HW

Haiyu Wang

cs.LGcs.ARcs.CV

On Valency

published · living versions

W_jwa95vfk·v1 · currentpublished

HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE Models

with Sai Qian Zhang, Zechun Liu, Steven Li

1 version

Preprints & journals

4 papers in the corpus · 2026

Acceptance-Aware Draft Model Training for Speculative Decoding2609.24150v1 · Tianhua Xia, Mugilan Ganesan, Yifei Feng et al.2026 · 0 citationsarXiv

EPIC: A System Framework for Efficient Egocentric Perception on Embodied AR Glasses2606.15859v1 · Tianhua Xia, Haiyu Wang, Jiajing Zheng et al.2026 · 0 citationsarXiv

LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models2606.00573v2 · Haiyu Wang, Yutong Wang, Leshu Li et al.2026 · 0 citationsarXiv

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models2604.02570v1 · Haiyu Wang, Yutong Wang, Jack Jiang et al.2026 · 0 citationsarXiv

Career total: 4 works. 4 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.