Cheng Lin

@_cheng_lin

Associate Professor @MUST | Prev Research Scientist @Tencent&MiHoYo | 3D Vision, 3D AIGC, Geometric Modeling, Graphics

clinplayer.github.io

Joined March 2020

350 Following

996 Followers

Replies Reposts Media

Pinned
Cheng Lin
@_cheng_lin
Jul 29, 2025
🔎Excited to share our PDT: Point Distribution Transformation with Diffusion Models (SIGGRAPH2025)! 💡While autoregressive models are now widely adopted for predicting structures, we find diffusion models can also reveal high-level structures by transforming point distributions!
6
Cheng Lin
@_cheng_lin
12h
🤩
Elena Shi🍣
@imoe_na
Nov 4
I’m 20 👋🏻 First time building in public. So many AI products here but where's the HARDWARE? 🥲 Currently building next gen AI glasses If you are a founder or hardware geek let’s connect! 🥰
Cheng Lin
@_cheng_lin
Oct 21
🌍Meet our World2HOSI: 3D Gaussian scenes + text → long-horizon human–object–scene interactions. Existing motion experts collaborate through a shared, evolving world—without training a new unified motion generator. nintreesssss.github.io/World2HOSI/
5
Cheng Lin
@_cheng_lin
Oct 17
Adaptive patch-wise denoising makes video diffusion much more efficient!
Zekai Gu
@skygoo2000
Oct 16
A static sky may need just one denoising step. A moving subject may need four. Yet most video diffusion models give every patch the same budget. 🚀 Introducing ForcingBooster: adaptive patch-wise denoising that lets easy regions finish early while spending more computation where
Cheng Lin
@_cheng_lin
Oct 13
An object-centric Transformer for learning rigid-body dynamics!
Zhiyang (Frank) Dou
@frankzydou
Oct 13
✨RigidFormer: Learning Rigid Dynamics using Transformers — accepted at #NeurIPS2026! 💻 Code is now open source: github.com/Frank-ZY-Dou/D… We propose an object-centric Transformer for learning rigid-body dynamics, enabling efficient and scalable mesh-free simulation. It achieves

Cheng Lin

Cheng Lin’s posts