2026
NeurIPS 2026 · ED Track
VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
Evaluating ultra-long-context reasoning and omni-modal understanding in long videos.
Haichen He
I am a PhD student at East China Normal University (ECNU), where I am supervised by Prof. Xi Chen and Prof. Xue Yang. My current research focuses on self-evolving agents.
Previously, I was a Research Assistant at Hong Kong Baptist University, supervised by Prof. Kaiyang Zhou. I received my M.S. from Beijing Jiaotong University and my B.S. from Communication University of China.
Publications
Google Scholar ↗2024
ACCV 2024 · Oral
BiEfficient: Bidirectionally Prompting Vision-Language Models for Parameter-Efficient Video Recognition
Bidirectional prompting for parameter-efficient video recognition with vision-language models.
2024
IEEE ISPA 2024
Parallel Assembly Sequence Planning Based on Sparrow Search Algorithms
2024 IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 42–49.
Education & experience
Sep 2026 — Present
Sep 2025 — Aug 2026
Sep 2022 — Jun 2025
Beijing Jiaotong University
M.S.
Sep 2018 — Jun 2022
Communication University of China
B.S.