mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 19 Feb 2026

329 papers

  1. DIALECTIC: A Multi-Agent System for Startup EvaluationLLM agents and tool use → Financial trading and forecasting agents
  2. ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMsLLM agents and tool use → Software engineering coding agents +1
  3. AI Agents Alone Are Not (Yet) Sufficient for Social SimulationLLM agents and tool use → Social simulation and multi-agent debate
  4. Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard vs. Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  5. El Agente Gr'afico: A Semantic Execution Runtime for Scientific AgentsLLM agents and tool use → Medical and scientific domain agents
  6. MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and AnalysisDiffusion models → Medical imaging and segmentation
  7. Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear ApproximationsMechanistic interpretability → Activation steering methods
  8. MultiVer: Zero-Shot Multi-Agent Vulnerability DetectionLLM agents and tool use → Agent threats, guardrails and governance
  9. Understanding the Fine-Grained Knowledge Capabilities of Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  10. Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  11. Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based SystemsRetrieval-augmented generation → Agentic RAG, agents and memory
  12. Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  13. MePoly: Max Entropy Polynomial Policy OptimizationOffline RL and imitation learning from data → Inverse reinforcement learning +1
  14. The Token Games: Evaluating Language Model Reasoning with Puzzle DuelsLLM reasoning → Reasoning benchmarks and evaluation
  15. Drift Estimation for Stochastic Differential Equations with Denoising Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  16. Enabling Training-Free Text-Based Remote Sensing SegmentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace ManifoldsMixture-of-experts → Expert routing strategies
  18. Learning Flow Distributions via Projection-Constrained Diffusion on ManifoldsDiffusion models → Flow matching, time series and science
  19. The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  20. Bayesian Optimality of In-Context Learning with Selective State SpacesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  21. Reasoning-Native Agentic Communication for 6GLLM agents and tool use → Agentic AI for wireless networks
  22. OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial AgentsLLM reasoning → Spatial and embodied reasoning
  23. Sink-Aware Pruning for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  24. When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAsVision-language-action models → Failure recovery and robustness
  25. MARS: Margin and Semantic-Aware Data Augmentation for Reward ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  26. Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail TargetingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  27. When to Trust the Cheap Check: Weak and Strong Verification for ReasoningLLM reasoning → Test-time compute and efficient thinking
  28. SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online TransferOffline RL and imitation learning from data → Offline RL algorithms +1
  29. What Makes a Good LLM Agent for Real-world Penetration Testing?LLM agents and tool use → Agent threats, guardrails and governance
  30. Towards Anytime-Valid Statistical WatermarkingLLM safety and security → Watermarking generated content and models
  31. AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific ComputingLLM agents and tool use → Web, search, and research agents
  32. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion ModelsDiffusion models → Flow matching, time series and science
  33. Modeling Distinct Human Interaction in Web AgentsLLM agents and tool use → Web, search, and research agents
  34. Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral SpaceDiffusion models → Diffusion and flow policies for robotics
  35. Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot TuningKnowledge distillation → General knowledge distillation methods
  36. ODESteer: A Unified ODE-Based Steering Framework for LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  37. RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist RewardMultimodal LLMs / vision-language models → Image editing and quality assessment +2
  38. GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph ThinkingLLM reasoning → Multimodal reasoning
  39. MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  40. KLong: Training LLM Agent for Extremely Long-horizon TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Evaluating Chain-of-Thought Reasoning through Reusability and VerifiabilityLLM reasoning → Prompting and chain-of-thought reasoning +1
  42. LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMsMultimodal LLMs / vision-language models → Medical vision-language models
  43. Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory SignalMechanistic interpretability → Interpreting biomedical and science models
