alphaFeedback
GS

Guangming Sheng

cs.DCcs.LGcs.AIcs.CL

On Valency

published · living versions
W_vfnqaepu·v1 · currentpublished
BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design
with Dayou Du, Woon Yee Ng, Nick Lau, Jianyi Cheng +1
1 version

Preprints & journals

10 papers in the corpus · 2023–2026
PrefixFlow: Training-Time KV Caching for Schedule-Level Prefix Reuse in LLM RL Training2606.01143v4 · Pengbo Li, Feiyuan Zhang, Guangming Sheng et al.2026 · 0 citationsarXiv
Laminar: A Scalable Asynchronous RL Post-Training Framework2510.12633v1 · Guangming Sheng, Yuxuan Tong, Borui Wan et al.2025 · 2 citationsarXiv
Robust LLM Training Infrastructure at ByteDance2509.16293v4 · Borui Wan, Gaohong Liu, Zuquan Song et al.2025 · 10 citationsarXiv
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning2504.13914v3 · ByteDance Seed: Jiaze Chen, Tiantian Fan, Xin Liu et al.2025 · 1 citationarXiv
DAPO: An Open-Source LLM Reinforcement Learning System at Scale2503.14476v2 · Qiying Yu, Zheng Zhang, Ruofei Zhu et al.2025 · 53 citationsarXiv
HybridFlow: A Flexible and Efficient RLHF Framework2409.19256v2 · Guangming Sheng, Chi Zhang, Zilingfeng Ye et al.2024 · 74 citationsarXiv
MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline2402.15113v2 · Guangming Sheng, Junwei Su, Chao Huang et al.2024 · 12 citationsarXiv
GNNFlow: A Distributed Framework for Continuous Temporal GNN Learning on Dynamic Graphs2311.17410v2 · Yuchen Zhong, Guangming Sheng, Tianzuo Qin et al.2023 · 0 citationsarXiv
SWIFT: Expedited Failure Recovery for Large-scale DNN Training2302.06173v1 · Yuchen Zhong, Guangming Sheng, Juncheng Liu et al.2023 · 3 citationsIEEE Transactions on Parallel and Distributed Systems ( Volume: 35, Issue: 9, September 2024)
Career total: 13 works. 10 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.