SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  12. BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis GenerationLLM agents and tool use → Medical and scientific domain agents
  13. Transforming User Defined Criteria into Explainable Indicators with an Integrated LLM AHP System
  14. Refined Bayesian Optimization for Efficient Beam Alignment in Intelligent Indoor Wireless Environments
  15. TIP and Polish: Text-Image-Prototype Guided Multi-Modal Generation via Commonality-Discrepancy Modeling and Refinement
  16. A centroid based framework for text classification in itsm environments
  17. Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward
  18. Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health
  19. Practical Machine Learning for Aphasic Discourse Analysis
  20. How Well Do LLMs Understand Tunisian Arabic?
  21. Bench360: Benchmarking Local LLM Inference from 360 Degrees
  22. Shona spaCy: A Morphological Analyzer for an Under-Resourced Bantu Language
  23. Chain of Summaries: Summarization Through Iterative Questioning
  24. Convex Clustering Redefined: Robust Learning with the Median of Means Estimator
  25. Human or LLM as Standardized Patients? A Comparative Study for Medical Education
  26. nuCarla: A nuScenes-Style Bird's-Eye View Perception Dataset for CARLA Simulation
  27. Review of Passenger Flow Modelling Approaches Based on a Bibliometric Analysis
  28. Blurred Encoding for Trajectory Representation Learning
  29. ECCENTRIC: Edge-Cloud Collaboration Framework for Distributed Inference Using Knowledge Adaptation
  30. Multiscale Grassmann Manifolds for Single-Cell Data Analysis
  31. CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition
  32. Federated Learning for Pediatric Pneumonia Detection: Enabling Collaborative Diagnosis Without Sharing Patient Data
  33. Understanding the Representation of Older Adults in Motion Capture Locomotion Datasets
  34. LE-CapsNet: A Light and Enhanced Capsule Network
  35. FSC-Net: Fast-Slow Consolidation Networks for Continual Learning
  36. Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental Modelling
  37. Multimodal ML: Quantifying the Improvement of Calorie Estimation Through Image-Text Pairs
  38. Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
  39. Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting
  40. EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance
  41. Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification
  42. Moirai 2.0: When Less Is More for Time Series Forecasting
  43. Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantification
  44. Toward Dignity-Aware AI: Next-Generation Elderly Monitoring from Fall Detection to ADL
  45. AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation
  46. Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues
  47. Generative AI Purpose-built for Social and Mental Health: A Real-World Pilot
  48. Does Scientific Writing Converge to U.S. English? Evidence from Generative AI-Assisted Publications
  49. Regularized Schr"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement
  50. R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models
  51. A Bayesian Model for Multi-stage Censoring
  52. Stratified Knowledge-Density Super-Network for Scalable Vision Transformers
  53. Generalized Inequality-based Approach for Probabilistic WCET Estimation
  54. Probabilistic Wildfire Susceptibility from Remote Sensing Using Random Forests and SHAP
  55. Free-Boundary Quasiconformal Maps via a Least-squares Operator in Diffeomorphism Optimization
  56. A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systems
  57. DualVision ArthroNav: Investigating Opportunities to Enhance Localization and Reconstruction in Image-based Arthroscopy Navigation via External Cameras
  58. π-Attention: Online Efficient Sparse Transformers for Long-Context Modeling
  59. "As Eastern Powers, I will veto." : An Investigation of Nation-level Bias of Large Language Models in International Relations
  60. Where does an LLM begin computing an instruction?
  61. Do AI Voices Learn Social Nuances? A Case of Politeness and Speech Rate
  62. Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models
  63. Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games
  64. Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data
  65. Robust Watermarking on Gradient Boosting Decision Trees
  66. From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance
  67. Improving Graduate Outcomes by Identifying Skills Gaps and Recommending Courses Based on Career Interests
  68. Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration
  69. Multiple Treatments Causal Effects Estimation with Task Embeddings and Balanced Representation Learning
  70. Khmer Spellchecking: A Holistic Approach
  71. On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks
  72. Constrained Best Arm Identification with Tests for Feasibility
  73. Generalized infinite dimensional Alpha-Procrustes based geometries
  74. Predicate-Argument Structure Divergences in Chinese and English Parallel Sentences and their Impact on Language Transfer
  75. Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning
  76. PANDA -- Patch And Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning
  77. Trend-Aware Multi-Task Learning for Short-Term Energy Forecasting
  78. Why Open Small AI Models Matter for Interactive Art
  79. AI Annotation Orchestration: Evaluating LLM verifiers to Improve the Quality of LLM Annotations in Learning Analytics
  80. Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures
  81. Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization
  82. Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction
  83. NeuroLingua: A Language-Inspired Hierarchical Framework for Multimodal Sleep Stage Classification Using EEG and EOG
  84. STORM: Segment, Track, and Object Re-Localization from a Single Image
  85. Structure tensor Reynolds-averaged Navier-Stokes turbulence models with equivariant neural networks
  86. ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias
  87. Modelos Empiricos de Pos-Dupla Selecao por LASSO: Discussoes para Estudos do Transporte Aereo
  88. Ksurf-Drone: Attention Kalman Filter for Contextual Bandit Optimization in Cloud Resource Allocation
  89. Brian Intensify: An Adaptive Machine Learning Framework for Auditory EEG Stimulation and Cognitive Enhancement in FXS