  44. Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  45. A Picture of Agentic SearchLLM agents and tool use → Web, search, and research agents
  46. Variational Grey-Box Dynamics MatchingDiffusion models → Flow matching, time series and science
  47. EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  48. 2Mamba2Furious: Linear in Complexity, Competitive in AccuracyState-space sequence models (S4, Mamba) → Vision Mamba backbones
  49. PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email WritingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  50. LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward HierarchyOffline RL and imitation learning from data → Safe offline RL
  51. MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questionsLLM agents and tool use → Medical and scientific domain agents
  52. ArXiv-to-Model: A Practical Study of Scientific LM TrainingLLM reasoning → Reasoning benchmarks and evaluation
  53. RLGT: A reinforcement learning framework for extremal graph theoryDeep reinforcement learning methods → RL for games and combinatorial optimization
  54. Unified Latents (UL): How to train your latentsDiffusion models → Diffusion foundations and sampling
  55. FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation AlignmentWorld models → Embodied and robot world models +1
  56. Web Agents Should Use Typed Actions Instead of Click-Based BrowsingLLM agents and tool use → Web, search, and research agents
  57. Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's TaxonomyMechanistic interpretability → Knowledge and representations inside LLMs
  58. Continual learning and refinement of causal models through dynamic predicate inventionWorld models → World models for language agents
  59. MGD: Moment Guided Diffusion for Maximum Entropy GenerationDiffusion models → Diffusion foundations and sampling
  60. EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  61. Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information GainMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  62. Robustness and Reasoning Fidelity of Large Language Models in Long-Context Code Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
  63. BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive LearningLLM safety and security → Backdoor and data poisoning attacks
  64. The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AILLM reasoning → Reasoning for agents, planning and code
  65. AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance OptimizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  67. Agentic Wireless Communication for 6G: Intent-Aware and Continuously Evolving Physical-Layer IntelligenceLLM agents and tool use → Agentic AI for wireless networks
  68. What to Cut? Predicting Unnecessary Methods in Agentic Code GenerationLLM agents and tool use → Software engineering coding agents
  69. Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure ModelingDiffusion models → Flow matching, time series and science
  70. MeGU: Machine-Guided Unlearning with Target Feature DisentanglementLLM safety and security → Machine unlearning
  71. Dynamic Decision-Making under Model Misspecification: A Stochastic Stability ApproachDeep reinforcement learning methods → RL theory and sample complexity
  72. How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review ResponsesLLM agents and tool use → Software engineering coding agents
  73. BankMathBench: A Benchmark for Numerical Reasoning in Banking ScenariosLLM reasoning → Reasoning for agents, planning and code
  74. RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  75. IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. Amber-Image: Efficient Compression of Large-Scale Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  77. Phase-Aware Mixture of Experts for Agentic Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  78. Wink: Recovering from Misbehaviors in Coding AgentsLLM agents and tool use → Software engineering coding agents
  79. PartRAG: Retrieval-Augmented Part-Level 3D Generation and EditingRetrieval-augmented generation → Multimodal RAG
  80. Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative PaintingsLLM agents and tool use → Multimodal and embodied agents
  81. WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient ReasoningLLM reasoning → Reinforcement learning for reasoning
  82. ReIn: Conversational Error Recovery with Reasoning InceptionLLM reasoning → Reasoning benchmarks and evaluation
  83. Arcee Trinity Large Technical ReportMixture-of-experts → Efficient MoE training and inference systems
  84. Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User HistoryLLM reasoning → Reasoning for agents, planning and code +1
  85. Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  86. A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agentsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  87. Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable ModelingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  88. Fail-Closed Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  89. DDiT: Dynamic Patch Scheduling for Efficient Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  90. HalalBench: A Multilingual OCR Benchmark for Food Packaging Ingredient Extraction
