2.6B开源世界模型撑1分钟720p (opens in new tab)

同一天两篇 AR 视频蒸馏指向同一个瓶颈位移——单步成本不再是主要矛盾,long rollout 的训练-推理分布漂移接力上位;SANA-WM 用混合线性注意力把分钟级 720p 世界模型拉到 2.6B;多模态长期记忆评测、统一 agentic/latent 视觉推理、合成分层设计数据三篇也值得读。

Read the original article
Sign in to keep reading the full article.

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help