THU-MUG

university

Activity Feed Request to join this org

AI & ML interests

Multimodal Learning

Recent Activity

kkakkkka published a model 3 days ago

kkakkkka submitted a paper 5 months ago

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

kkakkkka submitted a paper 10 months ago

MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment

View all activity

Organization Card

Community About org cards

Multimodal Understanding & Generation Group (MUG), Intelligence Computing Lab, Tsinghua University

models 6

thuteam/CoG

Updated 3 days ago • 3

thuteam/CLD

Updated Dec 7, 2025 • 7

thuteam/S2C

Updated Sep 4, 2025 • 5

thuteam/ETRIS

Updated Jun 26, 2025 • 3

thuteam/DETRIS

Updated Jan 17, 2025 • 5

thuteam/MambaTalk

Updated Jan 11, 2025 • 5

datasets 0

None public yet