HiFOR adds hierarchical foresight and action-guided grounding to VLA models
Rongxing Ding · hf · 2026-11-02
Researchers from Nanjing University of Science and Technology, NUS, Shenyang Institute of Automation, and CUHK propose HiFOR, a Vision-Language-Action framework for robotic manipulation. Addressing the gap where prior foresight methods model short-term dynamics and long-term prediction separately, HiFOR hierarchically predicts future states and retrieves action-relevant future information via action-guided world grounding to steer action generation. Posted to arXiv on Oct 29, 2026.
More from Embodied
- Stanford's RoboArchitect Auto-Designs Robot Harnesses, Lifting Unseen-Scene Success from 9.7% to 43.3% — Shengguang Wu · 2026-11-02
- CausalWAM Isolates Action Causes in World Action Models via Sparse Routing — causal-intelligence · 2026-11-02
- CUHK's CaPtain-4B Post-Trains Small VLMs as Code-as-Policy Robot Agents, Hitting 78.3 on LIBERO-PRO — CUOHK · 2026-11-02
- Foxconn deploys 10+ humanoid robots in its Texas AI server plants, built on NVIDIA GR00T — CyberRobooo · 2026-11-02
- Unitree robot dog guards home under a 'Beware of Dog' sign while the backup dog naps — yassineyousfi_ · 2026-11-02
- Probing 10 vision foundation models finds none supports a full spatial state — liuziwei7 · 2026-11-02