Research could pave the way for a prosthetic hand and robot to be able to feel touch like a human hand. The technology could also be used to help restore lost functionality to patients after a stroke.
Greater computational cost is required for larger Transformers to function well. Recent research suggests that model size and training data must be scaled simultaneously to use any training compute resource the most. Sparse mixes of experts are a possible substitute that enables model scalability without incurring their full computational cost. Language, vision, and multimodal models…
To support the safety of highly-capable AI systems, we are developing our approach to catastrophic risk preparedness, including building a Preparedness team and launching a challenge. Post Views: 48
Semantic structure abounds in the representation spaces used by deep vision models. However, humans have difficulty making sense of these deep feature spaces because of the sheer volume of statistics involved. Unlike deep models, humans have developed language to succinctly represent the world around them, which encodes concepts as vectors in high-dimensional spaces. The University…
Post Content Post Views: 46
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of…
We have partnered with international news organizations Le Monde and Prisa Media to bring French and Spanish news content to ChatGPT. Post Views: 29