Author

Zhong Guan

Observed name: Guan, Zhong

Institutions: Tianjin University, Chinese Academy of Sciences, Jingdong (China), Infrared Laboratories (United States), University of Chinese Academy of Sciences

Observed institutions: Tianjin University, Chinese Academy of Sciences, Jingdong (China), Infrared Laboratories (United States), University of Chinese Academy of Sciences

OpenAlex ID: A5125195887

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

2026 · Chen, Wenhui, Cheng, Shiwen, et al. · arXiv (Cornell University)

When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization

2026 · Li, Haozhang, Shao, Yangguang, et al. · arXiv (Cornell University)

Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

2026 · Lei Zhang, Fubo Sun, et al. · International Joint Conference on Artificial Intelligence

From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation

2026 · Wang, Yihan, Guan, Zhong, et al. · arXiv (Cornell University)

AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training

2026 · Guo, Yucheng, Guo, Yongjian, et al. · arXiv (Cornell University)

D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models

2026 · Guo, Yucheng, Guo, Yongjian, et al. · arXiv (Cornell University)

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

2026 · Guan, Zhong, Guo, Yongjian, et al. · arXiv (Cornell University)

Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training

2026 · Gao, Jiaxuan, Guo, Yongjian, et al. · arXiv (Cornell University)

NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models

2026 · Huang, Wen, Sun, Haoran, et al. · arXiv (Cornell University)

Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure

2026 · Guo, Yongjian, Ma, Yunxuan, et al. · arXiv (Cornell University)

RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training

2026 · Sun, Haoran, Guo, Yongjian, et al. · arXiv (Cornell University)

Works count: 12

Citation count:

H-index:

I10-index: