works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

astro-ph.IM2026

JWST MIRI Medium Resolution Spectrometer Point Fixed Pattern Corrections: Cleaner and Higher Signal-to-Noise Spectra of Point Sources

Karl D. Gordon, David R. Law

The JWST Mid-Infrared Instrument Medium Resolution Spectrometer provides the capability to obtain spectra from 5-28 micron. The JWST data reduction pipeline removes the majority bu…

cs.RO2026

A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation

Yunhai Feng, Natalie Leung, Jiaxuan Wang +3

The paper introduces REGRIND, a simple pipeline that retargets a single human hand‑object demonstration to a robot hand and uses reinforcement learning to train a residual policy t…

cs.LG2026

Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning

Brett Barkley, Preston Culbertson, David Fridovich-Keil

Models trained with deep learning often fail to signal when inputs fall outside their training data manifold, leading to unreliable predictions under distribution shift. Prior work…

cs.RO2026

Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation

John Z. Zhang, Maks Sorokin, Jan Brüdigam +14

This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our key insight is that by perfor…

cs.RO2026

TransMASK: Masked State Representation through Learned Transformation

Sagar Parekh, Preston Culbertson, Dylan P. Losey

Humans train robots to complete tasks in one environment, and expect robots to perform those same tasks in new environments. As humans, we know which aspects of the environment (i.…

cs.RO2026

Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation

Lara Brudermüller, Brandon Hung, Xinghao Zhu +4

We present a generative predictive control (GPC) framework that amortizes sampling-based Model Predictive Control (SPC) by bootstrapping it with conditional flow-matching models tr…