Yuting Li

Email: yutingli0606 at gmail dot com

Bio: I am a first-year PhD student at Shanghai Jiao Tong University, where I am a member of the MIFA Lab, advised by Prof. Weiran Huang. I am also a joint PhD student with the Beijing Institute for General Artificial Intelligence (BIGAI). Currently, I am interning with the Klear team at Kuaishou, focusing on long-context modeling for large language models. I also collaborate closely with Dr. Xi Shen from Intellindust, Dr. Dexiong Chen from Max Planck Institute and Prof. Lichao Sun from Lehigh University.

My passion and dream are to advance AI systems to a level where they are not only intelligent but also truly beneficial and safe for humanity.

GitHub CV Google Scholar

• 26 / 01 / 2026  Our paper "IDER: IDempotent Experience Replay for Reliable Continual Learning" is accepted to ICLR 2026.
• 19 / 09 / 2025  Our paper "Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO" is accepted to NeurIPS 2025.
• 12 / 06 / 2025  Our technical report: Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning is available on arXiv.
• 02 / 09 / 2024  Building on our CVPR work SURE, we won 1st place in the Open-set Recognition challenge at the Out Of Distribution Generalization in Computer Vision Workshop, ECCV 2024.
• 29 / 08 / 2024  Our paper "HTR-VT: Handwritten Text Recognition with Vision Transformer" is accepted to Pattern Recognition 2025.
• 27 / 02 / 2024  Our paper "SURE: SUrvey REcipes for building reliable and robust deep networks" is accepted to CVPR 2024. This is my first paper!

^‡ indicates project lead.
^* indicates equal contribution.
⁺ indicates corresponding author.
Representative papers are highlighted.

Coding

        All of my released code is maintained on my GitHub account .