Zhen Wu

@zhenkirito123

Amazon FAR (Frontier AI & Robotics). CS @Stanford. Humanoid Robots & Character Animation 🤖

2 273Followers

402Following

90Posts total

893KViews on collected posts

Son gönderiler

Zhen Wu@zhenkirito1233 Oct 2025

@zhenkirito123 climbed like a real human. Soon, we will see robot parkour competitions. 1K views · 18 likes · 0 reposts · 3 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

We are open-sourcing over 4 hours of high-quality, retargeted trajectories! Website: https://t.co/EeW71PaXVI ArXiv: https://t.co/8jxK1svcmT Datasets: https://t.co/xUq8seOxtM Huge shout out to the amazing team: @lujieyang98, @x_h_ucb, @akanazawa, @pabbeel, @carlo_sferrazza, 4.4K views · 62 likes · 5 reposts · 3 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

Standing on the shoulders of giants! Our work builds on amazing research in the community💡. We use the "interaction mesh" 🕸️ [1], [2] to preserve spatial relationships and leverage the minimal RL formulation from works like BeyondMimic [3]. Our long-horizon sequence is a nod to 9.5K views · 37 likes · 1 reposts · 1 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

Our grand finale: A complex, long-horizon dynamic sequence, all driven by a proprioceptive-only policy (no vision/LIDAR)! In this task, the robot carries a chair to a platform, uses it as a step to climb up, then leaps off and performs a parkour-style roll to absorb the landing. 31.7K views · 155 likes · 28 reposts · 5 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

But how much better is our data? 🤔 Compared to widely-used baselines, our motions show far fewer physical artifacts—virtually zero foot-skating and penetration—while better preserving contact. This allows us to use an open-sourced RL framework (BeyondMimic) without https://t.co/ 3.7K views · 33 likes · 0 reposts · 2 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

And it's not just for a specific robot! Our framework is highly general and adapts to different robot embodiments, including the @UnitreeRobotics H1 and the @boosterobotics T1. We can retarget complex object-carrying and platform-climbing skills across these different robots with 3.6K views · 36 likes · 0 reposts · 1 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

What about scalability? OmniRetarget transforms a SINGLE human demo into diverse motion clips. We can systematically vary terrain height, object size, and initial poses. Best of all, these augmented skills transfer directly from sim to our real-world hardware! 🤖➡️🦾 4/9 https:// 4.2K views · 36 likes · 1 reposts · 1 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

The result of this high-quality data? We can train diverse skills like box carrying 📦, slope crawling 🐾, and platform climbing 🧗 with a radically simplified RL process! All policies use just 5 reward terms, achieving successful zero-shot sim-to-real transfer! 🎯➡️🦾 3/9 https://t. 4.9K views · 55 likes · 0 reposts · 1 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

Existing retargeting often produces artifacts like foot-skating and penetration ❌. To compensate, RL policies rely on complex ad-hoc reward terms, forcing a trade-off between accurate motion tracking and correcting errors like slipping or bad contacts. OmniRetarget fixes this ht 7K views · 74 likes · 4 reposts · 3 replies Open on X →

Zhen Wu@zhenkirito1231 Oct 2025

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR https://t.co/5VtrXN4vlq 823K views · 670 likes · 154 reposts · 32 replies Open on X →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

823K1 Oct

4.9K

4.2K

3.6K

3.7K

31.7K

9.5K

4.4K

1K3 Oct

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.11%1 Oct

1.15%

0.90%

1.02%

0.94%

0.63%

0.42%

1.60%

2.07%3 Oct

Reactions — likes, reposts, replies and quotes — divided by views.

What the audience does

Likes62.7%1 176 in total

Reposts10.3%193 in total

Replies2.8%52 in total

Quotes3.0%56 in total

Bookmarks21.3%399 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Son gönderiler

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Benzer hesaplar