Kewei Lian — accepted AI-conference papers

2026

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies

Guangyu Zhao, Kewei Lian, Haoxuan Ru, Borong Zhang, Haowei Lin, Zhancun Mu +5

ICML 2026poster

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of discrete text prompts, we formulate post-training adaptatio…

Cited by 0 Source ↗Scholar ↗

2025

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

Shaofei Cai, Zihao Wang, Kewei Lian, Zhancun Mu, Xiaojian Ma, Anji Liu +1

CVPR 2025poster

Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective p…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