Xinyan Chen

About Me

I’m a first-year Ph.D. student in Multimedia Lab (MMLab), CUHK, supervised by Prof. Hongsheng Li. Before that, I received my B.E. degree from the University of Science and Technology of China (USTC).

My research interests focus on multimodal reasoning, including the understanding and generation of multimodal models.

News

• [2026-03] 🔥 We release MME-CoF-Pro, a comprehensive video reasoning benchmark.
• [2026-02] 🎉 Two papers are accepted by CVPR 2026 (one Main, one Findings).
• [2025-11] 🔥 We release Thinking-while-Generating (TwiG), an interleaved framework that enables co-evolving textual reasoning throughout the visual generation process.
• [2025-10] 🔥 We release Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark, an empirical study on the zero-shot reasoning capabilities of video models.
• [2025-09] 🎉 One paper (MINT-CoT) is accepted by NeurIPS 2025.
• [2025-05] 🎉 One paper (Mme-cot) is accepted by ICML 2025.
• [2024-09] 🎉 One paper (Learning from Mistakes) is accepted by EMNLP 2024.

Publications and Preprints

Educations

• 2025.08 – now, PhD Student, Electronic Engineering, The Chinese University of Hong Kong.
• 2021.09 – 2025.06, Bachelor of Engineering, Electronic Information Engineering, University of Science and Technology of China

Honors and Awards

• 2025: Hong Kong PhD Fellowship Scheme
• 2025: Guo Moruo Scholarship
• 2025: Outstanding Graduate of Anhui Province
• 2024: National Scholarship
• 2023: National Scholarship