Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generationby Michael Ogezi, Ning ShiFirst…
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learningby Mark D. McDonnell,…
Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generationby Junyan…
Synthetic Privileged Information Enhances Medical Image Representation Learningby Lucas Farndale, Chris Walsh, Robert Insall, Ke…
Denoising Autoregressive Representation Learningby Yazhe Li, Jorg Bornschein, Ting ChenFirst submitted to arxiv on: 8…
ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transportby Nazar Buzun, Maksim…
Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformerby Naifu Xue, Qi Mao,…
Behavior Generation with Latent Actionsby Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur…
Critical windows: non-asymptotic theory for feature emergence in diffusion modelsby Marvin Li, Sitan ChenFirst submitted…
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Modelsby Neta Shaul, Uriel Singer,…