4 papers · 1 filter
HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
Arani Roy, Shristi Das Biswas, Kaushik Roy
Text-to-image diffusion models can generate visually stunning images, yet, controlling what appears and how it appears, remains surprisingly difficult, especially when operating so…
Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation
Shristi Das Biswas, Arani Roy, Kaushik Roy
Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, infe…
CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
Shristi Das Biswas, Arani Roy, Kaushik Roy
As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content. Existing safety interventions - ranging from training…
Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition
Shristi Das Biswas, Efstathia Soufleri, Arani Roy +1
Training robust deep video representations has proven to be computationally challenging due to substantial decoding overheads, the enormous size of raw video streams, and their inh…