alphaFeedback
XH

Xiangyu Hong

cs.AIcs.CLcs.CVcs.LGcs.RO

On Valency

published · living versions
W_mebhrdwy·v1 · currentpublished
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
with Ermo Hua, Baiting Wu, Che Jiang, Haozheng Hou +9
1 version

Preprints & journals

6 papers in the corpus · 2024–2026
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE2610.27598v1 · Ermo Hua, Xiangyu Hong, Baiting Wu et al.2026 · 0 citationsarXivon Valency
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning2608.14290v1 · Kai Chen, Jifeng Ding, Ning Ding et al.2026 · 0 citationsarXiv
DePass: Unified Feature Attributing by Simple Decomposed Forward Pass2510.18462v2 · Xiangyu Hong, Che Jiang, Kai Tian et al.2025 · 1 citationarXiv
On the token distance modeling ability of higher RoPE attention dimension2410.08703v2 · Xiangyu Hong, Che Jiang, Biqing Qi et al.2024 · 2 citationsarXiv
On Large Language Models' Hallucination with Regard to Known Facts2403.20009v2 · Che Jiang, Biqing Qi, Xiangyu Hong et al.2024 · 18 citationsarXiv
Career total: 11 works. 6 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.