CE⁴L: Continual Ego, Exo, and Ego-Exo Learning
Introduces a multi-view continual learning benchmark spanning four video tasks and VISTA, a lightweight adapter method with training-free subspace routing for simultaneous task and viewpoint shifts.
Hongwei Yan 燕鸿伟
PhD student · School of Life Sciences, Tsinghua University
I am a PhD student in Biology at Tsinghua University, jointly advised by Prof. Yi Zhong in the School of Life Sciences and Prof. Kaisheng Ma in the Institute for Interdisciplinary Information Sciences (IIIS). I received my B.Eng. in Computer Science from Tsinghua's Yao Class at IIIS in 2022.
I'm interested in how insights from learning and memory in the brain can lead to better AI, and how AI can help us study the brain. I collaborate with Prof. Liyuan Wang in Tsinghua's Department of Psychological and Cognitive Sciences, and work with Dr. Bo Lei as a research intern in the Brain-inspired AI group at the Beijing Academy of Artificial Intelligence (BAAI).
Research
- Brain-inspired AI. I explore how foundation models and agents can accumulate knowledge, reason, adapt over time, and improve through experience. My research draws on biological learning and memory, with published work in continual learning and generalization.
- AI for Science. I build foundation models from neural and biological data and develop AI tools for neuroscience and computational biology, spanning multimodal representations, transcriptomics, and scientific data acquisition and analysis.
Selected publications
All publications* Equal contribution.
FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
Combines brain-inspired random-expanded routing with temporal-ensemble experts to learn from single-pass, evolving data streams without explicit task boundaries.
Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
Introduces a time interval between teacher and student updates in online and self-distillation, connecting improved generalization to flatter optimization landscapes.
Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
Coordinates experts at multiple network depths with multi-level supervision and reverse self-distillation to balance underfitting and overfitting in online continual learning.