Kangyu Wang — accepted AI-conference papers

2026

CogStream: Context-guided Streaming Video Question Answering

Zicheng Zhao, Kangyu Wang, Shijie Li, Rui Qian, Weiyao Lin, Huabin Liu

AAAI 2026technical

Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available historical contextual information into Vid-LLMs, resulting in a sign

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding

Zhihao He, Tieyuan Chen, Kangyu Wang, Ziran Qin, Yang Shao, Chaofan Gan +3

ICML 2026poster

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck: strictly unidirectional attention compromises *understanding …

Cited by 3 Source ↗Scholar ↗