Optimizing Few-Step Generation with Adaptive Matching Distillation
Paper • 2602.07345 • Published • 9
Zikai Zhou
Klayand
AI & ML interests
Knowledge Distillation, Generated Models
Recent Activity
upvoted a paper 1 day ago
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model upvoted a paper 3 days ago
Rethinking Classifier-Free Guidance in On-Policy Diffusion DistillationOrganizations
None yet
authored a
paper 5 months ago
submitted a
paper to Daily Papers 5 months ago
authored 3
papers over 1 year ago
Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
Paper • 2411.10781 • Published
Golden Noise for Diffusion Models: A Learning Framework
Paper • 2411.09502 • Published • 1
CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
Paper • 2503.09662 • Published • 33