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

Hao Tan

2 indexed papers

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

Publications per year

2
26

Top categories

ML×2AI×2

Frequent co-authors

Yuchen Zhu2×
Jing Shi2×
Chongjian Ge2×
Yiran Xu2×
Wanrong Zhu2×
Jason Kuen2×

Research Timeline

2026
FLARE: Diffusion for Hybrid Language Model

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achieving competitive performance and throughput gains.

FLARE: Diffusion for Hybrid Language Model

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achieving competitive performance and throughput gains.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentJun 1, 2026

FLARE: Diffusion for Hybrid Language Model

Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan +8 more

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

View →
cs.LGcs.AIRecentJun 1, 2026

FLARE: Diffusion for Hybrid Language Model

Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan +8 more

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

View →