Walter Talbott

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N

Latest preprint from @Apple MLR - we use conditional diffusion models + Perceiver I/O to learn the policy's state visitation and the value function on hard offline robotic tasks arxiv.org/abs/2306.07290. Work with @waltertalbott, @itsbautistam, Devon, Alex and @jsusskin.

New paper TRACT - Faster diffusion model sampling - Single-step diffusion SotA for CIFAR10 and ImageNet64 with L2 loss without architecture changes - Up to 2.4x FID improvement arxiv.org/abs/2303.04248

Excited for this to be out! Introducing GAUDI: a generative model for 3D indoor scenes. We tackle the problem of learning a generative model of 3D scenes parametrized as radiance fields. This has been a great collaboration across multiple teams at @Apple. arxiv.org/abs/2207.13751

Check out our work on model-based RL in the presence of severe visual distractions at the #NeurIPS2021 Deep RL workshop on Monday Dec 13, 1230 PST. Arxiv: arxiv.org/abs/2112.01163 Code: github.com/apple/ml-core

1/n Check out our @Apple research paper "On the generalization of learning-based 3D reconstruction" (or 3D43D) arxiv.org/abs/2006.15427

@wtalbott I keep getting email for you. Did you recently purchase a flight from Key West to Columbus?

I am tweeting from my new iPad. Why not embrace the age in which I live?