Noah Siegel

Computer Science · Physical Sciences

12h-index806citations34works17.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(15), Explainable Artificial Intelligence (XAI)(6), Adversarial Robustness in Machine Learning(5), Topic Modeling(4), Robotic Locomotion and Control(4)

Publications34 total

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
arXiv (Cornell University)·2026Open Access
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
arXiv (Cornell University)·2026Open Access
Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
arXiv (Cornell University)·2025Open Access
The Effect of Model Size on LLM Post-hoc Explainability via LIME
arXiv (Cornell University)·2024· 1 citedOpen Access
Learning agile soccer skills for a bipedal robot with deep reinforcement learning
Science Robotics·2024· 136 cited
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
arXiv (Cornell University)·2024Open Access
On scalable oversight with weak LLMs judging strong LLMs
2024
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
2024Open Access
Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
arXiv (Cornell University)·2023· 6 citedOpen Access
Solving math word problems with process- and outcome-based feedback
arXiv (Cornell University)·2022· 21 citedOpen Access
Figure Data for the paper "From Motor Control to Team Play in Simulated Humanoid Football"
Zenodo (CERN European Organization for Nuclear Research)·2022Open Access
Figure Data for the paper "From Motor Control to Team Play in Simulated Humanoid Football"
2022Open Access
From motor control to team play in simulated humanoid football
Science Robotics·2022· 77 cited
Abstract 1304: Brachytherapy dose heterogeneity primes response to immune checkpoint blockade to generate anti-tumor immunity
Cancer Research·2022
Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
arXiv (Cornell University)·2022· 20 citedOpen Access
Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion
5th Annual Conference on Robot Learning·2021· 5 cited
From Motor Control to Team Play in Simulated Humanoid Football
arXiv (Cornell University)·2021· 12 citedOpen Access
Data-efficient Hindsight Off-policy Option Learning
arXiv (Cornell University)·2021· 6 citedOpen Access
"What, not how": Solving an under-actuated insertion task from scratch
arXiv (Cornell University)·2020· 1 citedOpen Access
Data-efficient Hindsight Off-policy Option Learning
arXiv (Cornell University)·2020· 9 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Nicolas Heess(22), Roland Hafner(14), Markus Wulfmeier(13), Abbas Abdolmaleki(13), Martin Riedmiller(11), Michael Neunert(10), Jost Tobias Springenberg(9), Thomas Lampe(9), Tuomas Haarnoja(8), Saran Tunyasuvunakool(8), Leonard Hasenclever(7), Yuval Tassa(7), Josh Merel(7), Guy Lever(6), Arunkumar Byravan(5), S. M. Ali Eslami(5), Tim Hertweck(5), Jan Humplik(4), Michael Bloesch(4), Nathan Batchelor(4)