  90. Is nasty noise actually harder than malicious noise?
  91. Distributional Treatment Effect Transportability across Heterogeneous Sites
  92. History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting
  93. Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations
  94. How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation
  95. Feature Quality and Adaptability of Medical Foundation Models: A Comparative Evaluation for Radiographic Classification and Segmentation
  96. TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training
  97. Soiling detection for Advanced Driver Assistance Systems
  98. Assessing the Applicability of Natural Language Processing to Traditional Social Science Methodology: A Case Study in Identifying Strategic Signaling Patterns in Presidential Directives
  99. Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy
  100. Data Heterogeneity and Forgotten Labels in Split Federated Learning
  101. Social LSTM with Dynamic Occupancy Modeling for Realistic Pedestrian Trajectory Prediction
  102. A Fourier-Based Global Denoising Model for Smart Artifacts Removing of Microscopy Images
  103. Generalizing PDE Emulation with Equation-Aware Neural Operators
  104. The Data Fusion Labeler (dFL): Challenges and Solutions to Data Harmonization, Labeling, and Provenance in Fusion Energy
  105. PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model
  106. Density Estimation and Crowd Counting
  107. Masked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling
  108. SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control
  109. Contextual morphologically-guided tokenization for Latin encoder models
  110. Efficient Hyperdimensional Computing with Modular Composite Representations
  111. Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression
  112. Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
  113. Boosted GFlowNets: Improving Exploration via Sequential Learning
  114. PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild
  115. Lithological Controls on the Permeability of Geologic Faults: Surrogate Modeling and Sensitivity Analysis
  116. GEM+: Scalable State-of-the-Art Private Synthetic Data with Generator Networks
  117. Generalization Can Emerge in Tabular Foundation Models From a Single Table
  118. Alignment Debt: The Hidden Work of Making AI Usable
  119. Analysis of the TAIGA-HiSCORE Data Using the Latent Space of Autoencoders
  120. TomoGraphView: 3D Medical Image Classification with Omnidirectional Slice Representations and Graph Neural Networks
  121. An explainable Recursive Feature Elimination to detect Advanced Persistent Threats using Random Forest classifier
  122. Cogent argument extensions are weakly admissible but not vice versa
  123. FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning
  124. Amortized Multi-Objective Optimization Across Tasks with Generative Solution Modeling
  125. Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off
  126. DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior
  127. Siegel Neural Networks
  128. Prostate-VarBench: A Benchmark with Interpretable TabNet Framework for Prostate Cancer Variant Classification
  129. IFG: Internet-Scale Guidance for Functional Grasping Generation
  130. Understanding and Improving Communication Performance in Multi-node LLM Inference
  131. SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation
  132. RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
  133. Breadth-First Search vs. Restarting Random Walks for Escaping Uninformed Heuristic Regions
  134. NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages
  135. Readability Measures and Automatic Text Simplification: In the Search of a Construct
  136. Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
  137. SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins
  138. Event-Driven Digital-Time-Domain Inference Architectures for Tsetlin Machines
  139. GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences
  140. DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimation
  141. Distributional Shrinkage I: Universal Denoiser Beyond Tweedie's Formula
  142. Fundamentals of Physical AI
  143. Consensus Sampling for Safer Generative AI
  144. Enhancing Password Security Through a High-Accuracy Scoring Framework Using Random Forests
  145. PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness
  146. A general framework for adaptive nonparametric dimensionality reduction
  147. SPIDER: Scalable Physics-Informed Dexterous Retargeting
  148. Latent Planning via Embedding Arithmetic: A Contrastive Approach to Strategic Reasoning
  149. Enhancing Explainability in Solar Energetic Particle Event Prediction: A Global Feature Mapping Approach
  150. Hand Held Multi-Object Tracking Dataset in American Football
  151. Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets
  152. How does the Performance of the Data-driven Traffic Flow Forecasting Models deteriorate with Increasing Forecasting Horizon? An Extensive Approach Considering Statistical, Machine Learning and Deep Learning Models
  153. MCAD: Multimodal Context-Aware Audio Description Generation For Soccer
  154. BronchOpt : Vision-Based Pose Optimization with Fine-Tuned Foundation Models for Accurate Bronchoscopy Navigation
  155. LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning
  156. What We Don't C: Manifold Disentanglement for Structured Discovery
  157. Adversarially and Distributionally Robust Virtual Energy Storage Systems via the Scenario Approach
  158. BIG5-TPoT: Predicting BIG Five Personality Traits, Facets, and Items Through Targeted Preselection of Texts
