5 papers
Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
Dahye Kim, Jaehyun Choi, Hyun Seok Seong +4
While existing AI-generated image detectors report high performance, we identify that this is largely driven by a critical prediction asymmetry: a bias toward the real class that s…
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal +3
While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted ev…
DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency…
Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
Dahye Kim, Deepti Ghadiyaram
Despite the remarkable progress in text-to-image generative models, they are prone to adversarial attacks and inadvertently generate unsafe, unethical content. Existing approaches…
: Interpreting and leveraging semantic information in diffusion models
Dahye Kim, Xavier Thomas, Deepti Ghadiyaram
We study rich visual semantic information is represented within various layers and denoising timesteps of different diffusion architectures. We uncover monosemantic…