  91. Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
  92. OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
  93. The IJCNN 2025 Review Process
  94. A Hybrid Tsallis-Polarization Impurity Measure for Decision Trees: Theoretical Foundations and Empirical Evaluation
  95. CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
  96. Valid Feature-Level Inference for Tabular Foundation Models via the Conditional Randomization Test
  97. Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark
  98. ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learning
  99. ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation
  100. A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification
All 329
  1. Automated Quality Check of Sensor Data Annotations
  2. Catalyzing Informed Residential Energy Retrofit Decisions via Domain-Specific LLM
  3. The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure
  4. AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals
  5. Sketch2Feedback: Grammar-in-the-Loop Framework for Rubric-Aligned Feedback on Student STEM Diagrams
  6. Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data
  7. Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling
  8. Weak-Form Evolutionary Kolmogorov-Arnold Networks for Solving Partial Differential Equations
  9. Beyond Pass-by-Pass Optimization: Intent-Driven IR Optimization with Large Language Models
  10. Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
  11. Learning from Biased and Costly Data Sources: Minimax-optimal Data Collection under a Budget
  12. COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models
  13. Machine Learning Based Prediction of Surgical Outcomes in Chronic Rhinosinusitis from Clinical Data
  14. Interactive Learning of Single-Index Models via Stochastic Gradient Descent
  15. MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
  16. ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
  17. Financial time series augmentation using transformer based GAN architecture
  18. JAX-Privacy: A library for differentially private machine learning
  19. TopoGate: Quality-Aware Topology-Stabilized Gated Fusion for Longitudinal Low-Dose CT New-Lesion Prediction
  20. On the Evaluation Protocol of Gesture Recognition for UAV-based Rescue Operation based on Deep Learning: A Subject-Independence Perspective
  21. Neural Prior Estimation: Learning Class Priors from Latent Representations
  22. Mind the Style: Impact of Communication Style on Human-Chatbot Interaction
  23. Quad Length Codes for Lossless Compression of e4m3
  24. On the scaling relationship between cloze probabilities and language model next-token prediction
  25. TFL: Targeted Bit-Flip Attack on Large Language Model
  26. Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
  27. Causality by Abstraction: Symbolic Rule Learning in Multivariate Timeseries with Large Language Models
  28. Avoid What You Know: Divergent Trajectory Balance for GFlowNets
  29. Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge
  30. Neural Synchrony Between Socially Interacting Language Models
  31. VQPP: Video Query Performance Prediction Benchmark
  32. Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineation
  33. Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning
  34. VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
  35. Deep Learning for Dermatology: An Innovative Framework for Approaching Precise Skin Cancer Detection
  36. LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge
  37. Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
  38. Multi-Modal Monocular Endoscopic Depth and Pose Estimation with Edge-Guided Self-Supervision
  39. QueryPlot: Generating Geological Evidence Layers using Natural Language Queries for Mineral Exploration
  40. Multi-material Multi-physics Topology Optimization with Physics-informed Gaussian Process Priors
  41. Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval
  42. Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
  43. Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method
  44. Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance
  45. CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild
  46. KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding
  47. Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring
  48. Inelastic Constitutive Kolmogorov-Arnold Networks: A generalized framework for automated discovery of interpretable inelastic material models
  49. Detection and Classification of Cetacean Echolocation Clicks using Image-based Object Detection Methods applied to Advanced Wavelet-based Transformations
  50. AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice
  51. Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity
  52. GeneZip: Region-Aware Compression for Long Context DNA Modeling
  53. CLEF HIPE-2026: Evaluating Accurate and Efficient Person-Place Relation Extraction from Multilingual Historical Texts
