Google Scholar has parsed this cafeteria lunch menu as an author list, and it's delightful

Introducing Enigma: stefanzukin.com/enigma I trained GPT2 on 10,000 Nature papers and made a game where you try to distinguish between a real abstract and one that is computer generated.

When you think you have a bug but the problem was having batch norm in RL architecture🤯 Cutting down the problem, I created an easy env with constant state and reward=action. I couldn't solve it with batch norm in the arch. I wrote a small blog post here: rdednl.github.io/blog/batch-nor…

Apparently one paper I am reviewing for ICLR 2026 has been on arxiv since July. I discovered so, because another paper I am reviewing is built on top of that one. 😬

Some writing tips for the upcoming NeurIPS deadline

Excited to see many SIGGRAPH 2022 go public! kesen.realtimerendering.com/sig2022.html It's amazing that Ke-Sen single-handedly provides the best indexing of graphics papers on the web for *15 years*!

Our most recent work is now available! Check out the web demo at brachiation-rl.github.io/brachiation

Have been waiting for this update since M1 was announced. Can't wait to try it!

PaLM can answer questions that will make an average human's head explode

Rock, paper, scissors for the stage win 😂 #TourOfSlovenia

Once a year, for a rare moment at 7:15 AM EDT on July 8th, 99% of the world's population will be in the Sun. About 6.4 billion people in the daytime, while more than 1.2 billion people experience twilight. How cool is that! Source: earthsky.org

Excited for my first SIGGRAPH conference! We’ll be presenting Learning to Brachiate at the Roundtable session on Physics-Based Character Control, Tuesday at 2.15pm, Ballroom A/B. Video, paper, code and demo are here: brachiation-rl.github.io/brachiation/

I recently discovered notcous's NotMilk which is the best plant-based milk I've tried. They have an ML system "Giuseppe" that analyzes and proposes recipes to match foods at the molecular level and the result is amazing! It's new to me and I love when ML is used in these fields!

This is a super fun paper on simulating locomotion for virtual gibbons. You can even play with it - check it out! 😀 brachiation-rl.github.io/brachiation/

This paper from my Reality Labs at Meta internship shows how to control different characters and retarget the user's pose from only the sensors of the Quest using reinforcement learning. Coauthors: Alexander Winkler @Mvandepanne Jungdam Won and Yuting Ye Website: cs.ubc.ca/~dreda/retarge…

Non-human avatars like a mouse or a dinosaur would be fun to use in VR. The challenge is how to map a users's motion, detected solely by the headset and controllers, to different creatures. In this work we use physics to fill in missing information in a natural way. 1/5👇

Love to see our retargeting work featured in the latest 2MinutePaper video! For more details check the website: cs.ubc.ca/~dreda/retarge…

Flexible Motion In-betweening with Diffusion Models🧎🚶🧍Done together with Guy Tevet, Daniele Reda, Jason Peng, and @Mvandepanne 📄Paper: arxiv.org/abs/2405.11126 🌐Website: setarehc.github.io/CondMDI/ Grateful for the insights and feedback provided by everyone!

[NEW Preprint] 🔔🔔 CLoSD embeds real-time Motion Diffusion into a multi-task RL agent. Performing a task is as easy as describing it with a text prompt! Want to move to the next task? Just change the prompt on the fly😁 [1/4]🧵 guytevet.github.io/CLoSD-page/

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics