239 citations · 430 across the 19 of their papers we have counts for
21 papers
TEMPO: Learning Temporal Context for Dynamic Robot Manipulation
Zhenyang Feng, Jimin Heo, Erik B. Sudderth +1
Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks because they operate on a single o…
"It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models
Kapil Garg, Xinru Tang, Jimin Heo +4
Vision-Language Models (VLMs) are increasingly used by blind and low-vision (BLV) people to identify and understand products in their everyday lives, such as food, personal care it…
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
Ali Younis, Erik B. Sudderth
For challenging state estimation problems arising in domains like vision and robotics, particle-based representations attractively enable temporal reasoning about multiple posterio…
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
Sakshi Agarwal, Gabriel Hope, Jimin Heo +1
Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditio…
Bayesian temporal biclustering with applications to multi-subject neuroscience studies
Federica Zoe Ricci, Erik B. Sudderth, Jaylen Lee +3
We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their rec…
Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
Ali Younis, Erik Sudderth
Particle filters flexibly represent multiple posterior modes nonparametrically, via a collection of weighted samples, but have classically been applied to tracking problems with kn…