CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks Paper • 2608.06352 • Published 4 days ago • 21
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper • 2608.05987 • Published 4 days ago • 85
UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models Paper • 2608.04701 • Published 5 days ago • 7
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents Paper • 2608.03509 • Published 6 days ago • 22