← 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。
方
方先生
M.Eng. student @ ZJU CCNT Lab. Building and breaking multimodal LLMs, speech models, and vision systems. Sometimes things work.
- 公司
- @ZJU-CCNT
- 位置
- Hangzhou, China
- Stars
- 3
- 粉丝 / 仓库
- 2
代表作品 / 项目
- LightVLM⭐ 1Efficient vision-language inference via dynamic visual token pruning — 2-5x faster prefill with minimal accuracy drop
- speechllm-bench⭐ 1Comprehensive benchmark and evaluation harness for speech large language models: ASR, SER, speech translation, and TTS quality
- vl-data-engine⭐ 1Scalable data processing pipeline for vision-language pretraining: quality filtering, deduplication, and bilingual caption augmentation
- MemoryBear⭐ 0MemoryBear Equip AI with human-like memory capability
- Dressage⭐ 0Scalable RL for Any Agent and Sandbox.