Liyan Tang

@liyan-tang · 2 works

Studies chain-of-thought reasoning and self-reflection in vision-language models.

Recent posts by Liyan Tang

• WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution - Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which… · Paper · arxiv.org
• Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning - Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasoning is self-reflection: revisiting earlier… · Paper · arxiv.org