← Search

Shiyu Zhu

2 accepted papers

2026

Teaching to Individual Needs: Bidirectional Teacher-Student Learning for Wheeled-Legged Locomotion

ICRA 2026poster

Reinforcement Learning (RL) enables robust and adaptive locomotion in legged and wheeled-legged robots. A common approach is the Teacher-Student (TS) paradigm, in which a teacher policy with privileged information supervises a proprioceptive student. While the TS paradigm has proven effective on leg…

Cited by 0Scholar
2025

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

ACL 2025finding

Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows t…