MIT HAN Lab

mit-han-lab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

cjy2003 

in mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers about 9 hours ago

Heads identification

4

#1 opened about 21 hours ago by

edmond

Lmxyy 

updated a model 1 day ago

mit-han-lab/nunchaku-artifacts

Updated 1 day ago • 3

Qinghao 

authored a paper 4 days ago

Scaling RL to Long Videos

Paper • 2507.07966 • Published 7 days ago • 129

zhuoyang20 

published 6 models 14 days ago

mit-han-lab/lpd_orders

Updated 14 days ago

mit-han-lab/lpd_xl_512

Updated 22 days ago

mit-han-lab/lpd_l_512

Updated 22 days ago

mit-han-lab/lpd_xxl_256

Updated 22 days ago

mit-han-lab/lpd_xl_256

Updated 22 days ago

mit-han-lab/lpd_l_256

Updated 23 days ago

zhuoyang20 

updated a collection 14 days ago

LPD

Collection

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation • 6 items • Updated 14 days ago • 1

zhuoyang20 

updated a model 14 days ago

mit-han-lab/lpd_orders

Updated 14 days ago

zhuoyang20 

updated a collection 15 days ago

LPD

Collection

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation • 6 items • Updated 14 days ago • 1

Lmxyy 

in mit-han-lab/nunchaku-flux.1-dev 17 days ago

Are there any quality or speed differences between the int4 and fp4 models?

4

#2 opened about 1 month ago by

nymical

Lmxyy 

in mit-han-lab/nunchaku-flux.1-kontext-dev 17 days ago

There is a significant loss in quality, making it impossible to operate normally.

2

#2 opened 17 days ago by

zmlw

Lmxyy 

in mit-han-lab/nunchaku-flux.1-kontext-dev 18 days ago

when will "unquantized_layers.safetensors" and "config.json" for kontext-dev be available? Thank you!!!!!

6

#1 opened 18 days ago by

algaxu

Lmxyy 

authored a paper 20 days ago

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published 23 days ago • 38