🅻🅸🆅 @ollywogs

I make things go beep boop beep | creativity and machine learning | @hseas @medialab @MIT_CSAIL @idmMIT oliviaseow.com Cambridge, MA Joined January 2020

Tweets

118
Followers

293
Following

2K
Likes

664

Omar Sanseviero @osanseviero

6 months ago

Introducing Gemma Scope 2 🤗Largest open release of interpretability tools (over 1 trillion parameters trained!) 🔬Works as a microscope to analyze all Gemma 3 models' internal activations 🗣️Advanced tools for analyzing chat behaviors

23 92 959 78K 466

View Details

Jerry Han @JerryHan_og

7 months ago

I pulled a random street from Google Maps. Turned it into a 3D world with World Labs. Dropped a Unitree G1 into it and hooked it up to our server-side MuJoCo setup. Now the G1 is actually walking around a real Malaysian street in my browser. Three.js is doing the rendering. MuJoCo is running the physics and walking policy on the server. A simple WebSocket keeps everything locked together. Real street → 3D world → server physics + policy → live control in the browser. Kinda feels like cheating. Physical AI is getting wild. Huge shoutout to @theworldlabs. Marble makes this stuff way too fun. #robotics #MuJoCo #WorldLabs #simulation #unitree #sim2real

62 318 3K 166K 2K

View Details

Neal Agarwal @nealagarwal

7 months ago

Made a site comparing the sizes of living things :) The great Julius Csotonyi spent 5 months painting over 60 illustrations for the site, no ai used

329 6K 51K 1.1M 9K

View Details

Linoy Tsaban @linoy_tsaban

8 months ago

turns out it works with paintings too 🤯

Linoy Tsaban @linoy_tsaban

8 months ago

adding camera control to the list of things Qwen Image Edit is great at + with a specialized multi-angle LoRA it's even better✨ > rotate the camera > tilt between bird’s-eye and worm’s-eye views > adjust lens (wide, close-up) of course we built a demo for it 🤝📹

22 136 1K 375K 1K

24 114 1K 130K 1K

View Details

el.cine @EHuanglu

a year ago

omg.. this cant be real China’s 4DV AI just dropped 4D Gaussian Splatting, you can turn 2D video into 4D with sound.. imagine.. we will be able to change camera angle, zoom in/out while watching movies 5 examples:

718 4K 36K 3.6M 18K

View Details

Terrible Maps @TerribleMaps

2 years ago

Mapping the Lickability of the Periodic Table

451 5K 39K 4.3M 5K

View Details

Olivia Moore @omooretweets

2 years ago

Crazy to see how far AI video has come in the last few months The handling of shadows and light here feels like a new standard 👇 (from @endlesstaverns, made with Runway Gen-3 + Suno)

14 117 611 251K 221

View Details

Tianyuan Zhang @tianyuanzhang99

2 years ago

3D Gaussian is great, but how can you interact with it 🌹👋? Introducing #PhysDreamer: Create your own realistic interactive 3D assets from only static images! Discover how we do this below👇 🧵1/: Website: physdreamer.github.io

13 80 381 61K 131

View Details

🅻🅸🆅 @ollywogs

2 years ago

@quarbby 🫀💪✨

0 0 1 35 0

View Details

Puyuan Peng @PuyuanPeng

2 years ago

Announcing 𝐕𝐨𝐢𝐜𝐞𝐂𝐫𝐚𝐟𝐭🪄 SotA for both speech editing and zero-shot text-to-speech, Outperforming VALL-E, XTTS-v2, etc. VoiceCraft works on in-the-wild data such as movies, random videos and podcasts We fully open source it at tinyurl.com/3r8fvyzk

29 134 668 160K 554

View Details

Tim Rocktäschel @_rockt

2 years ago

I am really excited to reveal what @GoogleDeepMind's Open Endedness Team has been up to 🚀. We introduce Genie 🧞, a foundation world model trained exclusively from Internet videos that can generate an endless variety of action-controllable 2D worlds given image prompts.

132 539 2K 833K 849

View Details

Bob West @cervisiarius

2 years ago

In our new preprint, we ask: Do multilingual LLMs trained mostly on English use English as an “internal language”? - A key question for understanding how LLMs function. “Do Llamas Work in English? On the Latent Language of Multilingual Transformers” arxiv.org/abs/2402.10588

12 114 637 115K 399

View Details

Turing Post @TheTuringPost

2 years ago

Aya model is a new open-source massively multilingual language model. It was instruction fine-tuned by people from all over the world through one year! Aya is the unique model supporting 101 languages! It's the next step in building truly multilingual models. 1/10

1 4 18 2K 6

View Details

Omar Sanseviero @osanseviero

2 years ago

Great week for ML and multilingualism! - French with CroissantLLM hf.co/posts/manu/470… - Basque with Latxa - Chinese with Qwen 1.5 hf.co/collections/Qw… - Dutch with GEITje hf.co/posts/BramVanr…

HiTZ zentroa (EHU) @Hitz_zentroa

2 years ago

We are happy to present the Latxa family of open language models, which includes the largest and best model for Basque. It is based on @Meta's Llama models ranging between 7-70 billion parameters, with the open license Llama-2.

2 29 65 24K 10

2 15 80 12K 34

View Details

Nataniel Ruiz @natanielruizg

3 years ago

With collaborators @Google we're announcing 💫 ZipLora 💫! Merging LoRAs has been a big thing in the community, but tuning can be an onerous process. ZipLora allows us to easily combine any subject LoRA with any style LoRA! Easy to reimplement 🥳 link: ziplora.github.io

30 221 1K 366K 709

View Details

Rinon Gal @RinonGal

3 years ago

TL;DR: We use SDS from text-to-video models to animate vector-graphics sketches! Please check our project page for more details, and more penguins: livesketch.github.io

27 236 1K 174K 552

View Details

dylan @dylan_ebert_

3 years ago

Stop using text-to-image. this blender + real-time latent consistency workflow is way more fun, and shows how you can use Generative AI collaboratively, instead of as a creative slot machine try it yourself here huggingface.co/spaces/radames…

11 61 382 68K 272

View Details

Suhail @Suhail

3 years ago

@madebyollin @fofrAI @multimodalart @GaggiXZ Enjoy:

9 42 303 60K 185

View Details

🅻🅸🆅 @ollywogs

3 years ago

@quarbby take care Lynnette, sending you all my good thoughts and prayers for a speedy recovery!! 🙏🌟🌻

0 0 0 139 0

View Details

Anthropic @AnthropicAI

3 years ago

The fact that most individual neurons are uninterpretable presents a serious roadblock to a mechanistic understanding of language models. We demonstrate a method for decomposing groups of neurons into interpretable features with the potential to move past that roadblock.