NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 3 days ago • 390
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 25 days ago • 340
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 17 days ago • 143
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone Paper • 2607.25895 • Published Jul 28 • 159
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment Paper • 2607.13429 • Published Jul 15 • 16