Author

Langshi Chen

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool

Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost operators, but the dominant attention cost scales with the sum of squared sequence lengths. Thus, equally sized packed sequences drawn from a l...

Yan Wang, Xiu-Long Yuan, Kaiming Yang et al. · arXiv.org · 1 citation

#natural language process... Preprint Aug 2026

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

The architecture and the Muon optimizer together shift the optimal learning rate and batch size upwards, render batch-size warmup unnecessary, and substantially improve stability under stress tests.

Zi-Han Qiu, Zekun Wang, Xiao Li et al. · 20 citations · ⚡2