Multiple papers accepted by top conferences such as NeurIPS 2025 and ICML 2025; Open-sourced projects include NVIDIA-Nemotron-Nano-v2-9B, ProRL v2, etc.; Research works like Fast-dLLM, CLIMB, etc.
Research Experience
Currently a research scientist at NVIDIA Research; Was a research intern at ByteDance AI Lab, working with Dr. Hang Li and Dr. Xinsong Zhang; Interned at Sinovation Ventures AI Institute.
Education
Ph.D. from the Hong Kong University of Science and Technology, advised by Professor Tong Zhang; Visiting scholar at BLENDER LAB@UIUC, working with Professor Heng Ji; Interned at WING Group @ NUS and PKU, where he worked with Prof. Min-Yen Kan and Prof. Xiaojun Wan during his undergraduate study.
Background
Research interests: pre-training, efficient-tuning, and alignment of large foundation models.