Congratulations to the Livermore researchers whose work has been accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) on June 3–7 in Denver. Follow @Livermore_Comp on X with the #CVPR2026 hashtag. Workshop websites and paper preprints are linked below.

Paper: Interpretable and Steerable Concept Bottleneck Sparse Autoencoders | Vivek Narayanaswamy, Shusen Liu, Wesam Sakla, Kowshik Thopalli

Poster: ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation | Rudrasis Chakraborty

Workshop: Trustworthy, Robust, Uncertainty-Aware, and Explainable Visual Intelligence and Beyond (TRUE-V) | Bhavya Kailkhura, Kowshik Thopalli