Papers

New on arXiv

Sat 18 Jul 2026

165 papers

Steal the Knowledge, Inherit the Mark: TwinMark for Distillation Watermarking via Second Moments and Class MultiplexingKnowledge distillation → Federated, robust and private distillation
WordPolo: Evaluating Language Models Through Iterative Semantic FeedbackLLM reasoning → Reasoning benchmarks and evaluation
Code Consistency Preference Optimization Verification for Language Model AlignmentLLM reasoning → Mathematical reasoning +1
PDD: Unleashing Economical and Flexible Heterogeneous LLM Inference via Cross-Datacenter Prefill-Decode DisaggregationEfficient LLM inference and serving → Serving systems and request scheduling
Scalable Causal Imitation LearningOffline RL and imitation learning from data → Imitation learning methods +1
Counterfactual Shapley Credit AssignmentDeep reinforcement learning methods → Interpretable and logic-guided RL
User-Driven Learning from Demonstration: A Trajectory and Impedance Learning MethodOffline RL and imitation learning from data → Robot learning from demonstration
TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious QuantizationRetrieval-augmented generation → Privacy and security of RAG
Training Continuous Chain of Thought Models: A Tale of Two RegimesLLM reasoning → Prompting and chain-of-thought reasoning
Lomekwi: Resource-Bounded Tool Discovery in LLM AgentsLLM agents and tool use → Tool learning and function calling
CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle LearningEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
Enhancing Personalized Bladder Cancer Treatment Through Reinforcement Learning: A Recurrent Patient State Transition Decision Support FrameworkDeep reinforcement learning methods → RL for clinical treatment and surgery
Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World ModelsWorld models → World models for language agents +1
TVGL-CFM:Generating and Forecasting Time-Varying Trajectories of Dynamic Networks with Conditional Flow MatchingDiffusion models → Flow matching, time series and science
A Deep Reinforcement Learning Algorithm for the Vehicle Routing Problem with Stochastic Demands and OutsourcingDeep reinforcement learning methods → RL for games and combinatorial optimization
Trace-Based On-Policy Distillation for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy EstimatorsDeep reinforcement learning methods → Deep RL algorithms and representations
AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM AgentsLLM agents and tool use → Educational agents and math problem solving
Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context RestorationLLM agents and tool use → Agent memory systems
Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual RealignmentMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image GenerationDiffusion models → Robustness, privacy and adversarial aspects
First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained TransformersMechanistic interpretability → Circuits and mechanistic analysis
RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent PlanningLLM agents and tool use → Agent skill learning and evolution
Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and ModelMixture-of-experts → Vision mixture-of-experts
Agentic Code Review in the Terminal: A Trajectory-Level Analysis of Behavior, Cost, and Human-AlignmentLLM agents and tool use → Software engineering coding agents
Constraint-Anchored Reasoning TracesLLM reasoning → Reasoning benchmarks and evaluation +1
Can Experts Adapt Without Training? On Test-Time Modality Generalization in MVLMsMultimodal LLMs / vision-language models → Medical vision-language models +1
Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for CodingMixture-of-experts → MoE large language models
RECON: Benchmarking Agent Memory for Compositional Reasoning over Long ContextsLLM reasoning → Reasoning for agents, planning and code +1
DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidance for Conversational Depression ScreeningLLM agents and tool use → Medical and scientific domain agents
Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System ModelsLLM agents and tool use → Software engineering coding agents
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMsMechanistic interpretability → Circuits and mechanistic analysis
Semi-Supervised Conditional Diffusion via Label AugmentationDiffusion models → Diffusion foundations and sampling
Specification-Driven Development as the Foundation of AI-Native Enterprise Software EngineeringLLM agents and tool use → Software engineering coding agents
CLDRoute: Conditional Latent Diffusion for Routability Map Generation in Physical DesignDiffusion models → Flow matching, time series and science
SpecLA: Efficient Speculative Decoding for Linear-Attention ModelsEfficient LLM inference and serving → Speculative decoding
DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-ResolutionDiffusion models → Medical imaging and segmentation
Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion ModelsLLM safety and security → Watermarking generated content and models
PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical ExecutionWorld models → World models for language agents +1
CLOSER-Bench: Evaluating Budgeted Cross-Stage Design Closure for Hardware AgentsLLM agents and tool use → Software engineering coding agents
Dynamic mean-variance portfolio selection with no-shorting constraints and unknown investment opportunity setsDeep reinforcement learning methods → Adversarial robustness and RL in finance
From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM AgentsLLM agents and tool use → Agent skill learning and evolution
Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine LearningLLM safety and security → Membership inference attacks
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data PipelinesLLM agents and tool use → Software engineering coding agents
Just A Rather Very Intelligent Spoken AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
Can Multimodal Large Language Models Understand OCT?Multimodal LLMs / vision-language models → Medical vision-language models
NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and ReasoningLLM reasoning → Reasoning for agents, planning and code
PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action ExplorationWorld models → Embodied and robot world models +1
Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RLWorld models → Latent dynamics models and model-based RL +1
Automating structural reliability analysis with a multi-agent large language model frameworkLLM agents and tool use → Multimodal and embodied agents
AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative IntelligenceMixture-of-experts → Efficient MoE training and inference systems
Modality Discrepancy Transformer for Ambivalence and Hesitancy Recognition
When Literature Data Mislead Artificial Intelligence in Materials Discovery
Gurukul AI: An Interactive AI-Driven Educational Platform for Indian Education System
Local AI pre-screening for human triple-blind peer review in health sciences
MIME: Multimodal Interactive Motion Encoder
RoleMix: Unifying Sequential and Non-Sequential Features via Semantic Tokenization for Post-Click Conversion Rate Prediction
Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
FogDrive: A Multi-Modal Synthetic Driving Dataset for Perception under Graded Fog
Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
CT-Merging: Consensus Directions and Task-Specific Scaling for LoRA Adapter Merging
Hazard or Anomaly? Evaluating VLMs for Understanding Dangers and Discrepancies
Cost Accounting for Reactive Computational Graphs: Exhaustive Sweeps, Sequential Mutation, and the Backward-Locality Gap
Increasing Line Outage Localization Performance with Ensemble Classifiers
PriorProof: A Point-in-Time Measure of Technique Novelty for Formal Proofs
Automated Cardiac Adipose Tissue Segmentation in Computed Tomography: A Literature Review
Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
Twisted Schr"odinger Bridge Matching
Periodic Bootstrap Thompson Sampling For Periodically Non-Stationary Bandit Problems
Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
SurvCF(t): Counterfactual Explanations for Survival Analysis in Predictive Maintenance Multivariate Time Series Data
Tight Sample Bounds for Renyi and Min-Entropy Estimation
Points as Tori: Fast Pointwise Signed Distance for Point Clouds
Investigation of Polycystic Ovary Syndrome (PCOS) Diagnosis Using Machine Learning Approaches
Pediatric Bone Age Prediction Using Deep Learning
Optimizing Clinical Trial Protocols Using EHR-Derived Heterogeneous Treatment Effects
A Multi-Agent System for 5G Throughput Prediction in Multi-Operator Urban Environments
C3DIR: A Deep Learning 3-Dimensional Cloud Property Retrieval Scheme for Passive Satellite Imagers
Deep Adaptive Bayesian Screening
Splat-based 3D Scene Reconstruction with Extreme Motion-blur
Pedestrian Archetypes Extension -- More Pedestrian Models for Autonomous Vehicle Safety Testing
PREFAIL: Identifying Precursors to Failures in Robotic Lift-and-Place Tasks to Improve Task Execution Performance
A Method for Learning Value Systems in Generative AI
Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing
When Can Safe Controllers Adapt? Information before Commitment
Certified-Gap Dual-Price Policies for Real-Time Truckload Bid Acceptance with Relocating, Clock-Constrained Resources
Transferable Low-Rank Convolutional Bases for Onboarding Unseen Medical Imaging Modalities
HyBDM: Multi-Scale Hybrid Experts for Time Series Forecasting with Bidirectional Dependency Modeling
Hierarchical Wireless Foundation Model for Multi-Task Optimization
InfoDense: Density-Aware Regional Decisive Replay for Memory-Efficient Incremental Face Forgery Detection
Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models
Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification
Bridging battery design and health assessment through virtual sensing and physics-informed learning
InLiER: Learning-Free Heterogeneous LiDAR Place Recognition via Intermediate Mixed-Radix Structural Keypoint Tokenization
Dataset Distillation by Influence Matching
Group Entropy-Controlled Policy Optimization
From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data

All 165