← Search

Shelly Francis-Meretzki

2 accepted papers

2026

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models

ICML 2026poster

Recent advances in vision-language-action (VLA) models for robotics have highlighted the importance of reliable uncertainty quantification in sequential tasks. However, assessing and improving calibration in such settings remains mostly unexplored, especially when only partial trajectories are obser…

Cited by 0SourceScholar
2025

Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames

NeurIPS 2025poster

Behavioral cloning is a simple yet effective technique for learning sequential decision-making from demonstrations. Recently, it has gained prominence as the core of foundation models for the physical world, where achieving generalization requires countless demonstrations of a multitude of tasks. Ty…

Cited by 0SourceScholar