Wu's picture

Wu

Diankun

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

MARS: Enabling Autoregressive Models Multi-Token Generation

upvoted a paper about 1 month ago

SimRecon: SimReady Compositional Scene Reconstruction from Real Videos

authored a paper about 1 month ago

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

View all activity

Organizations

Collections 1

Papers 5

arxiv:2603.12255

arxiv:2507.07982

arxiv:2505.23747

arxiv:2408.12601

models 3

Diankun/Spatial-MLLM-v1.1-Instruct-820K

Video-Text-to-Text • 6B • Updated Jan 17 • 67

Diankun/Spatial-MLLM-v1.1-Instruct-135K

Video-Text-to-Text • 5B • Updated Jan 17 • 146

Diankun/Spatial-MLLM-subset-sft

Video-Text-to-Text • 5B • Updated Jun 10, 2025 • 289 • 3

datasets 1

Diankun/Spatial-MLLM-Data

Viewer • Updated Jan 17 • 8.19k • 42