Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xinyu Chen

Xinyu Chen

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×1Architecture×1

Frequent co-authors

Zhuoyu Wang1×
Junnan Huang1×
Jiaxiang Zou1×
Yonghao Chen1×
Ruilong Wu1×

Research Timeline

2026
MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations

MixFP4 introduces a mixed micro-format extension to NVFP4, allowing blocks to dynamically select between two stored FP4 formats (E2M1 and E1M2) to improve quantization accuracy without altering the standard hardware execution path.

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding

TAPS introduces a target-aware prefix selection method that optimizes the trade-off between draft tree acceptance and verification cost, achieving significant speedups in speculative decoding.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 30, 2026

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding

Zhuoyu Wang, Junnan Huang, Xinyu Chen

TAPS introduces a target-aware prefix selection method that optimizes the trade-off between draft tree acceptance and verification cost, achieving significant speedups in speculative decoding.

View →
cs.ARRecentMay 29, 2026

MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations

Jiaxiang Zou, Yonghao Chen, Ruilong Wu, Xinyu Chen

MixFP4 introduces a mixed micro-format extension to NVFP4, allowing blocks to dynamically select between two stored FP4 formats (E2M1 and E1M2) to improve quantization accuracy without altering the st…

View →