Scholar
Renrui Zhang
Google Scholar ID: YlL3xN4AAAAJ
Seed ByteDance & MMLab & PKU
Citations & Impact
Citations
14,776
H-index
50
i10-index
93
Publications
20
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Selected as World's Top 2% Scientists by Stanford University in 2025
- 9 papers accepted at NeurIPS 2025
- 1 paper at ICML 2025; 5 at ICLR 2025 (including 2 Spotlight); 3 at CVPR 2025 (including 1 Highlight); 4 at ECCV 2024; 3 at ICML 2024; 7 at CVPR 2024 (including 2 Highlight); 4 at ICLR 2024
- Led or co-led the release of multiple influential models and projects: Seed1.5-VL (state-of-the-art multimodal large models), T2I-R1 (introducing R1 reasoning into image generation), HybridVLA (first unifying autoregression and diffusion in VLA), Image Generation with CoT (first exploring CoT strategies in autoregressive text-to-image generation), Video-MME (selected as one of the 14 Groundbreaking Studies in 2024), LLaVA-OneVision (latest LLaVA for image/video/interleaved scenarios), LLaVA-NeXT-Interleave, MAVIS (for multimodal mathematical reasoning), and MathVerse (novel benchmark with CoT evaluation)
- Key contributions as project lead or equal first author in works such as 'Can We Generate Images with CoT?' (CVPR 2025), 'MME-CoT' (arXiv 2025), 'MAVIS' (ICLR 2025), and 'MathVerse'
