Kaican Li's picture

Kaican Li PRO

m-Just

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

upvoted a paper 1 day ago

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

upvoted a paper 1 day ago

VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?

View all activity

Organizations

None yet

Collections 1

Papers 4

arxiv:2512.18745

arxiv:2411.19757

arxiv:2203.07724

arxiv:2106.03721

models 1

m-Just/InSight-o3-vS

Image-Text-to-Text • 8B • Updated Jan 29 • 3

datasets 3

m-Just/InfoVQA_RegionLocalization

Viewer • Updated Jan 29 • 10.2k • 35 • 1

m-Just/VisCoT_VStar_Collage

Viewer • Updated Jan 29 • 15.3k • 126 • 2

m-Just/O3-Bench

Viewer • Updated Jan 26 • 345 • 370 • 16