← 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。
D
Ding Gao
MSc student in Chengdu, mostly working on multimodal models — speech, vision, and the messy parts where they meet.
- 公司
- UESTC
- 位置
- Chengdu, China
- Stars
- 2
- 粉丝 / 仓库
- 1
代表作品 / 项目
- cross-modal-alignment-bench⭐ 1Vision-speech grounding benchmark for audio-visual MLLMs with controlled distractor strategies
- codec-layer-probe⭐ 1Layer-wise representation analysis for neural speech codecs (CKA, SVCCA, mutual information, linear probes)
- verl-omni⭐ 0Multimodal RL training framework for diffusion & omni models
- K12-KGraph⭐ 0A curriculum-aligned knowledge graph, benchmark, and multimodal training dataset for evaluating and improving curriculum cognition in educational LLMs.
- spectrum-ts⭐ 0Bring agents to any interfaces