←
Ge Yang2,339 posts
Ge Yang avatar

Ge Yang

@EpisodeYang

I am planting acorns one at a time with policy gradient.

◷ Joined November 2011▧ 223 Photos and videos
Ge Yang avatar
Ge Yang@EpisodeYang·10 May 2020

What can unsupervised representation learning learn from deep RL? As it turned out, we can learn representations (unsupervised) by making plans! Check out our new work at geyang.github.io/plan2vec

Ge Yang avatar
Ge Yang@EpisodeYang·Nov 11

Making training distribution the same as test distribution is not the best. That is a common misconception.

Chat when Russ Tedrake does a point by point takedown of your blog post in his keynote is it a good thing

Post attachment
Ge Yang avatar
Ge Yang@EpisodeYang·Nov 10

Robots Learning in a Million Worlds — before entering ours. My essay on where robot learning goes next, and how simulation can scale the research needed to get there. dreamlake.ai/geyang/public/r…

Ge Yang avatar
Ge Yang@EpisodeYang·Nov 10

When I started my PhD, quantum computing gatherings were small. By the time I shifted to AI, they filled conference halls. CoRL this year feels the same. Here are some thoughts on what comes next for robot learning.

Post attachment
Ge Yang avatar
Ge Yang@EpisodeYang·Nov 6

Here is mine 🥳 @MatthiasCaro

0:20

Trained entirely in imagination, our policy matches a PPO policy trained in simulation on the same locomotion test (81.8% vs 80.7% command-tracking success), with 7.9× fewer simulator transitions and about half the training time. More results soon 🤫

0:23
Ge Yang avatar
Ge Yang@EpisodeYang·Oct 20

People are underestimating the importance of sensorimotor learning. We loved Eka’s demo, and want more people to be able to do the same. so we figured that we should show what a few MIT undergrads are able to do in a week. This video was our first test.

0:15

@EkaRobotics has raised a $150M Series A. Generality v/s Performance is the fundamental tension at the frontier of robotics. Generality without performance is just a prototype. Performance without generality is just a single-purpose tool. Customers shouldn’t have to choose. Eka breaks the tradeoff. Powered by our Vision-Force-Action (VFA) model, we deliver the performance and versatility customers need to put robots to work every day. Eka is built on three convictions: ⚡️Force is the language of manipulation. 🚀 Reinforcement learning is how dexterous manipulation scales. 🎂 System 1—fast, reliable physical execution—is the bottleneck to solve. With this funding, we will scale our model and accelerate customer deployments. Grateful to be building alongside a dream team and investors who share our ambition.

0:24
Ge Yang avatar
Ge Yang@EpisodeYang·Oct 20

You got to take a look at the cut where the arm flew off together with the ball :P A perfect example of how massive closed-loop training can do to physical systems.

2/9 To train it, we reset the simulator to a recorded hardware state, apply the same recorded commands, and learn command corrections so the simulated rollout matches the recorded hardware trajectory. We previously used UAN on a quadruped's arm (uan.csail.mit.edu). But motion with contact was tricky.

0:10
Ailing Zeng avatar
⟳ Ge Yang retweeted
Ailing Zeng@AilingZeng81332·Apr 10

Introducing LPM 1.0 — a video-based character performance model that speaks, sings, listens, reacts, and emotes in real time. - Generating full-duplex conversation, identity-consistent infinite-length generation, and nuanced human-like performance. - Building across a co-designed data pipeline, Base model, Online model, and streaming inference optimization. - Key advantages over other video generation models: performance quality, emotional conversation, precise lip-sync, identity preservation, and lifelike naturalness. Turning an image into a performance video, LPM 1.0 serves as a visual engine for conversational agents, live streaming characters, and game NPCs. Page: large-performance-model.gith… Arxiv: huggingface.co/papers/2604.0…

10:19
Ge Yang avatar
Ge Yang@EpisodeYang·22 Nov 2025

This is one of those iconic designs that will go down in history, that is destined to be remembered.

Tony Zhao@tonyzzhao19 Nov 2025

Today, we present a step-change in robotic AI @sundayrobotics. Introducing ACT-1: A frontier robot foundation model trained on zero robot data. - Ultra long-horizon tasks - Zero-shot generalization - Advanced dexterity 🧵->

4:10
Ge Yang avatar
Ge Yang@EpisodeYang·22 Nov 2025

for the love of robots ❤️

Tony Zhao@tonyzzhao19 Nov 2025

Today, we present a step-change in robotic AI @sundayrobotics. Introducing ACT-1: A frontier robot foundation model trained on zero robot data. - Ultra long-horizon tasks - Zero-shot generalization - Advanced dexterity 🧵->

4:10
Ge Yang avatar
Ge Yang@EpisodeYang·13 Nov 2025

Do you know who this is person was? You can see the Green Building and MIT in the background.

0:05
Huy Ha avatar
⟳ Ge Yang retweeted
Huy Ha@haqhuy·8 Oct 2025

Spent just over an hour collecting UMI data in Stanford, sent it to @harshgupta in CMU to run drone I've never seen before, and it just works 🤯 I was expecting to iterate on the data a few more times but embodiment guidance is so robust! umi-on-air.github.io/ to learn more!

💾 Data from across the country. 🚁 No access to the drone. 🤖 Still works, zero-shot. UMI-on-Air makes large-scale data collection → real-world deployment possible.

0:16
Kevin Zakka avatar
⟳ Ge Yang retweeted
Kevin Zakka@kevin_zakka·29 Sep 2025

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.

0:38
Ge Yang avatar
Ge Yang@EpisodeYang·22 Sep 2025

Really cool to see the g1 do this! Was expecting some punching involved 😆

This tweet is unavailable