Scholar
Ji Hou
Google Scholar ID: 63TZXq4AAAAJ
Research Scientist, Meta Superintelligence Labs
Citations & Impact
Citations
2,471
H-index
16
i10-index
20
Publications
20
Co-authors
46
list available
Publications
Resume
Academic Achievements
- Co-authored multiple high-impact papers published at NeurIPS 2025 (Spotlight), CVPR 2025, etc.
- Contributed to MetaQueries, a minimal recipe for unified multimodal understanding and generation models.
- Contributed to MoCha, enabling multi-character conversational video synthesis with turn-based dialogue for the first time.
- Worked on Token-Shuffle, pushing autoregressive text-to-image generation to 2048x2048 resolution.
- Developed LinGen, a linear-complexity framework for high-resolution, minute-length text-to-video generation on a single GPU.
- Contributed to Movie Weaver, supporting tuning-free multi-concept video personalization.
- Core contributor to Movie Gen, a suite of Meta media foundation models generating 1080p HD videos with synchronized audio.
