Efficient Generative Model Training via Embedded Representation Warmup
Paper
•
2504.10188
•
Published
•
12
•
2
Deyuan Liu
SempraETY
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
21 minutes ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
liked
a model
7 days ago
Lightricks/LTX-2
liked
a model
10 days ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Organizations
None yet
commented
a
paper
9 months ago