5 papers
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Amandeep Kumar, Vishal M. Patel
Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these…
Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation
Buddhi Wijenayake, Nichula Wasalathilake, Roshan Godaliyadda +3
Long-tailed class imbalance remains a fundamental obstacle in semantic segmentation of high-resolution remote-sensing imagery, where dominant classes shape learned representations…
CGCE: Classifier-Guided Concept Erasure in Generative Models
Viet Nguyen, Vishal M. Patel
Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the gen…
AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data
Nidhi Soley, Vishal M Patel, Casey O Taylor
In this study, we present AttentiveGRUAE, a novel attention-based gated recurrent unit (GRU) autoencoder designed for temporal clustering and prediction of outcome from longitudina…
Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark
Nisarg A. Shah, Amir Ziai, Chaitanya Ekanadham +1
While recent advancements in vision-language models have improved video understanding, diagnosing their capacity for deep, narrative comprehension remains a challenge. Existing ben…