Aran Komatsuzaki's banner
Aran Komatsuzaki's profile picture

Aran Komatsuzaki

@arankomatsuzaki • 196,887 subscribers

Sharing AI research. Early work on AI (GPT-J, scaling, MoE). Ex ML PhD (GT) & Google.

Shorts

Automating the Search for Artificial Life with Foundation Models Presents ASAL, the first use of vision-language models in Artificial Life, discovering diverse, novel simulations across substrates proj: abs:

Automating the Search for Artificial Life with Foundation Models Presents ASAL, the first use of vision-language models in Artificial Life, discovering diverse, novel simulations across substrates proj: abs:

39,180 görüntüleme

Text-To-4D Dynamic Scene Generation Presents MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. proj: abs:

Text-To-4D Dynamic Scene Generation Presents MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. proj: abs:

54,674 görüntüleme

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

PingpongDuo Humanoid table tennis now has doubles, while I'm still single. proj: abs:
0:23
arankomatsuzaki's profile picture

PingpongDuo Humanoid table tennis now has doubles, while I'm still single. proj: abs:

Aran Komatsuzaki

17,738 görüntüleme • 5 gün önce

Nvidia presents Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution proj: abs:
0:30
arankomatsuzaki's profile picture

Nvidia presents Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution proj: abs:

Aran Komatsuzaki

13,772 görüntüleme • 5 gün önce

MusicLM: Generating Music From Text Presents MusicLM, a model for generating high-fidelity music from text. MusicLM generates music at 24 kHz that remains consistent over several minutes. proj: abs: data:
0:30
arankomatsuzaki's profile picture

MusicLM: Generating Music From Text Presents MusicLM, a model for generating high-fidelity music from text. MusicLM generates music at 24 kHz that remains consistent over several minutes. proj: abs: data:

Aran Komatsuzaki

163,093 görüntüleme • 3 yıl önce

Meta presents: Pippo : High-Resolution Multi-View Humans from a Single Image Generates 1K resolution, multi-view, studio-quality images from a single photo in a one forward pass
0:20
arankomatsuzaki's profile picture

Meta presents: Pippo : High-Resolution Multi-View Humans from a Single Image Generates 1K resolution, multi-view, studio-quality images from a single photo in a one forward pass

Aran Komatsuzaki

32,588 görüntüleme • 1 yıl önce

Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text Outperforms previous SotA motion synthesis methods across the board proj: abs:
0:21
arankomatsuzaki's profile picture

Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text Outperforms previous SotA motion synthesis methods across the board proj: abs:

Aran Komatsuzaki

38,403 görüntüleme • 2 yıl önce

Daha fazla içerik yok.