Papers

New on arXiv

Sat 14 Mar 2026

253 papers

Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for BiometricsLLM agents and tool use → General LLM agent frameworks and benchmarks
Domain-Specialized Tree of Thought through Plug-and-Play PredictorsLLM reasoning → Test-time compute and efficient thinking
AgriChat: A Multimodal Large Language Model for Agriculture Image UnderstandingMultimodal LLMs / vision-language models → Agricultural vision-language models
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMsMultimodal LLMs / vision-language models → Agricultural vision-language models
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking FeedbackLLM reasoning → Prompting and chain-of-thought reasoning +1
IdentityGuard: Context-Aware Restriction and Provenance for Personalized SynthesisLLM safety and security → Watermarking generated content and models
MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World VideosLLM reasoning → Audio-language model reasoning +1
Conditional flow matching for physics-constrained inverse problems with finite training dataDiffusion models → Flow matching, time series and science
Diffusion Reinforcement Learning via Centered Reward DistillationDiffusion models → Diffusion and flow policies for robotics +1
Improving Visual Reasoning with Iterative Evidence RefinementLLM reasoning → Multimodal reasoning +1
Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-ResolutionDiffusion models → Inverse problems and image restoration
DeepFix: Debugging and Fixing Machine Learning Workflow using Agentic AILLM agents and tool use → Software engineering coding agents
TMPDiff: Temporal Mixed-Precision for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent FailureLLM reasoning → Reasoning for agents, planning and code +1
Amortizing Trajectory Diffusion with Keyed Drift FieldsOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
LegacyTranslate: LLM-based Multi-Agent Method for Legacy Code TranslationLLM agents and tool use → Software engineering coding agents
A Multi-Agent Perception-Action Alliance for Efficient Long Video ReasoningLLM agents and tool use → Multimodal and embodied agents
The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QALLM reasoning → Knowledge- and tool-augmented reasoning +2
GRPO and Reflection Reward for Mathematical Reasoning in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
EyeWorld: A Generative World Model of Ocular State and DynamicsWorld models → Medical and surgical world models
Probing neural audio codecs for distinctions among English nuclear tunesMechanistic interpretability → SAE features and their applications
Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump DiffusionDiffusion models → Audio, speech and music
Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical ReasoningLLM reasoning → Clinical and biomedical applications
When Visual Privacy Protection Meets Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Chunk-Guided Q-LearningOffline RL and imitation learning from data → Offline RL algorithms +1
EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram SynthesisDiffusion models → Medical imaging and segmentation
vla-eval: A Unified Evaluation Harness for Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization
IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset DistillationDiffusion models → Diffusion foundations and sampling
ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic CoveringLLM agents and tool use → Tool learning and function calling
Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote SensingDiffusion models → Inverse problems and image restoration
GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMsLLM reasoning → LLM reasoning for recommendation
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance DatasetLLM safety and security → Safety alignment, refusal and guardrails
Discriminative Flow Matching Via Local Generative PredictorsDiffusion models → Flow matching, time series and science
SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness OptimizationVision-language-action models → Reinforcement learning and post-training
Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene GenerationDiffusion models → 3D, point cloud and scene generation
CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-ResolutionDiffusion models → Medical imaging and segmentation
UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal BenchmarkingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent InteractionsLLM agents and tool use → Social simulation and multi-agent debate
Path-conditioned Reinforcement Learning-based Local Planning for Long-Range NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation AnalysisLLM reasoning → Multimodal reasoning +1
Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question AnsweringLLM reasoning → Clinical and biomedical applications
How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent SimulationLLM agents and tool use → Social simulation and multi-agent debate
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMsLLM safety and security → Audio jailbreaks and speech backdoors
Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
ImagiNav: Scalable Embodied Navigation via Generative Visual Prediction and Inverse DynamicsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Building Explicit World Model for Zero-Shot Open-World Object ManipulationWorld models → Embodied and robot world models
PA-Net: Precipitation-Adaptive Mixture-of-Experts for Long-Tail Rainfall NowcastingMixture-of-experts → MoE for time series and graphs
Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in SpaceLLM reasoning → Clinical and biomedical applications +1
Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and ExpressionLLM safety and security → Federated unlearning and poisoning
DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot ManipulationVision-language-action models → 3D and spatial-aware VLA
Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation DetectionVision-language-action models → Failure recovery and robustness
AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context ComparisonMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query ExpansionLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation AlignmentDiffusion models → Video generation
Knowledge Distillation for Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
QTrack: Query-Driven Reasoning for Multi-modal MOTLLM reasoning → Multimodal reasoning
Exploration-assisted Bottleneck Transition Toward Robust and Data-efficient Deformable Object ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
UniVid: Pyramid Diffusion Model for High Quality Video GenerationDiffusion models → Video generation
R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest SignalsLLM reasoning → LLM reasoning for recommendation +1
Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-IdealityLLM reasoning → Test-time compute and efficient thinking
Do AI Agents Really Improve Code Readability?LLM agents and tool use → Software engineering coding agents
Sparse-Dense Mixture of Experts Adapter for Multi-Modal TrackingMixture-of-experts → Multimodal MoE models
REAEDP: Entropy-Calibrated Differentially Private Data Release with Formal Guarantees and Attack-Based EvaluationLLM safety and security → Membership inference attacks
REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
Steering Generative Models for Accessibility: EasyRead Image GenerationDiffusion models → Image generation, text-to-image and editing
τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World DomainsLLM agents and tool use → General LLM agent frameworks and benchmarks
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion TransformersDiffusion models → Diffusion foundations and sampling
FMS2: Unified Flow Matching for Segmentation and Synthesis of Thin StructuresDiffusion models → Flow matching, time series and science
Precautionary Governance of Autonomous AI: Legal Personhood as Functional Instrument
Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging
Deep Learning for Virtual Reality User Identification: A Benchmark
When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
On the First Computer Science Research Paper in an Indian Language and the Future of Science in Indian Languages
MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites
EVNextTrade: Learning-to-Rank-Based Recommendation of Next Charging Nodes for EV-EV Energy Trading
Fusion Learning from Dynamic Functional Connectivity: Combining the Amplitude and Phase of fMRI Signals to Identify Brain Disorders
JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction
MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning
Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
Quotient Geometry and Persistence-Stable Metrics for Swarm Configurations
Sharpness Aware Surrogate Training for Spiking Neural Networks
Integrating Explainable Machine Learning and Mixed-Integer Optimization for Personalized Sleep Quality Intervention
TDMM-LM: Bridging Facial Understanding and Animation via Language Models
GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference
Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation
Facial beauty prediction fusing transfer learning and broad learning system
Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
Clinician input steers AI toward accurate and harmful recommendations
Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images
CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction
An Alternative Trajectory for Generative AI

All 253