Walter Talbott retweeted
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
Walter Talbott retweeted
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.
Walter Talbott retweeted
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
Walter Talbott retweeted
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
GAUDI: A Neural Architect for Immersive 3D Scene Generation
abs: arxiv.org/abs/2207.13751
github: github.com/apple/ml-gaudi
Walter Talbott retweeted
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
Walter Talbott retweeted
1/n Check out our @Apple research paper "On the generalization of learning-based 3D reconstruction" (or 3D43D) arxiv.org/abs/2006.15427