Log inSign up
Zhiyang (Frank) Dou
1,523 posts
Image
user avatar
Zhiyang (Frank) Dou
@frankzydou
PhD student @MIT_CSAIL. MPhil @HKUniversity. Ex-visiting @Penn. Dynamics Modeling, Physical AI, Robotics, Sim, Geometry, Control, AIGC. 🦋frankzydou.bsky.social
Cambridge, MA
people.csail.mit.edu/frankzydou/
Joined July 2020
2,110
Following
2,017
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    May 18
    Here are more results from #RigidFormer: predicting physical dynamics with purely neural simulators — an attempt to learn physical dynamics in a scalable manner. 🤖 1) Controllable Articulated Body Simulation — More Results Additional Unitree G1 humanoid rollouts under
    Image
    00:00
    Image
    00:26
    user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    May 11
    Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers. RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact
    20K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Dec 28, 2023
    🔥Yes! You can achieve REAL-TIME text-to-motion generation using a simulated humanoid to perform various skills! This feat is realized through the integration of PHC and EMDM. 💬This combination addresses two pivotal challenges in human motion synthesis: ensuring physical
    user avatar
    Zhengyi “Zen” Luo
    @zhengyiluo
    Dec 28, 2023
    You can now ask your simulated humanoid to perform actions, in REAL-TIME 👇🏻 Powered by the amazing EMDM (@frankzydou, @Alex_wangjingbo, etal) and PHC. EMDM: frank-zy-dou.github.io/projects/EMDM/… PHC: github.com/ZhengyiLuo/Per… Simulation: Isaac Gym
    Image
    00:00
    36K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Dec 6, 2023
    Introducing🏃𝐄𝐌𝐃𝐌🏃(𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐭 𝐌𝐨𝐭𝐢𝐨𝐧 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥)! 🔥Now, you can achieve efficient text-to-motion generation using a diffusion model within only ~𝟎.𝟎𝟓𝐬 for one sequence (MDM takes ~𝟏𝟎𝐬). Our simple yet effective approach, EMDM, ensures
    Image
    00:00
    20K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jul 1, 2024
    Got five papers accepted by #ECCV2024 @eccvconf ! Huge thanks to all my collaborators! 😃 See you in Milan 🇮🇹 Summary of Selected Works (I made a fast-forward for them 😄) - [Shape Generation] Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion
    Image
    00:00
    18K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Feb 27, 2024
    🎉 🚀 𝐖𝐨𝐧𝐝𝐞𝐫𝟑𝐃 has been accepted to #CVPR2024! Wonder3D is able to convert a single image into a high-fidelity 3D model, complete with textured meshes and color, in just 2 to 3 minutes. Congratulations to Xiaoxiao (@xxlong0), Benny (@superbennyguo) and all
    Image
    00:00
    user avatar
    Xiao-Xiao Long
    @xxlong0
    Feb 27, 2024
    Wonder3D gets accepted to CVPR! Thanks the help from all the coauthors. The full codes including training and data rendering codes are available in our github repo github.com/xxlong0/Wonder… ( too many 3D generative papers recently, cannot believe it just passes three months! )
    12K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Nov 29, 2023
    (1/3) Introducing 🚀Surf-D🚀, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Surf-D demonstrates superior performance in 3D shape generation across various modalities (TBC)! Good job, Zhengming @Proof_Yu !
    Image
    15K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    May 28, 2024
    🔥Check out our SIGGRAPH 2024 paper: 𝐏𝐚𝐫𝐭𝟏𝟐𝟑: 𝐏𝐚𝐫𝐭-𝐚𝐰𝐚𝐫𝐞 𝟑𝐃 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐟𝐫𝐨𝐦 𝐚 𝐒𝐢𝐧𝐠𝐥𝐞-𝐯𝐢𝐞𝐰 𝐈𝐦𝐚𝐠𝐞. Diffusion models have advanced single-view reconstruction, but current methods lack 𝗣𝗮𝗿𝘁-𝗯𝗮𝘀𝗲𝗱 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝘀,
    Image
    00:00
    5K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Nov 29, 2023
    (3/3) The clothes 🎽👖👗🩳generated by 🚀Surf-D🚀can be used for virtual try-ons with high quality and fidelity. You can just use sketches to generate whatever clothes you want, then put on your own avatar and use captured/generated human motion to animate them :D #SurfD #AIGC
    Image
    GIF
    9.4K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jul 3, 2024
    🔥 Check it out! 🚀 The code is now available! Surf-D at @eccvconf #ECCV2024: Our method achieves high-quality surface generation for detailed geometry and various topologies using a diffusion model. It sets the state of the art in various shape generation tasks, including
    Image
    00:00
    Image
    Image
    Image
    user avatar
    Zhengming Yu
    @Proof_Yu
    Jul 3, 2024
    Our Surf-D is accepted at ECCV 2024 @eccvconf. Codes are released. Surf-D can generate arbitrary typology shapes in high resolution using UDF representation. Project page: yzmblog.github.io/projects/SurfD/ Arxiv: arxiv.org/abs/2311.17050 Codes: github.com/Yzmblog/SurfD #eccv #SurfD
    6.5K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jun 23, 2024
    ✈️ From #CVPR2024 in Seattle to #SGP2024 in Boston (MIT). Excited to catch up with old friends and meet new ones at these conferences!
    Image
    Image
    00:00
    Image
    Image
    8.8K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jul 28, 2024
    I've just arrived in Denver for SIGGRAPH @siggraph. Excited to catch up if you're around! #SIGGRAPH2024 #siggraph
    Image
    Image
    Image
    Image
    3.6K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jun 20, 2024
    So cute! #CVPR2024
    Image
    00:00
    3.5K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Nov 30, 2023
    💃𝐓𝐋𝐂𝐨𝐧𝐭𝐫𝐨𝐥💃 is a novel and powerful method for controllable human motion generation using both low-level Trajectories ✏️ and high-level Language semantics 💬 controls. It effectively supports multi-joint control :D 𝐓𝐋𝐂𝐨𝐧𝐭𝐫𝐨𝐥 significantly outperforms the SOTAs
    Image
    00:00
    Image
    01:00
    user avatar
    Wanwl
    @Wanwl123
    Nov 30, 2023
    Presenting our recent work, 𝐓𝐋𝐂𝐨𝐧𝐭𝐫𝐨𝐥, a new approach to synthesizing realistic human motion. 𝐓𝐋𝐂𝐨𝐧𝐭𝐫𝐨𝐥 effectively integrates low-level trajectories with high-level language semantics for controllable motion generation. Thank @frankzydou and all collaborators!
    5.5K
  • user avatar
    Zhiyang (Frank) Dou
    @frankzydou
    Jun 24, 2024
    Compact Representation Computation for Shapes—Summary of the Coverage Axis Series The latest work in the Coverage Axis series🐱, Coverage Axis++, has recently been completed and accepted by SGP2024. Here, I provide a summary of our efforts on this problem. In the Coverage Axis
    Image
    Image
    Image
    Image
    5.8K
This post is unavailable.
Advertisement
Advertisement