Bing-Sheng He

This work develops lightweight characterization methods to uncover per-chip compute topology and memory affinity and uses the discovered information to make existing fine-grained scheduling asymmetry-aware, considering not only how many resources are allocated but also which physical resources are assigned.

Traditional single-session assessments can mislead clinicians by failing to accurately track worsening depression trends, underscoring the need for longitudinal approaches.

NodeImport reveals that strategically filtering nodes based on importance can dramatically enhance GNN performance in imbalanced settings.

LLM judges may misinterpret peer review quality, favoring superficial traits over genuine analytical depth, raising questions about their reliability in academic assessments.

Label Influence Propagation reveals that dynamically adjusting label influences can significantly enhance multi-label node classification performance, outperforming existing methods.

Achieving up to 10x weight compression in LLMs without altering weights could revolutionize GPU memory usage and model deployment efficiency.

A unified hardware acceleration framework for aggregation achieves notable efficiency gains while simplifying programming across diverse platforms.

Run 2x more LLM fine-tuning jobs on the same hardware with MuxTune's clever spatial-temporal multiplexing, making your datacenter greener and your boss happier.