HT

Hongshi Tan

0000-0002-3243-6875

cs.ARcs.AIcs.DCcs.DBcs.LGcs.PFcs.SE

On Valency

published · living versions

W_ut3cd6v2·v1 · currentpublished

VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

with Borui Xu, Wenqi Jiang, Bingsheng He, Ming Wu +2

1 version

Preprints & journals

10 papers in the corpus · 2020–2026

Approaching Shannon Bound with Lossless LLM Weight Compression2606.15789v1 · Hongshi Tan, Yao Chen, Gustavo Alonso et al.2026 · 0 citationsarXiv

Hardware-accelerated Aggregation: Unification and Specialization2606.10030v1 · Alireza Shateri, Hongshi Tan, Michael Ng et al.2026 · 0 citationsarXiv

HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning2605.13536v2 · Qingyun Zou, Feng Yu, Hongshi Tan et al.2026 · 0 citationsarXiv

Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench2605.15226v1 · Qingyun Zou, Feng Yu, Hongshi Tan et al.2026 · 0 citationsarXiv

XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA2605.06052v1 · Feng Yu, Hongshi Tan, Yao Chen et al.2026 · 0 citationsarXiv

RidgeWalker: Perfectly Pipelined Graph Random Walks on FPGAs2601.11057v1 · Hongshi Tan, Yao Chen, Xinyu Chen et al.2026 · 0 citationsarXiv

LightRW: FPGA Accelerated Graph Dynamic Random Walks2304.07004v2 · Hongshi Tan, Xinyu Chen, Yao Chen et al.2023 · 9 citationsarXiv

ReGraph: Scaling Graph Processing on HBM-enabled FPGAs with Heterogeneous Pipelines2203.02676v1 · Xinyu Chen, Yao Chen, Feng Cheng et al.2022 · 48 citationsarXiv

Skew-Oblivious Data Routing for Data-Intensive Applications on FPGAs with HLS2105.04151v1 · Xinyu Chen, Hongshi Tan, Yao Chen et al.2021 · 6 citationsarXiv

HaoCL: Harnessing Large-scale Heterogeneous Processors Made Easy2005.08466v1 · Yao Chen, Xin Long, Jiong He et al.2020 · 1 citationarXiv

Career total: 17 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.