ZG
Zhong Guan
cs.AIcs.LGcs.ROcs.DCcs.CLcs.CRcs.CV
On Valency
published · living versionsW_zbunfz7y·v1 · currentpublished
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
with Wenhui Chen, Shiwen Cheng, Hao Dong, Chenda Duan +38
1 version
Preprints & journals
12 papers in the corpus · 2025–2026Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work2609.11977v1 · Wenhui Chen, Shiwen Cheng, Hao Dong et al.2026 · 0 citationsarXivon Valency
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization2609.02964v1 · Haozhang Li, Yangguang Shao, Xinjie Lin et al.2026 · 0 citationsarXiv
From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation2607.19395v1 · Yihan Wang, Zhong Guan, Haoran Sun et al.2026 · 0 citationsarXiv
Robust Contrastive Graph Clustering with Adaptive Local-Global Integration2605.28209v2 · Lei Zhang, Fubo Sun, Haipeng Yang et al.2026 · 0 citationsarXiv
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training2605.17923v1 · Yucheng Guo, Yongjian Guo, Zhong Guan et al.2026 · 0 citationsarXiv
D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models2605.13276v2 · Yucheng Guo, Yongjian Guo, Zhong Guan et al.2026 · 0 citationsarXiv
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction2605.12070v3 · Zhong Guan, Yongjian Guo, Haoran Sun et al.2026 · 0 citationsarXiv
Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training2605.07288v1 · Jiaxuan Gao, Yongjian Guo, Zhong Guan et al.2026 · 0 citationsarXiv
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models2605.07794v1 · Wen Huang, Haoran Sun, Yongjian Guo et al.2026 · 0 citationsarXiv
Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure2603.11101v2 · Yongjian Guo, Yunxuan Ma, Haoran Sun et al.2026 · 0 citationsarXiv
RL-VLA: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training2602.05765v3 · Haoran Sun, Yongjian Guo, Zhong Guan et al.2026 · 0 citationsarXiv
Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration2508.16677v1 · Zhong Guan, Likang Wu, Hongke Zhao et al.2025 · 0 citationsarXiv
Career total: 12 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.