HangzhouDianziUniversity

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

yxl66666 authored a paper 20 days ago

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

yxl66666 authored a paper about 1 month ago

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

yxl66666 authored a paper about 1 month ago

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning

View all activity

models 0

None public yet

datasets 0

None public yet