  159. Supporting Evidence for the Adaptive Feature Program across Diverse Models
  160. Transformer Semantic Genetic Programming for d-dimensional Symbolic Regression Problems
  161. GSAP-ERE: Fine-Grained Scholarly Entity and Relation Extraction Focused on Machine Learning
  162. CARE-Bench: A Benchmark of Diverse Client Simulations Guided by Expert Principles for Evaluating LLMs in Psychological Counseling
  163. OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS
  164. Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
  165. Diffusion-based Sinogram Interpolation for Limited Angle PET
  166. Frontier Large Language Models Rival State-of-the-Art Planners
  167. From Decision Trees to Boolean Logic: A Fast and Unified SHAP Algorithm
  168. MTQ-Eval: Multilingual Text Quality Evaluation for Language Models
  169. Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks
  170. Augment to Augment: Diverse Augmentations Enable Competitive Ultra-Low-Field MRI Enhancement
  171. BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems
  172. Spider4SSC & S2CLite: A text-to-multi-query-language dataset using lightweight ontology-agnostic SPARQL to Cypher parser
  173. FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection
  174. Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
  175. GAMMA_FLOW: Guided Analysis of Multi-label spectra by MAtrix Factorization for Lightweight Operational Workflows
  176. Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
  177. MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment
  178. Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference
  179. AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
  180. A Tensor Residual Circuit Neural Network Factorized with Matrix Product Operation
  181. Towards Explainable Khmer Polarity Classification
  182. LiteraryTaste: A Preference Dataset for Creative Writing Personalization
  183. TaskSense: Cognitive Chain Modeling and Difficulty Estimation for GUI Tasks
  184. Efficiently Transforming Neural Networks into Decision Trees: A Path to Ground Truth Explanations with RENTT
  185. DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures
  186. GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks
  187. C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation
  188. Prediction horizon shapes representations in predictive learning
  189. From Model Training to Model Raising
  190. End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
  191. Deep Learning for Metabolic Rate Estimation from Biosignals: A Comparative Study of Architectures and Signal Selection
  192. HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting
  193. GRACE: Designing Generative Face Video Codec via Agile Hardware-Centric Workflow
  194. A Distributed Training Architecture For Combinatorial Optimization
  195. Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning
  196. MedFuse: Multiplicative Embedding Fusion For Irregular Clinical Time Series
  197. Robust Least-Squares Optimization for Data-Driven Predictive Control: A Geometric Approach
  198. Spatial Information Bottleneck for Interpretable Visual Recognition
  199. POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
  200. Leveraging Large Language Models for Use Case Model Generation from Software Requirements
  201. Learning Binary Autoencoder-Based Codes with Progressive Training
  202. Pretraining Finnish ModernBERTs
  203. Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)
  204. CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction
  205. Resource-Efficient Variational Quantum Classifier
  206. Stochastic Mean-Shift Clustering
  207. Sure! Here's a short and concise title for your paper: "Contamination in Generated Text Detection Benchmarks"
  208. The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages
  209. Enhancing PIBT via Multi-Action Operations
  210. Iterated Population Based Training with Task-Agnostic Restarts
  211. Scalable Mixed-Integer Optimization with Neural Constraints via Dual Decomposition
  212. Context is Enough: Empirical Validation of textitSequentiality on Essays
  213. A Hybrid Search for Complex Table Question Answering in Securities Report
  214. Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary Evidence
  215. HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests
  216. Compact Memory for Continual Logistic Regression
  217. Unsupervised Feature Selection Through Group Discovery
  218. LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
  219. PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh Recovery
  220. DoPE: Denoising Rotary Position Embedding
  221. Practical Global and Local Bounds in Gaussian Process Regression via Chaining
  222. MACEval: A Multi-Agent Continual Evaluation Network for Large Models
  223. Trusted Multi-view Learning for Long-tailed Classification
  224. One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning
  225. Assessing the Capabilities of LLMs in Humor:A Multi-dimensional Analysis of Oogiri Generation and Evaluation
  226. PIFF: A Physics-Informed Generative Flow Model for Real-Time Flood Depth Mapping
  227. Differentially Private Rankings via Outranking Methods and Performance Data Aggregation
  228. Learning to Validate Generative Models: a Goodness-of-Fit Approach
  229. DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization
  230. FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters
  231. Factorization-in-Loop: Proximal Fill-in Minimization for Sparse Matrix Reordering
  232. Improving Sustainability of Adversarial Examples in Class-Incremental Learning
