Zikai Zhou

Klayand's activity

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

upvoted a paper 4 days ago

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Paper • 2508.09968 • Published 5 days ago • 13

upvoted 3 papers 4 months ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published Apr 8 • 76

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published Apr 8 • 63

Rethinking Reflection in Pre-Training

Paper • 2504.04022 • Published Apr 5 • 80

upvoted 10 papers 5 months ago

Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs

Paper • 2503.16870 • Published Mar 21 • 6

AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset

Paper • 2503.19462 • Published Mar 25 • 10

Wan: Open and Advanced Large-Scale Video Generative Models

Paper • 2503.20314 • Published Mar 26 • 56

Scale-wise Distillation of Diffusion Models

Paper • 2503.16397 • Published Mar 20 • 42

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Paper • 2503.12937 • Published Mar 17 • 30

Personalize Anything for Free with Diffusion Transformer

Paper • 2503.12590 • Published Mar 16 • 44

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster

Paper • 2503.09662 • Published Mar 12 • 34

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

Paper • 2503.08619 • Published Mar 11 • 20

Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model

Paper • 2503.07703 • Published Mar 10 • 36

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

Paper • 2503.05978 • Published Mar 7 • 36

upvoted 3 papers 6 months ago

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

Paper • 2502.17258 • Published Feb 24 • 80

Magic 1-For-1: Generating One Minute Video Clips within One Minute

Paper • 2502.07701 • Published Feb 11 • 36

Weak-to-Strong Diffusion with Reflection

Paper • 2502.00473 • Published Feb 1 • 23

upvoted a paper 10 months ago

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10, 2024 • 53