I am a Ph.D. student at The Chinese University of Hong Kong, working with Weiyang Liu at Sphere Lab.
My research focuses on training and adapting foundation models, especially post-training, parameter-efficient adaptation, and model geometry. I study how models acquire new capabilities while retaining existing ones.
Previously, I worked on 3D vision and generative modeling, including research at NVIDIA. I received my master’s and bachelor’s degrees from Zhejiang University, where I worked with Deng Cai.
PEFT-Arena accepted to EMNLP Findings; BesiegeField accepted to EMNLP Main.
Symbolic Graphics Programming accepted to TMLR.
AdaHuman accepted to ICCV. Recognized as an Outstanding Reviewer at CVPR.
Findings of EMNLP 2026
Evaluating what models learn and what they retain—and studying the geometry of parameter-efficient updates under supervised and reinforcement-learning post-training.
EMNLP 2026 · Main Conference
A physically grounded testbed in which LLM agents write machine-construction programs, simulate their behavior, and refine designs using physical feedback.
Open-source project · 2026
Deployment-aligned RL with a frozen low-precision base and trainable adapters, enabling trillion-scale post-training on a single GPU node.
TMLR · 2026
Benchmarking symbolic graphics generation and improving it with reinforcement learning from renderability checks and cross-modal visual rewards.
ICCV · 2025
Detailed, animation-ready 3D humans from a single image using pose-conditioned joint diffusion and compositional 3D Gaussian refinement.
3DV · 2024
Reconstructing detailed, textured clothed humans from a single image with textual guidance and a personalized text-to-image prior.
CVPR 2024 · Highlight
Animatable Gaussian avatars with implicit mesh learning for text-driven 3D human generation.
3DV · 2024
Expressive, animatable 3D avatars generated from text descriptions.
ICCV · 2023
One-shot animatable avatar reconstruction with geometric and semantic model-based priors.
Waymo Challenge · 2022
First-place solution in the 2022 Waymo Open Dataset Challenge’s camera-only 3D detection track.
ICCV · 2021
Fine-grained feature fusion in transformers for sharp, temporally coherent video inpainting.
Ph.D. student, Computer Science and Engineering · Advisor: Weiyang Liu
M.Eng., Software Engineering · Advisor: Deng Cai
B.Eng., Computer Science · Chu Kochen Honors College
Research assistant · Yandong Wen
Research intern · Ye Yuan and Umar Iqbal
Research intern, Creative AI · Hongwei Yi
Earlier research internship at SenseTime Research.
Outstanding Reviewer, CVPR 2025.
Reviewer for CVPR, ICCV, ECCV, BMVC, KDD, TVCG, SIGGRAPH, and ACM Multimedia.
