no code implementations • 25 Nov 2024 • Yanwei Wang, Lirui Wang, Yilun Du, Balakumar Sundaralingam, Xuning Yang, Yu-Wei Chao, Claudia Perez-D'Arpino, Dieter Fox, Julie Shah
Generative policies trained with human demonstrations can autonomously accomplish multimodal, long-horizon tasks.
no code implementations • 25 Mar 2024 • Yanwei Wang, Tsun-Hsuan Wang, Jiayuan Mao, Michael Hagenow, Julie Shah
Grounding the common-sense reasoning of Large Language Models (LLMs) in physical domains remains a pivotal yet unsolved problem for embodied AI.
no code implementations • 23 Feb 2024 • Eike Schneiders, Christopher Fourie, Stanley Celestin, Julie Shah, Malte Jung
This paper contributes to the Human-Computer/Robot Interaction (HCI/HRI) literature using a human-centred approach to identify characteristics of entrainment during pair- and group-based collaboration.
1 code implementation • 11 Oct 2023 • Lindsay Sanneman, Mycal Tucker, Julie Shah
This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.
no code implementations • 12 Jul 2023 • Andi Peng, Aviv Netanyahu, Mark Ho, Tianmin Shu, Andreea Bobu, Julie Shah, Pulkit Agrawal
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments.
1 code implementation • 18 May 2023 • Cristian-Paul Bara, Ziqiao Ma, Yingzhuo Yu, Julie Shah, Joyce Chai
To complete these tasks, agents need to engage in situated communication with their partners and coordinate their partial plans towards a complete plan to achieve a joint task goal.
no code implementations • 3 Feb 2023 • Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie Shah, Anca D. Dragan
To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior.
no code implementations • 31 Oct 2022 • Peter Stone, Rodney Brooks, Erik Brynjolfsson, Ryan Calo, Oren Etzioni, Greg Hager, Julia Hirschberg, Shivaram Kalyanakrishnan, Ece Kamar, Sarit Kraus, Kevin Leyton-Brown, David Parkes, William Press, AnnaLee Saxenian, Julie Shah, Milind Tambe, Astro Teller
In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
no code implementations • 27 Oct 2022 • Michael L. Littman, Ifeoma Ajunwa, Guy Berger, Craig Boutilier, Morgan Currie, Finale Doshi-Velez, Gillian Hadfield, Michael C. Horowitz, Charles Isbell, Hiroaki Kitano, Karen Levy, Terah Lyons, Melanie Mitchell, Julie Shah, Steven Sloman, Shannon Vallor, Toby Walsh
In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
no code implementations • 30 Jun 2022 • Mycal Tucker, Julie Shah, Roger Levy, Noga Zaslavsky
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication.
no code implementations • 9 Jun 2022 • Yanwei Wang, Nadia Figueroa, Shen Li, Ankit Shah, Julie Shah
In this work, we identify the roots of this challenge as the failure of a learned continuous policy to satisfy the discrete plan implicit in the demonstration.
1 code implementation • 27 May 2022 • Mycal Tucker, Julie Shah
Artificial neural nets can represent and classify many types of data but are often tailored to particular applications -- e. g., for "fair" or "hierarchical" classification.
1 code implementation • 18 May 2022 • Yilun Zhou, Julie Shah
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency.
1 code implementation • NAACL 2022 • Yilun Zhou, Marco Tulio Ribeiro, Julie Shah
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment.
1 code implementation • NAACL 2022 • Mycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy, Julie Shah
Recent causal probing literature reveals when language models and syntactic probes use similar representations.
no code implementations • 26 Jan 2022 • Mycal Tucker, William Kuhl, Khizer Shahid, Seth Karten, Katia Sycara, Julie Shah
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified.
1 code implementation • NAACL (TrustNLP) 2022 • Yiming Zheng, Serena Booth, Julie Shah, Yilun Zhou
We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved.
no code implementations • 8 Oct 2021 • Lindsay Sanneman, Julie Shah
One context where human understanding of agent reward functions is particularly beneficial is in the value alignment setting.
no code implementations • NeurIPS 2021 • Mycal Tucker, Huao Li, Siddharth Agrawal, Dana Hughes, Katia Sycara, Michael Lewis, Julie Shah
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone.
no code implementations • 6 Jul 2021 • Ankit Shah, Pritish Kamath, Shen Li, Patrick Craven, Kevin Landers, Kevin Oden, Julie Shah
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
1 code implementation • 27 Apr 2021 • Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, Julie Shah
Feature attribution methods are exceedingly popular in interpretable machine learning.
no code implementations • 28 Mar 2021 • Ramya Ramakrishnan, Vaibhav Unhelkar, Ece Kamar, Julie Shah
Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand.
no code implementations • 4 Mar 2020 • Ankit Shah, Samir Wadhwania, Julie Shah
Defining sound and complete specifications for robots using formal languages is challenging, while learning formal specifications directly from demonstrations can lead to over-constrained task policies.
1 code implementation • 19 Feb 2020 • Serena Booth, Yilun Zhou, Ankit Shah, Julie Shah
To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx.
no code implementations • 16 Jan 2020 • Mycal Tucker, Yilun Zhou, Julie Shah
Robotic agents must adopt existing social conventions in order to be effective teammates.
no code implementations • 9 Jan 2020 • Serena Booth, Ankit Shah, Yilun Zhou, Julie Shah
In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming.
no code implementations • 23 May 2018 • Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey, Julie Shah, Eric Horvitz
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments.
no code implementations • 11 May 2018 • Matthew Gombolay, Reed Jensen, Jessica Stigile, Toni Golen, Neel Shah, Sung-Hyun Son, Julie Shah
We empirically demonstrate that this approach accurately learns multifaceted heuristics on a synthetic data set incorporating job-shop scheduling and vehicle routing problems, as well as on two real-world data sets consisting of demonstrations of experts solving a weapon-to-target assignment problem and a hospital resource allocation problem.
no code implementations • NeurIPS 2014 • Been Kim, Cynthia Rudin, Julie Shah
We present the Bayesian Case Model (BCM), a general framework for Bayesian case-based reasoning (CBR) and prototype classification and clustering.
no code implementations • 24 May 2014 • Stefanos Nikolaidis, Keren Gu, Ramya Ramakrishnan, Julie Shah
We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human.
no code implementations • 5 Jun 2013 • Been Kim, Caleb M. Chacha, Julie Shah
We present an algorithm that reduces this translation burden by inferring the final plan from a processed form of the human team's planning conversation.