Hongcan Guo
Scholar

Hongcan Guo

Google Scholar ID: -hKl_DUAAAAJ
BUPT, ByteDance Seed
Large Language ModelReinforcement LearningMixture of ExpertsDiffusion Model
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
13
 
H-index
1
 
i10-index
1
 
Publications
6
 
Co-authors
3
list available
Contact
Emailhongcanguo@gmail.comCVOpen ↗GitHubOpen ↗
Publications
7 items
Disentangling Deception and Hallucination Failures in LLMs
2026
Cited
0
Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
2026
Cited
0
VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization
2025
Cited
0
A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
2025
Cited
0
Advancing Compositional LLM Reasoning with Structured Task Relations in Interactive Multimodal Communications
2025
Cited
0
Two Is Better Than One: Rotations Scale LoRAs
2025
Cited
0
Advancing Expert Specialization for Better MoE
2025
Cited
0
Resume (English only)
Co-authors
3 total
Guoshun Nan
Guoshun Nan
Professor of Beijing University of Posts and Telecommunications
Tony Q.S. Quek
Tony Q.S. Quek
Associate Provost (AI & Digital Innovation) and Chair Professor, SUTD
Sicong Leng
Sicong Leng
Nanyang Technological University