PonderPounce: Pretrained MLLM as Episode Context Engine for Robot Control
maum-ai · hf · 2026-08-31
PonderPounce leverages native causal context in MLLMs as robot episode memory, jointly training a reasoning System2 module and a fast System1 action model to improve long-horizon policy performance.
More from Embodied
- Chinese Humanoid Robot Runs 100m in 8.86 Seconds — FinanceYF5 · 2026-08-31
- Engineer insight: Building a pen plotter solves 30% of manufacturing — _Stocko_ · 2026-08-31
- Humanoid robot makes ice cream at Shanghai DQ — CyberRobooo · 2026-08-31
- US builds drone barriers, but China's scale may bypass them — TechCrunch AI · 2026-08-31
- Ropedia Launches HOMIE Gen2, Betting Robots Need Scaled Human Experience, Not Bigger Models — 机器之心 · 2026-08-31
- VLAct: Representation-Centric Continued Pre-training for Vision-Language-Action Models — StarVLA · 2026-08-31