  54. What Language is This? Ask Your Tokenizer
  55. Mine and Refine: Optimizing Graded Relevance in E-commerce Semantic Search Retrieval
  56. Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking
  57. Human-level 3D shape perception emerges from multi-view learning
  58. Multi-Round Human-AI Collaboration with User-Specified Requirements
  59. A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning
  60. FAMOSE: A ReAct Approach to Automated Feature Discovery
  61. IntRec: Intent-based Retrieval with Contrastive Refinement
  62. CORAL: Correspondence Alignment for Improved Virtual Try-On
  63. Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
  64. Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning
  65. Unmasking the Factual-Conceptual Gap in Persian Language Models
  66. Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
  67. Guarding the Middle: Protecting Intermediate Representations in Federated Split Learning
  68. Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery
  69. SOLVAR: Fast covariance-based heterogeneity analysis with pose refinement for cryo-EM
  70. Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment
  71. The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASRrightarrowLLM Pipelines?
  72. From Approximation Rates to Loss-Landscape Barrier Decay in Shallow ReLU Networks
  73. AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
  74. Asymptotically Optimal Sequential Testing with Markovian Data
  75. Canonicalizing Multimodal Contrastive Representation Learning
  76. Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction
  77. FR-GESTURE: An RGBD Dataset For Gesture-based Human-Robot Interaction In First Responder Operations
  78. Be Wary of Your Time Series Preprocessing
  79. A Hybrid Federated Learning Based Ensemble Approach for Lung Disease Diagnosis Leveraging Fusion of SWIN Transformer and CNN
  80. Revisiting Weight Regularization for Low-Rank Continual Learning
  81. Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis
  82. Neural Implicit Representations for 3D Synthetic Aperture Radar Imaging
  83. A Theoretical Framework for Modular Learning of Robust Generative Models
  84. Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
  85. Adaptive Decentralized Composite Optimization via Three-Operator Splitting
  86. genriesz: A Python Package for Automatic Debiased Machine Learning with Generalized Riesz Regression
  87. Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems
  88. IRIS: Learning-Driven Task-Specific Cinema Robot Arm for Visuomotor Motion Control
  89. Toward a Fully Autonomous, AI-Native Particle Accelerator
  90. Position: Evaluation of ECG Representations Must Be Fixed
  91. Provably Explaining Neural Additive Models
  92. The Anxiety of Influence: Bloom Filters in Transformer Attention Heads
  93. Variational inference via radial transport
  94. Depth Augmented and FE Free 3D/2D Liver Registration for Laparoscopic Liver AR
  95. Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics
  96. LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
  97. Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems
  98. Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
  99. Learning with Boolean threshold functions
  100. Linear Convergence in Games with Delayed Feedback via Extra Prediction
  101. Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection
  102. What Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal Data
  103. QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery
  104. Small LLMs for Medical NLP: a Systematic Analysis of Few-Shot, Constraint Decoding, Fine-Tuning and Continual Pre-Training in Italian
  105. 4D Monocular Surgical Reconstruction under Arbitrary Camera Motions
  106. Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
  107. PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions
  108. Entropy-Based Data Selection for Language Models
  109. Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
  110. Beyond Pipelines: A Fundamental Study on the Rise of Generative-Retrieval Architectures in Web Research
  111. ABCD: All Biases Come Disguised
  112. AIDG: A Formal Decomposition of Information Extraction and Containment Asymmetries in Multi-Turn LLM Dialogue
  113. WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
  114. Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
  115. Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics
  116. Diverse Word Choices, Same Reference: Annotating Lexically-Rich Cross-Document Coreference
  117. Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking
  118. A Privacy by Design Framework for Large Language Model-Based Applications for Children
  119. DAVE: A Policy-Enforcing LLM Spokesperson for Secure Multi-Document Data Sharing
  120. Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layers
  121. A Contrastive Variational AutoEncoder for NSCLC Survival Prediction with Missing Modalities
  122. A High-Level Survey of Optical Remote Sensing
  123. SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
  124. Voice-Driven Semantic Perception for UAV-Assisted Emergency Networks
  125. DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition
  126. Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval
  127. Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
  128. Corpus Prevalence of Multiple-Choice Question Options
  129. MDP Planning as Policy Inference
  130. Tree crop mapping of South America reveals links to deforestation and conservation
  131. RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering
  132. A feature-stable and explainable machine learning framework for trustworthy decision-making under incomplete clinical data
  133. Application and Evaluation of the Common Circles Method
  134. Shortcut learning in geometric knot classification
  135. Partial Optimality in the Preordering Problem
  136. What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
  137. From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
  138. Polaffini: A feature-based approach for robust affine and polyaffine image registration
  139. SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework
  140. WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval
  141. Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline
  142. The Sound of Death: Deep Learning Reveals Vascular Damage from Carotid Ultrasound
  143. Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation
  144. Flickering Multi-Armed Bandits
  145. Open Datasets in Learning Analytics: Trends, Challenges, and Best PRACTICE
