-
A False Sense of Safety: Unsafe Information Leakage in 'Safe' AI Responses
Paper • 2407.02551 • Published • 7 -
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
Paper • 2407.03300 • Published • 11 -
TokenPacker: Efficient Visual Projector for Multimodal LLM
Paper • 2407.02392 • Published • 21 -
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
Paper • 2407.02687 • Published • 22
Cheung
Weekendsalty
AI & ML interests
None yet
Organizations
None yet
Collections
1
models
None public yet
datasets
None public yet