Sicheng Feng — accepted AI-conference papers

2026

ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps

Sicheng Feng, Song Wang, Shuyi Ouyang, Lingdong Kong, Zikai Song, Jianke Zhu +2

CVPR 2026

Multimodal large language models (MLLMs) have demonstrated significant progress in semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on more complex tasks involving mathematics and logic. However, their proficiency in tasks requiring both fine-grain

Cited by 0 Source ↗code ↗Scholar ↗

2026

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Sicheng Feng, Kaiwen Tuo, Song Wang, Lingdong Kong, Jianke Zhu, Huan Wang

ICLR 2026poster

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and information-rich settings such as transit maps, a task of c…

Cited by 0 Source ↗code ↗Scholar ↗