  146. Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery
  147. Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
  148. Efficient privacy loss accounting for subsampling and random allocation
  149. Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
  150. Quantum Scrambling Born Machine
  151. Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution
  152. Gaussian Surrogates for Poisson Imaging: Some Theoretical and Empirical Results
  153. Federated Latent Space Alignment for Multi-user Semantic Communications
  154. Learning a Latent Pulse Shape Interface for Photoinjector Laser Systems
  155. Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study
  156. EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection
  157. A Multi-modal Detection System for Infrastructure-based Freight Signal Priority
  158. SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels
  159. Inferring Height from Earth Embeddings: First insights using Google AlphaEarth
  160. CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
  161. TAPO-Structured Description Logic for Information Behavior: Procedural and Oracle-Based Extensions
  162. All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting
  163. HiMAP: History-aware Map-occupancy Prediction with Fallback
  164. Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
  165. Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight
  166. From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences
  167. Extending quantum theory with AI-assisted deterministic game theory
  168. SoftDTW-CUDA-Torch: Memory-Efficient GPU-Accelerated Soft Dynamic Time Warping for PyTorch
  169. Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
  170. GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
  171. What Makes a Good Doctor Response? A Study on Text-Based Telemedicine
  172. Texo: Formula Recognition within 20M Parameters
  173. Anti-causal domain generalization: Leveraging unlabeled data
  174. The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions
  175. NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting
  176. NextCrystal: a Symmetry-Driven Generative Framework for Crystal Structure Prediction
  177. Continual Uncertainty Learning for Robust Control of Nonlinear Systems with Multiple Heterogeneous Uncertainties
  178. In-Context Learning in Linear vs. Quadratic Attention Models: An Empirical Study on Regression Tasks
  179. JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures
  180. Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
  181. TimeOmni-VL: Unified Models for Time Series Understanding and Generation
  182. Bonsai: A Framework for Convolutional Neural Network Acceleration Using Criterion-Based Pruning
  183. When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
  184. B3-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates
  185. VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation
  186. Efficient Parallel Algorithm for Decomposing Hard CircuitSAT Instances
  187. 3D Scene Rendering with Multimodal Gaussian Splatting
  188. TIFO: Time-Invariant Frequency Operator for Stationarity-Aware Representation Learning in Time Series
  189. i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting
  190. Epistemology of Generative AI: The Geometry of Knowing
  191. Semi-Supervised Learning on Graphs using Graph Neural Networks
  192. Instructor-Aligned Knowledge Graphs for Personalized Learning
  193. Projective Psychological Assessment of Large Multimodal Models Using Thematic Apperception Tests
  194. Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
  195. Toward Trustworthy Evaluation of Sustainability Rating Methodologies: A Human-AI Collaborative Framework for Benchmark Dataset Construction
  196. Simplify to Amplify: Achieving Information-Theoretic Bounds with Fewer Steps in Spectral Community Detection
  197. Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
  198. Operationalization of Machine Learning with Serverless Architecture: An Industrial Operationalization of Machine Learning with Serverless Architecture: An Industrial Implementation for Harmonized System Code Prediction
  199. Benchmarking the Effects of Object Pose Estimation and Reconstruction on Robotic Grasping Success
  200. FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment
  201. A Locality Radius Framework for Understanding Relational Inductive Bias in Database Learning
  202. ComptonUNet: A Deep Learning Model for GRB Localization with Compton Cameras under Noisy and Low-Statistic Conditions
  203. Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
  204. Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection
  205. AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation
  206. General sample size analysis for probabilities of causation: a delta method approach
  207. Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal control
  208. Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization
  209. Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
  210. Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
  211. Cholec80-port: A Geometrically Consistent Trocar Port Segmentation Dataset for Robust Surgical Scene Understanding
  212. ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning
  213. Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data
  214. Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders
  215. StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection
  216. Large Language Models Persuade Without Planning Theory of Mind
  217. LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation
  218. Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles
  219. Transforming Behavioral Neuroscience Discovery with In-Context Learning and AI-Enhanced Tensor Methods
  220. M2F: Automated Formalization of Mathematical Literature at Scale
  221. Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
  222. Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
  223. Exploring LLMs for User Story Extraction from Mockups
  224. Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation
  225. Fundamental Limits of Black-Box Safety Evaluation: Information-Theoretic and Computational Barriers from Latent Context Conditioning
  226. Discovering Universal Activation Directions for PII Leakage in Language Models
  227. HQFS: Hybrid Quantum Classical Financial Security with VQC Forecasting, QUBO Annealing, and Audit-Ready Post-Quantum Signing
  228. Early-Warning Signals of Grokking via Loss-Landscape Geometry
  229. A Unified Framework for Locality in Scalable MARL