← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
X
Xinchen Zhang
Multimodal Researcher @ByteDance-Seed
- 公司
- Tsinghua University
- 位置
- Beijing
- Stars
- 2,301
- 粉丝 / 仓库
- 77
代表作品 / 项目
- RPG-DiffusionMaster⭐ 1842[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)
- IterComp⭐ 202[ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
- RealCompo⭐ 122[NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
- OmniVerifier⭐ 69[ICLR 2026 Oral & ICML 2026] Generative Universal Verifier as Multimodal Meta-Reasoner
- BoxDiff-XL⭐ 28Extend BoxDiff to SDXL (SDXL-based layout-to-image generation)