Events
- Said Gürbüz (ETH Zurich) on controllable desktop environments for computer use agents, and Lorenzo Steno (Seldon Technologies) on building RL environments for computer use.161
- Haithem Turki from NVIDIA on photorealistic world models and Omar Sanseviero from Google DeepMind on the open Gemma model family.295(+58)
- Francis Engelmann from USI on superquadric representations for world models and Korrawe Karunratanakul from Flexion on versatile character control.250
- Zan Gojcic from NVIDIA on generative reconstruction and Vanessa Sklyarova from ETH Zurich on hairstyle modelling for avatars.192
- Paul-Edouard Sarlin from Google on 3D reconstruction for localization and Nando Metzger from ETH Zurich on high-resolution maps.280(+24)
- Felix Wimbauer from the Technical University of Munich and Google on understanding the 3D world from videos, and Joan Puigcerver from Google DeepMind on scaling computer vision architectures.290(+44)
- Ivan Vulić from the University of Cambridge and Google DeepMind on vision-language models for spatial reasoning and Tiago Pimentel from ETH Zurich on generalisation in language models.187
- Linus Scheibenreif from ETH Zurich on self-supervised learning for satellite imagery and Pascal Chang from ETH Zurich and Disney Research on visual anagram generation.111
- Xi Wang on egocentric learning and Nikolai Kalischek on diffusion-based panorama generation.75
10 of 16