Ruiqi GaoMember of Technical Staff · Anthropic↗
Researcher · Engineer
AnthropicMember of Technical Staff
Mannat Singh co-led Emu Video, which turns a text prompt into a still image and then animates it.[1] He was a core contributor to Movie Gen, Meta’s system for generating and editing video[2], and helped build the Muse image and video models.[3] At Anthropic, he works on teaching Claude to reason about what it sees.[4]
AnthropicSep 2026-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Co-first author; the paper describes generating an image from text and then generating a video conditioned on the image and text.
Meta lists Singh as a core contributor and describes video generation and editing.
Singh describes the image and video work at Meta that culminated in the Muse release.
Singh describes his current role in reinforcement learning for vision, alongside his earlier model contributions.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.