2026

📄 Dynamic Skill Lifecycle Management for Agentic Reinforcement 05-12

AI 前沿深度解读 05-12

📄 LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling 05-11

📄 ActCam: Zero-Shot Joint Camera and 3D Motion Control for Vid 05-10

📄 ActCam: Zero-Shot Joint Camera and 3D Motion Control for Vid 05-08

📄 D-OPSD: On-Policy Self-Distillation for Continuously Tuning 05-07

📄 Safety and accuracy follow different scaling laws in clinica 05-06

📄 Persistent Visual Memory: Sustaining Perception for Deep Gen 05-04

📄 Computing Equilibrium beyond Unilateral Deviation 05-01

📄 Turning the TIDE: Cross-Architecture Distillation for Diffus 04-30

📄 Recursive Multi-Agent Systems 04-29

📄 Personalized Worked Example Generation from Student Code Sub 04-28

📄 Seeing Fast and Slow: Learning the Flow of Time in Videos 04-26

📄 Seeing Fast and Slow: Learning the Flow of Time in Videos 04-25

📄 Seeing Fast and Slow: Learning the Flow of Time in Videos 04-24

📄 SpeechParaling-Bench: A Comprehensive Benchmark for Paraling 04-23

📄 Generalization at the Edge of Stability 04-22

📄 ASMR-Bench: Auditing for Sabotage in ML Research 04-20

📄 MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage 04-19

📄 When Numbers Speak: Aligning Textual Numerals and Visual Ins 04-10

• 1
• 2