← 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。
Q
Qizhe Zhang
Ph.D. candidate at Peking University. Interested in multimodal large language models and unified multimodal models.
- 公司
- Peking University
- 位置
- Beijing, China
- Stars
- 401
- 粉丝 / 仓库
- 46
代表作品 / 项目
- FasterVLM⭐ 116Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
- CDPruner⭐ 110[NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.
- VisPruner⭐ 85[ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
- MahjongZero⭐ 34MahjongZero: DouZero for Mahjong | 麻将AI
- BiCross-old⭐ 14BiCross (Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer).