Stéphane Liem Nguyen
@stephliemnguyen
Followers
32
Following
95
Media
0
Statuses
9
PhD student in Machine Learning at @UNIGE_en
Geneva, Switzerland
Joined April 2023
We’re starting a company to build the next frontier of embodied intelligence - General Intuition We believe the time has come to move from words to worlds, and we’re developing foundation models capable of acting in any environment. Starting with video games!
5
9
35
Introducing General Intuition. We build foundation models and general agents for environments that require deep spatial and temporal reasoning. Deeply grateful to @vkhosla @htaneja for backing us, and @EloiAlonso1 @AdamJelley2 and @micheli_vincent who created a world-class lab.
Introducing General Intuition and our $133.7M Seed from Khosla Ventures, General Catalyst, and Raine. We build foundation models and general agents for environments that require deep spatial and temporal reasoning.
62
39
610
On a random Saturday last October, @PimDeWitte reached out about a wild, large and incredibly diverse dataset of gaming clips. I was skeptical - such a dataset felt like a secret archaeological treasure. We dug. It’s real.
2
3
22
With the awesome @noctrog, @DanielePaliotta, @MatPagliardini, and Martin Jaggi. @sciences_UNIGE @ICepfl TL;DR: you can shuffle the middle layers of a transformer without retraining it. We take advantage of that to compute layers in parallel. https://t.co/pBavh8u6Gy
arxiv.org
Large Language Models (LLMs) demonstrate remarkable capabilities at the cost of high compute requirements. Recent studies have demonstrated that intermediate layers in LLMs can be removed or...
7
47
360
Try 💎 DIAMOND’s Counter Strike world model directly in your browser! → https://t.co/IqfatLyi6l ← How long can you stay in distribution? Can you beat @stephliemnguyen’s 1000 frames? @AdamJelley2 and I are at NeurIPS! Poster #6306, Friday 11am-2pm, West Ballroom
5
12
64
Ever wanted to play Counter-Strike in a neural network? These videos show people playing (with keyboard & mouse) in 💎 DIAMOND's diffusion world model, trained to simulate the game Counter-Strike: Global Offensive. 💻 Download and play it yourself → https://t.co/vLmGsPlaJp 🧵
67
355
2K
We were very impressed by the recent DOOM #GameNGen from @Google, which inspired us to apply DIAMOND to CS:GO (first made public for Atari in May https://t.co/jhNxLdTfdf). Our CS:GO world model runs at ~10 FPS on a standard gaming GPU (RTX 3090). (2/n)
7
44
330