Wenli Xiao (@_wenlixiao) / X

Wenli Xiao

240 posts

Wenli Xiao

@_wenlixiao

@physical_int | PhD Student at @CMU_Robotics | Ex GEAR Lab @NvidiaAI | Physical AI & Robotics

Joined August 2019

Pinned
Wenli Xiao
@_wenlixiao
Jun 16
Autoresearch just left the sandbox and entered the embodied world. We are excited to introduce 𝐄𝐍𝐏𝐈𝐑𝐄: a system that drops frontier coding agents onto a fleet of real robots and hands them the entire loop: reset the environment → search the literature → implement ideas
00:00
252K
Wenli Xiao
@_wenlixiao
Oct 31, 2025
What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD
00:00
185K
Wenli Xiao
@_wenlixiao
Jun 24, 2025
ummm… As a robotics PhD student, I’m genuinely worried that the problem I find important now will be solved in the next 2 years—by MORE DATA, without any need to understand the underlying structure. And this happens in many areas😂
Yu Xiang
@YuXiang_IRVL
Jun 22, 2025
“As a PHD student, your job is not publishing a paper every quarter. Focus on a problem in deep understanding and solve it in years under the protect of your adviser” from @RussTedrake #RSS2025
61K
Wenli Xiao
@_wenlixiao
Sep 6, 2024
Very exicted to announce I just started interning at @NVIDIAAI GEAR group! Looking forward to the wonderful journey that takes generalist humanoids to the next level with @DrJimFan @yukez 🤖
58K
Wenli Xiao
@_wenlixiao
Jun 13, 2024
🚨 Without Any Motion Priors, how to make humanoids do versatile parkour jumping🦘, clapping dance🤸, cliff traversal🧗, and box pick-and-move📦 with a unified RL framework? Introduce WoCoCo: 🧗 Whole-body humanoid Control with sequential Contacts 🎯Unified designs for minimal
00:00
70K
Wenli Xiao
@_wenlixiao
Aug 29, 2025
Definitely mind-blowing! It can even handle quite OOD cases when playing with Prof. Sastry 😂
00:00
00:32
Zhi Su
@ZhiSu22
Aug 29, 2025
🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.
18K
Wenli Xiao
@_wenlixiao
Oct 16, 2024
🚨🚨Can generalist robotics models perform agile tasks? Introducing 𝗔𝗻𝘆𝗖𝗮𝗿🏎️ 🚚 🚗, a transformer-based 𝗴𝗲𝗻𝗲𝗿𝗮𝗹𝗶𝘀𝘁 vehicle dynamics model that can adapt to various cars, tasks, and envs via in-context adaptation, 𝗼𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗶𝗻𝗴 𝘄𝗲𝗹𝗹-𝘁𝘂𝗻𝗲𝗱
GIF
31K
Wenli Xiao
@_wenlixiao
Jun 15, 2024
🧠We really need safety guarantee for humanoid ‼️ Otherwise agile humanoid becomes fragile robot😭 We are really fascinated by recent humanoid demos in academia that trying to pushing the limit of - autonomous: HumanPlus, OmniH2O; - agility: Humanoid Parkour Learning, WoCoCo.
00:00
28K
Wenli Xiao
@_wenlixiao
Oct 29, 2024
🚨🚨 One Policy, Many Modes! Check our new versatile humanoid wholebody controller👇
00:00
00:42
Tairan He
@TairanHe99
Oct 29, 2024
🤖 Humanoids are expected to be the ultimate embodiment for general-purpose robots, but reaching that potential means adapting to diverse tasks—navigation, tabletop manipulation, loco-manipulation—each needing unique control modes. 🤔 Can one controller handle it all? ✨
13K
Wenli Xiao
@_wenlixiao
Feb 4, 2025
🚨Apparently, Sim2Real is NOT ENOUGH to solve humanoid whole-body control 🎉To push humanoid agility to the next level, we developed a systematic Real2Sim2Real approach to align simulation and real-world physics for RL-based controllers. 🔗Check what we can achieve at:
00:00
00:55
Tairan He
@TairanHe99
Feb 4, 2025
🚀 Can we make a humanoid move like Cristiano Ronaldo, LeBron James and Kobe Byrant? YES! 🤖 Introducing ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills Website: agile.human2humanoid.com Code: github.com/LeCAR-Lab/ASAP
15K
Wenli Xiao
@_wenlixiao
Sep 25, 2024
It’s so exciting to witness the paradigm shift in robot whole-body control! 🫨Previously, we needed ‘hundreds of’ heuristic rewards and hours of training to make a robot walk with a natural gait, but now we can deploy the novel sampling-based MPC without any training in
Haoru Xue
@HaoruXue
Sep 25, 2024
🎉 Diffusion-style annealing + sampling-based MPC can surpass RL, and seamlessly adapt to task parameters, all 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴-𝗳𝗿𝗲𝗲! We open sourced DIAL-MPC, the first training-free method for whole-body torque control using full-order dynamics 🧵 lecar-lab.github.io/dial-mpc/
00:00
11K
Wenli Xiao
@_wenlixiao
Jun 2, 2025
Tired of watching fancy humanoid dancing? Can they just do some daily useful tasks like: "Pass me a bottle of Water🍺"? 🤔Turns out it's nontrivial to stablize whole-body manipulation and locomotion at the same time. We basically want our humanoid to be stable as a camera
00:00
01:21
Yitang Li
@li_yitang
Jun 2, 2025
🤖Can a humanoid robot carry a full cup of beer without spilling while walking 🍺? Hold My Beer ! Introducing Hold My Beer🍺: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control Project: lecar-lab.github.io/SoFTA/ See more details below👇
13K
Wenli Xiao
@_wenlixiao
Oct 2, 2024
Inspired by @karpathy, I uploaded a raw Google Slides of my recent humanoid research presentation to NotebookLM. The generated podcast🎙️ is so impressive! It not only goes through the text and pictures but also comments on the videos! 🤯Feels just like the excitement I had when I
00:00
Andrej Karpathy
@karpathy
Sep 29, 2024
Deep Dive is now my favorite podcast. The more I listen the more I feel like I'm becoming friends with the hosts and I think this is the first time I've actually viscerally liked an AI. Two AIs! They are fun, engaging, thoughtful, open-minded, curious. ok i'll stop now.
9.6K
Wenli Xiao
@_wenlixiao
Aug 7, 2025
humanoid locomotion is so solved!
Skild AI
@SkildAI
Aug 6, 2025
We’ve all seen humanoid robots doing backflips and dance routines for years. But if you ask them to climb a few stairs in the real world, they stumble! We took our robot on a walk around town to environments that it hadn’t seen before. Here’s how it works🧵⬇️
00:00
4.5K