190 citations · 823 across the 29 of their papers we have counts for
6 papers · 1 filter
Scaling 4D Representations
João Carreira, Dilara Gokay, Michael King +32
Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x20…
How to Spin an Object: First, Get the Shape Right
Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste +2
Image-to-3D models increasingly rely on hierarchical generation to disentangle geometry and texture. However, the design choices underlying these two-stage models--particularly the…
Moving Off-the-Grid: Scene-Grounded Video Representations
Sjoerd van Steenkiste, Daniel Zoran, Yi Yang +13
Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid,"…
How Does Code Pretraining Affect Language Model Task Performance?
Jackson Petty, Sjoerd van Steenkiste, Tal Linzen
Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code. Aside from aiding programming-related tasks, an…
Benchmarking Vision Language Models for Cultural Understanding
Shravan Nayak, Kanishk Jain, Rabiul Awal +5
Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their…
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
Ziyi Wu, Yulia Rubanova, Rishabh Kabra +6
We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object repres…