YuyangXie's picture

5 4

YuyangXie

YuyangXie

·

https://yuyangxie96.github.io/

yuyangxie96

AI & ML interests

Edge LLM, quantization, Speculative decoding, inference

Recent Activity

upvoted a paper 12 days ago

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

upvoted a paper 2 months ago

DFlash: Block Diffusion for Flash Speculative Decoding

upvoted an article 3 months ago

The Optimal Architecture for Small Language Models

View all activity

Organizations

None yet

upvoted a paper 12 days ago

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Paper • 2603.28458 • Published 19 days ago • 42

upvoted a paper 2 months ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 51

upvoted an article 3 months ago

Article

The Optimal Architecture for Small Language Models

Dec 26, 2025

•

120

upvoted a paper 6 months ago

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Paper • 2510.25602 • Published Oct 29, 2025 • 80

upvoted a paper 11 months ago

Scaling Law for Quantization-Aware Training

Paper • 2505.14302 • Published May 20, 2025 • 76