Author

Bin Ma

h-index 3 View on Semantic Scholar

We have 3 of 9 papers

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.

Preprint Sep 2026

A Multi-Engine Dataflow for MoE Decoding on AWS Tranium

Mixture-of-Experts (MoE) decoding on scratchpad-based tensor accelerators (STA) is dominated by moving expert weights while the compute engines sit idle. This traffic is hard to hide, because the experts are known only after routing, and hard to shrink without losing quality or adding critical-path work. We present CAR...

Bin Ma, Wen-Jie Fan, Jia-Lin Liu et al. · 0 citations

Open access Sep 2026

ZenFlow: Enabling Stall-Free Offloading for LLM Training

Fine-tuning large language models (LLMs) often exceeds GPU memory limits, prompting systems to offload model states to CPU memory. However, existing offloaded training frameworks like ZeRO-Offload treat all parameters equally and update the full model on the CPU, causing severe GPU stalls, where fast, expensive GPUs si...

Ting-Feng Lan, Yu-Sen Wu, Bin Ma et al. · Proceedings of the ACM on Ma... · 0 citations

Jul 2026

Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models

This work presents a principled framework that penalises or compensates anomalous confidence arising from collapsed generation patterns, by comparing a token's observed frequency against its corpus prior through an adjacent-conditional probability construction.

Wenjie Fan, Bin Ma, Dong Li · arXiv.org · 0 citations