Ge Yang

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

[Ge Yang @EpisodeYang]

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 https://t.co/3QbKataX3b

[Ge Yang @EpisodeYang]

@tonyzzhao Haha I am bookmarking this as one of the all greats.

[Ge Yang @EpisodeYang]

@_asadmemon Have been tracking this project for a while! would love to test it out!

[Ge Yang @EpisodeYang]

@ihorbeaver I am interested!

[Ge Yang @EpisodeYang]

@felixwyw Incredible lean, especially considering what you have accomplished!

[Ge Yang @EpisodeYang]

@ericjang11 This is really cool!

[Ge Yang @EpisodeYang]

@xiaolonw @Meta Congrats!!

[Ailing Zeng @AilingZeng81332]

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: https://t.co/Ve2c2YNuqj
Arxiv: https://t.co/cM54T3KSPs

[Ge Yang @EpisodeYang]

@akanazawa This is so cool!

[Ge Yang @EpisodeYang]

@_FelixHeide_ This is so cool!

[Ge Yang @EpisodeYang]

@gabriberton hahaha

[Ge Yang @EpisodeYang]

@bipashasen31 @tangiblerobots i want to see this!

[Ge Yang @EpisodeYang]

@giffmana right? this is just perfect

[Ge Yang @EpisodeYang]

@YuXiang_IRVL Yeah! So beautifully done ❤️

[Ge Yang @EpisodeYang]

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

[Tony Zhao @tonyzzhao]

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

🧵->

[Ge Yang @EpisodeYang]

@NliGjvJbycSeD6t That's so mean! hahaha

[Ge Yang @EpisodeYang]

for the love of robots ❤️

[Tony Zhao @tonyzzhao]

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

🧵->

[Ge Yang @EpisodeYang]

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

[Ge Yang @EpisodeYang]

@xiaolonw The visualization is so cool!!

[Ge Yang @EpisodeYang]

@yisongyue @klbouman @Caltech woa indeed. congrats @klbouman !