👋 Open to Work

Tianze Xia

Mukayi01

·

Mukayi

AI & ML interests

Computer Vision, MLLM, Diffusion Model

Recent Activity

upvoted a paper 3 days ago

KPage: Cross-Block Page Compaction for Hardware-Efficient Sparse Attention

commentedon a paper 9 days ago

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

authored a paper 10 days ago

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

View all activity

Organizations

upvoted a paper 3 days ago

KPage: Cross-Block Page Compaction for Hardware-Efficient Sparse Attention

Paper • 2610.28096 • Published 12 days ago • 7

upvoted a paper 10 days ago

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

Paper • 2610.29441 • Published 11 days ago • 23

upvoted a paper about 1 month ago

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 68

upvoted a paper over 1 year ago

A Survey of Context Engineering for Large Language Models

Paper • 2507.13334 • Published Jul 17, 2025 • 264