🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

My second hand redmi note 9 pro running flowpilot is driving my alto k10 😂Can it get more desi than this ? #flowpilot #openpilot #ai #robotics #autonomous #cars #Android

Excited to present some experiments we did with our partners from Volucap - Volumetric Studio on using neural rendering for creating a bullet time effect on a scene from #Matrix4🎥🌐 NR-Nerf project page: vcai.mpi-inf.mpg.de/projects/nonri… Volucap project page: volucap.com/portfolio-item…

Me and some members of my research group (Ayush Tewari, George Cazenavette, Cameron Smith) will be at NeurIPS - talk to us about our work on training 3D diffusion models only from images (…ffusion-with-forward-models.github.io) and pixelNeRF without camera poses (scenerepresentations.org/publications/f…)! #NeurIPS2023

2. Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering (vcai.mpi-inf.mpg.de/projects/2023-…) 12/14/2023 (Thu), 11:10pm-11:25pm Diffusion-prior meets inverse rendering for high-resolution illumination recovery!!

Find us at poster 226 where Cameron is presenting his cool work “FlowCam”!

How can we learn to generate 3D scenes directly with diffusion models if we only have images, no ground-truth 3d scenes? Ayush, Tianwei and George will tell you at our poster “diffusion with Forward Models”, #202!

🧠: “Let’s but this (text)book! Nice and now… instead of reading it… let’s buy another one!” 💡 All of the dopamine is generated only at the point of resolving to read something. After that there is no juice left 😅

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! cameronosmith.github.io/flowmap/ IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Excited to announce that I will be joining the University of Cambridge Engineering Dept as an assistant professor in spring 2025! I will be looking for students for the next year. Check out Elliott / Shangzhe Wu's thread for details on how to apply, and get in touch!

✨Applications are now open for PhDs at the Cambridge Machine Learning Group!✨ We're looking for outstanding candidates interested in fundamental ML research and applications to scientific domains! More info: mlg.eng.cam.ac.uk/phd_programme_… 🧵Find more about PIs & focus areas below!

Consider applying! Supervisors are Jose Miguel Hernandez-Lobato, Carl Rasmussen, Richard E. Turner, Adrian Weller, Hong Ge and Ayush Tewari.

Last two days to apply!

If you are looking to do a PhD on inverse graphics, 3D computer vision, differentiable rendering, etc, please apply to Ayush's lab at the University of Cambridge! He is brilliant, very patient, and a kind human :)

Robots can do flips and play chess, but they still can’t grab a snack or clean your table. Teleoperation is the key to unlocking real dexterity. It’s not a compromise—it’s a proven, powerful approach that combines human intuition with robotic precision. We’re not just using

📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. radfoam.github.io arxiv.org/abs/2502.01157 Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ Kwang Moo Yi

Join Us! University Assistant Professor in #MachineLearning #AI Engineering Dept Cambridge University details here: jobs.cam.ac.uk/job/49361/

Join our team at Cambridge! We have fully funded PhD positions in robot learning, novel robot hardware design, and reinforcement learning. Looking for applicants with a strong background in dexterous manipulation & hardware prototyping. Interested? Please send me a message/email.

Compression is the heart of intelligence From Occam to Kolmogorov—shorter programs=smarter representations Meet KARL: Kolmogorov-Approximating Representation Learning. Given an image, token budget T & target quality 𝜖 —KARL finds the smallest t≤T to reconstruct it within 𝜖🧵