Jinkun Cao
@jinkuncaoPhD student at Carnegie Mellon, working on robotics and 3D vision.
Similar User
@MinghuaLiu_
@HarryXu12
@kaiwynd
@haosu_twitr
@stevenpg8
@zhengyiluo
@Haoyu_Xiong_
@RchalYang
@QinYuzhe
@yufei_ye
@jonzamora_ai
@wang_jianren
@DonglaiXiang
@taochenshh
@zhijianliu_
Vision transformers split input videos into equal sized patches - the number of tokens depends only on the number of frames and their resolution. But some videos are more complex than others - does lofi girl need same number of tokens as Obito vs Kakashi?
Curious whether video generation models (like #SORA) qualify as world models? We conduct a systematic study to answer this question by investigating whether a video gen model is able to learn physical laws. Three are three key messages to take home: 1⃣The model generalises…
Sharing my recent project, agent-to-sim: From monocular videos taken over a long time horizon (e.g., 1 month), we learn an interactive behavior model of an agent (e.g., a 🐱) grounded in 3D. gengshan-y.github.io/agent2sim-www/
Imagine a future where you can ask humanoid robots to clean your room, but some items, like heavy sofas, are too challenging for just one robot to move. Introducing CooHOI, a learning-based framework designed for the cooperative transportation of objects by multiple humanoid…
Zhuang is amazing and Princeton is amazing! Students in related areas should definitely apply!
Excited to share that I will be joining Princeton Computer Science @PrincetonCS as an Assistant Professor in September 2025! I'm looking for students to join me. If you are interested in working with me on VLMs, LLMs, deep learning (vision/LLM) architectures, data, training,…
Did you exercise today? Breaking Records! G1 Humanoid Robot Achieves a Jump Distance/Height Ratio of Over 1! 🥰 The G1 robot can perform a standing long jump of up to 1.4 meters, possibly the longest jump ever achieved by a humanoid robot of its size in the world, standing only…
Added support for H1 & G1 humanoid full-body motion imitation in the PHC codebase: github.com/ZhengyiLuo/PHC This is the pipeline we used to develop the 'sim-to-data' workflow in H2O (human2humanoid.com) and OmniH2O (omni.human2humanoid.com). Working on IsaacSim/Lab support…
PHC has been accepted by ICCV 2023! We aim to develop a physics-based humanoid controller capable of imitating ALL of the motion from the AMASS dataset (almost there🧐), recover from failure state, does NOT use any external forces, all the while supporting real-time use cases!
Single codebase for multiple purpose and embodiments
Our codebase aims to support any embodiment, and to avoid limiting what the user can do. Out of the box we support: - SMPL and SMPL-X (fingers). Huge thanks to @zhengyiluo for SMPLSim (github.com/zhengyiluo/smp…)! - AMP and ASE humanoids. @xbpeng4! - Unitree H1. @TairanHe99 2/
Really nice work. Do need such datasets! Having been thinking about a solution for such challenging problems for a while.
To what extent does social interaction affect behavior in couples swing dancing? Our work looks at how we can predict a dancer's next moves based on their past motion alone or by considering both the dancer's and their partner's motions. 🪩🕺🏾 🆚 🪩🕺🏾💃🏾 🧵1/6
Excited to share our latest work! 🤩 Masked Mimic 🥷: Unified Physics-Based Character Control Through Masked Motion Inpainting Project page: research.nvidia.com/labs/par/maske… with: Yunrong (Kelly) Guo, @ofirnabati, @GalChechik and @xbpeng4 @SIGGRAPHAsia (ACM TOG). 1/ Read…
How can you scale up robot learning? We introduce HOP: Extract hand-object trajectories from in-the-wild videos. Train a next-token-prediction model to get a manipulation prior. Adapt to your task using BC or RL. Checkout our webpage: bit.ly/47tyeDv More details in 🧵
📢 Check out 𝐒𝐚𝐩𝐢𝐞𝐧𝐬 (#ECCV2024, Oral)! Largest human-centric foundational models that natively supports 1K high-res inputs, achieving SOTA on 2D kpts, seg, depth and normal! Code and models (each task + pretraining) are ready to use TODAY! github.com/facebookresear… (1/6)
Unitree G1 mass production version, leap into the future! Over the past few months, Unitree G1 robot has been upgraded into a mass production version, with stronger performance, ultimate appearance, and being more in line with mass production requirements. We hope you like it.🥳…
Really exciting and interesting idea.
Excited for the day we have Humanoid Olympics every four years! Imagine uploading your checkpoints and live-streaming the competition!
Meet our AI-powered robot that’s ready to play table tennis. 🤖🏓 It’s the first agent to achieve amateur human level performance in this sport. Here’s how it works. 🧵
The problems in a domain that you can simulate, can be solved by AI since you can create unlimited training data. This is true for games (think go, dota, etc), simple physical simulations, programming/coding environments and eventually more complex biological systems.
United States Trends
- 1. #WWERaw 27,3 B posts
- 2. Cowboys 33,1 B posts
- 3. Pulisic 2.996 posts
- 4. #AskShadow 4.561 posts
- 5. Mixon 6.143 posts
- 6. Tunsil N/A
- 7. #USMNT 1.026 posts
- 8. Skenes 12,2 B posts
- 9. #HOUvsDAL 3.415 posts
- 10. Merrill 6.007 posts
- 11. Sean Duffy 20 B posts
- 12. Luis Gil 6.299 posts
- 13. Rhea 13,6 B posts
- 14. #HTownMade 1.924 posts
- 15. Nico Collins 3.082 posts
- 16. Cowser 1.723 posts
- 17. Mazi Smith N/A
- 18. GOTY 52,1 B posts
- 19. Road Rules 1.367 posts
- 20. Katie Hobbs 17,9 B posts
Who to follow
-
Minghua Liu
@MinghuaLiu_ -
Huazhe Harry Xu@CORL
@HarryXu12 -
Kaifeng Zhang
@kaiwynd -
Hao Su
@haosu_twitr -
Shaowei Liu
@stevenpg8 -
Zhengyi “Zen” Luo
@zhengyiluo -
Haoyu Xiong
@Haoyu_Xiong_ -
Ruihan Yang
@RchalYang -
Yuzhe Qin
@QinYuzhe -
Yufei Ye
@yufei_ye -
Jonathan Zamora
@jonzamora_ai -
Jianren Wang
@wang_jianren -
Donglai Xiang
@DonglaiXiang -
Tao Chen
@taochenshh -
Zhijian Liu
@zhijianliu_
Something went wrong.
Something went wrong.