Zichuan Lin
Scholar

Zichuan Lin

Google Scholar ID: Tlc4yaMAAAAJ
Tencent
Reinforcement Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
829
 
H-index
14
 
i10-index
14
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
13 items
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
2026
Cited
0
Debiased Model-based Representations for Sample-efficient Continuous Control
2026
Cited
0
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
2026
Cited
0
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
2026
Cited
0
HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
2026
Cited
0
Cross-Domain Offline Policy Adaptation via Selective Transition Correction
2026
Cited
1
ProAct: Agentic Lookahead in Interactive Environments
2026
Cited
0
PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)