UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
Paper • 2508.05399 • Published • 17 •
4
Wonjun Kang
wjkang
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts upvoted a paper 8 months ago
ParallelBench: Understanding the Trade-offs of Parallel Decoding in
Diffusion LLMs authored a paper 10 months ago
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache
RematerializationOrganizations
commented a
paper 11 months ago
commented a
paper over 1 year ago