  233. Context-Aware Dynamic Chunking for Streaming Tibetan Speech Recognition
  234. Composition-Incremental Learning for Compositional Generalization
  235. Good-for-MDP State Reduction for Stochastic LTL Planning
  236. SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields
  237. VAE-Based Synthetic EMG Generation with Mix-Consistency Loss for Recognizing Unseen Motion Combinations
  238. Break the Tie: Learning Cluster-Customized Category Relationships for Categorical Data Clustering
  239. Guaranteeing Conservation of Integrals with Projection in Physics-Informed Neural Networks
  240. USF-Net: A Unified Spatiotemporal Fusion Network for Ground-Based Remote Sensing Cloud Image Sequence Extrapolation
  241. Advancing Autonomous Emergency Response Systems: A Generative AI Perspective
  242. MedHE: Communication-Efficient Privacy-Preserving Federated Learning with Adaptive Gradient Sparsification for Healthcare
  243. GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs
  244. Fairness-Aware Few-Shot Learning for Audio-Visual Stress Detection
  245. FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
  246. Solving a Million-Step LLM Task with Zero Errors
  247. Dense Cross-Scale Image Alignment With Fully Spatial Correlation and Just Noticeable Difference Guidance
  248. DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome
  249. RadHARSimulator V2: Video to Doppler Generator
  250. Assumed Density Filtering and Smoothing with Neural Network Surrogate Models
  251. A Neurosymbolic Approach to Natural Language Formalization and Verification
  252. Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models
  253. Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation
  254. T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection
  255. Generalisable prediction model of surgical case duration: multicentre development and temporal validation
  256. Fast k-means clustering in Riemannian manifolds via Fr'echet maps: Applications to large-dimensional SPD matrices
  257. Robust Sampling for Active Statistical Inference
  258. An ICTM-RMSAV Framework for Bias-Field Aware Image Segmentation under Poisson and Multiplicative Noise
  259. Data reuse enables cost-efficient randomized trials of medical AI models
  260. Heterogeneous Graph Neural Networks for Assumption-Based Argumentation
  261. A Finite Difference Approximation of Second Order Regularization of Neural-SDFs
  262. Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
  263. MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction
  264. EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
  265. Improving Conditional VAE with Non-Volume Preserving transformations
  266. FGM-HD: Boosting Generation Diversity of Fractal Generative Models through Hausdorff Dimension Induction
  267. Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
  268. QIBONN: A Quantum-Inspired Bilevel Optimizer for Neural Networks on Tabular Classification
  269. TransactionGPT
  270. Neural B-frame Video Compression with Bi-directional Reference Harmonization
  271. Boosting Adversarial Transferability via Ensemble Non-Attention
  272. Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation
  273. A Research on Business Process Optimisation Model Integrating AI and Big Data Analytics
  274. The Double Contingency Problem: AI Recursion and the Limits of Interspecies Understanding
  275. Achieving Equilibrium under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning
  276. DeepDR: an integrated deep-learning model web server for drug repositioning
  277. ROI-based Deep Image Compression with Implicit Bit Allocation
  278. HalluClean: A Unified Framework to Combat Hallucinations in LLMs
  279. Machines Serve Human: A Novel Variable Human-machine Collaborative Compression Framework
  280. OG-PCL: Efficient Sparse Point Cloud Processing for Human Activity Recognition
  281. Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images
  282. HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing
  283. Consistency Change Detection Framework for Unsupervised Remote Sensing Change Detection
  284. LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
  285. Improving VisNet for Object Recognition
  286. Classifying Histopathologic Glioblastoma Sub-regions with EfficientNet
  287. Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting
  288. FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis
  289. Spectral Predictability as a Fast Reliability Indicator for Time Series Forecasting Model Selection
  290. Improve Contrastive Clustering Performance by Multiple Fusing-Augmenting ViT Blocks
  291. Covariance Scattering Transforms
  292. Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
  293. UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
  294. Conformal Prediction for Multi-Source Detection on a Network
  295. Transformer-Based Sleep Stage Classification Enhanced by Clinical Information
  296. EEG-X: Device-Agnostic and Noise-Robust Foundation Model for EEG
  297. When is a System Discoverable from Data? Discovery Requires Chaos
  298. ForeSWE: Forecasting Snow-Water Equivalent with an Uncertainty-Aware Attention Model
  299. Path Signatures Enable Model-Free Mapping of RNA Modifications
  300. Decomposition of Small Transformer Models
  301. Rethinking Graph Super-resolution: Dual Frameworks for Topological Fidelity
  302. DRL-Based Beam Positioning for LEO Satellite Constellations with Weighted Least Squares
  303. Measurement-Driven Early Warning for Resilient 5G NSA Railway Networks
  304. On topological descriptors for graph products