Yutao Fan

activity

20242026

most citedThe Landscape of Agentic Reinforcement Learning for LLMs: A Survey

1 citations · 1 across the 4 of their papers we have counts for

collaborators

Showing cs.CVShow all

2 papers · 1 filter

cs.CV2026

Reading $\neq =$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Heng Zhou, Ao Yu, Li Kang +5

Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We…

cs.CV2024

Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

Minheng Ni, Yutao Fan, Lei Zhang +1

As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in re…

Reading = Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

Reading $\neq =$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models