Zhenxing Mi

Mifucius

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 8 days ago

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

upvoted a paper 5 months ago

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

upvoted a paper 7 months ago

WildActor: Unconstrained Identity-Preserving Video Generation

View all activity

Organizations

None yet

Papers 5

arxiv:2511.18922

arxiv:2505.02005

arxiv:2502.10458

arxiv:2411.11374

models 1

Mifucius/ThinkDiff

Updated Sep 7, 2025 • 2

datasets 0

None public yet