When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across De…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Rev…
AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Age…
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Rea…
Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Auto…
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and S…
FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare
ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable…
ChartAnno: Evaluating MLLMs for Chart Annotation Generation
SGFormer: Structure-Guided Transformer for Robust Local Feature Matching
Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance
FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection
Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning
Can Text-to-Image Models Draw from the Right Frame of Reference?
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation…
AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Que…
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
From Wearable Data to Personalized and Actionable Health Insights
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
On the Diversity of Analogy Making in Large Language Models
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign a…
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Self-Supervised Representation-Guided Generative Dataset Distillation
On the Implicit Flatness Bias of Sharpness-Aware Minimization: A Linear Stability Analysi…
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retri…