Scholar
Yicong Hong
Google Scholar ID: AerHOzUAAAAJ
Adobe Research
Citations & Impact
Citations
2,783
H-index
18
i10-index
21
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- 2025: 'Test-time training done right' – addresses long-context modeling for language, 3D, and video generation
- 2025: 'Pushing the Boundaries of State Space Models for Image and Video Generation' – introduces a Mamba-Transformer hybrid model
- 2024: 'Progressive Autoregressive Video Diffusion Models' for minute-long video generation, accepted to CVPR 2025 workshop
- 2024: 'LRM: Large Reconstruction Model for Single Image to 3D' (ICLR 2024 Oral); 'Instant3D' (ICLR 2024 Poster)
- 2023: Two papers accepted to ICCV 2023 (one Oral) on vision-and-language navigation
- 2022: Co-authored 'HOP+' accepted by IEEE TPAMI
- Created Recurrent Transformer and Large Reconstruction Models (LRM)
