What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
Yu Peng, Jingjing Fu, Chuheng Zhang, Li Zhao, Jiang Bian, Mingyu Liu, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
Ling Zhang
Senior Researcher
Publications
-
-
-
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li, Jingjing Fu, Li Zhao, Jiang Bian, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-
-
-
What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
Yu Peng, Jingjing Fu, Chuheng Zhang, Li Zhao, Jiang Bian, Mingyu Liu, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li, Jingjing Fu, Li Zhao, Jiang Bian, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-
-
-
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li, Jingjing Fu, Li Zhao, Jiang Bian, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-
-
-
What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
Yu Peng, Jingjing Fu, Chuheng Zhang, Li Zhao, Jiang Bian, Mingyu Liu, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li, Jingjing Fu, Li Zhao, Jiang Bian, Ling Zhang, Jun Zhang, Rui Wang
May 2026
arXiv | May 2026
-