Scholar
Qiyang Li
Google Scholar ID: qlwwdfEAAAAJ
University of California, Berkeley
Artificial Intelligence in Robotics
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,824
H-index
13
i10-index
13
Publications
20
Co-authors
29
list available
Publications
11 items
Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
2026
Cited
0
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
2026
Cited
0
AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
2026
Cited
0
Q-learning with Adjoint Matching
2026
Cited
1
FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
arXiv.org · 2026
Cited
0
Decoupled Q-Chunking
2025
Cited
0
Reinforcement Learning with Action Chunking
2025
Cited
0
EXPO: Stable Reinforcement Learning with Expressive Policies
2025
Cited
0
Load more
Co-authors
14 total
Sergey Levine
UC Berkeley, Physical Intelligence
Roger Grosse
Associate Professor, University of Toronto
Cem Anil
University of Toronto; Vector Institute
Angela Schoellig
Professor of Robotics, Technical University of Munich and University of Toronto
Xuchan Bao
University of Toronto
Aviral Kumar
Carnegie Mellon University
Sicong(Sheldon) Huang
University of Toronto
Sageev Oore
Associate Professor,Dalhousie University; Faculty Affiliate, Vector Institute
