AFFECT from KAIST makes world models dynamics-faithful via action effect matching
John Won · hf · 2026-11-20
KAIST researchers propose AFFECT, an auxiliary objective that trains world models to match visual responses to temporally correlated action noise, addressing their failure to capture how small action changes affect future observations. Across OGBench simulation and real-world DROID and ALOHA-2 setups, AFFECT improves rollout fidelity and planning success without requiring repeated executions from the same initial state.
More from Embodied
- NVIDIA's SOMA Retargeter adapts human motion to five humanoid robots, from G1 to AgiBot — jonstephens85 · 2026-11-20
- Mind2Act World: a 180-task benchmark exposing robots' mind-action composition failures — Mind2Act-World · 2026-11-20
- ZeroVLN navigates without SFT of the VLM brain using tool-calling and closed-loop RL — ZYT-AI · 2026-11-20
- Robot Paper Club recordings go live with four post-training talks; World Models edition next — DominiqueCAPaul · 2026-11-20
- Chinese student builds wearable tactical backpack robot, demo goes viral — TinfoilTricorn · 2026-11-20
- Huawei Cloud open-sources Ascend-native embodied world model CloudRobo-WM1.2, topping two benchmarks — 量子位 · 2026-11-20