Gemini and I also got a chance to watch the OpenAI live announcement of gpt4o, using Project Astra! Congrats to the OpenAI team, super impressive work!

Excited to share our work on Neural Assets: a new method for enabling 3D asset-level control in image diffusion models – scalable & without any 3D inductive biases. Neural Assets goes beyond text or pixel-based control & provides an interface inspired by 3D graphics tools. 🧵

We're excited to release TAPVid-3D: an evaluation benchmark of 4,000+ real world videos and 2.1 million metric 3D point trajectories, for the task of Tracking Any Point in 3D!

A 3B-parameter VLM that outperforms its 55B predecessor. This should be your go-to for captioning, VQA, or object-centric tasks! Check out the Huggingface demo or our tech report for extensive evaluations.