xintong hu(@Erics_Tong):Current robot policies overfit specific language templates, handling 'pick and place' but freezing on 'drag it to me ' or 'push it closer to me.' They also lack control over execution: which hand, what approach angle, where to grasp, which path to follow. 🤖 FineVLA make robots steerable : changing instruction alters execution; same task, different phrasing, distinct actions — all faithfully done. 🏠 Homepage: https://t.co/NVRV63Wweb 📄 Paper: https://t.co/RUsR51k688 💻Codebase: https://t.co/DyrjoFV395 🧵[1/6]

xintong hu

@Erics_Tong

PHD at @XLangNLP in @HKUniversity, advised by @taoyds. undergraduate from Zhejiang university Research field：Embodied AI, VLA, WAM

加入 February 2024

144 正在關注 76 粉絲

xintong hu@Erics_Tong

2026.06.24 20:09

Current robot policies overfit specific language templates, handling 'pick and place' but freezing on 'drag it to me ' or 'push it closer to me.' They also lack control over execution: which hand, what approach angle, where to grasp, which path to follow. 🤖 FineVLA make robots steerable : changing instruction alters execution; same task, different phrasing, distinct actions — all faithfully done. 🏠 Homepage: 📄 Paper: 💻Codebase: 🧵[1/6]