Zhijiang Tang (唐治江)

Zhijiang Tang (唐治江)

M.S. student in AI at UCAS (Hangzhou Institute for Advanced Study). LLM post-training, multimodal evaluation, and agent RL.

Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation

Published in 34th ACM International Conference on Multimedia (ACM MM), 2026

First author. Under review at ACM MM 2026 (CCF-A). Decouples long-context video quality from short-video metrics via DSA + MLLM scoring; validated with perturbation and human studies (Spearman 0.76).

Recommended citation: Tang, Z., Qi, J., Zhao, B., & Huang, J. (2026). "Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation." ACM MM 2026 (under review).
Download Paper