Chelsea Finn
Assistant Professor of Computer Science and of Electrical Engineering
Web page: http://ai.stanford.edu/~cbfinn
Bio
Chelsea Finn is an Assistant Professor in Computer Science and Electrical Engineering at Stanford University, and the William George and Ida Mary Hoover Faculty Fellow. Professor Finn's research interests lie in the ability to enable robots and other agents to develop broadly intelligent behavior through learning and interaction. Her work lies at the intersection of machine learning and robotic control, including topics such as end-to-end learning of visual perception and robotic manipulation skills, deep reinforcement learning of general skills from autonomously collected experience, and meta-learning algorithms that can enable fast learning of new concepts and behaviors. Professor Finn received her Bachelors degree in Electrical Engineering and Computer Science at MIT and her PhD in Computer Science at UC Berkeley. Her research has been recognized through the ACM doctoral dissertation award, an NSF graduate fellowship, a Facebook fellowship, the C.V. Ramamoorthy Distinguished Research Award, and the MIT Technology Review 35 under 35 Award, and her work has been covered by various media outlets, including the New York Times, Wired, and Bloomberg. Throughout her career, she has sought to increase the representation of underrepresented minorities within CS and AI by developing an AI outreach camp at Berkeley for underprivileged high school students, a mentoring program for underrepresented undergraduates across three universities, and leading efforts within the WiML and Berkeley WiCSE communities of women researchers.
Website: https://ai.stanford.edu/~cbfinn
Academic Appointments
-
Assistant Professor, Computer Science
-
Assistant Professor, Electrical Engineering
-
Faculty Affiliate, Institute for Human-Centered Artificial Intelligence (HAI)
Honors & Awards
-
Research Fellowship, Alfred P. Sloan Foundation (2023)
-
Early Academic Career Award in Robotics and Automation, IEEE RAS (2022)
-
Young Investigator Award, Office of Naval Research (2021)
-
Microsoft Faculty Fellowship, Microsoft (2020)
-
ACM Doctoral Dissertation Award, ACM (2019)
-
35 Under 35 Innovator, MIT Technology Review (2018)
-
C.V. Ramamoorthy Distinguished Research Award, UC Berkeley (2017)
Program Affiliations
-
Symbolic Systems Program
2024-25 Courses
- Deep Reinforcement Learning
CS 224R (Spr) -
Independent Studies (17)
- Advanced Reading and Research
CS 499 (Aut, Win, Spr) - Advanced Reading and Research
CS 499P (Aut, Win, Spr) - Curricular Practical Training
CS 390A (Aut, Win, Spr) - Curricular Practical Training
CS 390B (Aut, Win, Spr) - Curricular Practical Training
CS 390C (Aut, Win, Spr) - Directed Studies in Applied Physics
APPPHYS 290 (Aut, Win, Spr) - Independent Project
CS 399 (Aut, Win, Spr) - Independent Project
CS 399P (Aut, Win, Spr) - Independent Study
SYMSYS 196 (Aut, Win, Spr) - Independent Work
CS 199 (Aut, Win, Spr) - Independent Work
CS 199P (Aut, Win, Spr) - Part-time Curricular Practical Training
CS 390D (Aut, Win, Spr) - Programming Service Project
CS 192 (Aut, Win, Spr) - Senior Project
CS 191 (Aut, Win, Spr) - Special Studies and Reports in Electrical Engineering
EE 391 (Aut, Win, Spr) - Supervised Undergraduate Research
CS 195 (Aut, Win, Spr) - Writing Intensive Senior Research Project
CS 191W (Aut, Win, Spr)
- Advanced Reading and Research
-
Prior Year Courses
2023-24 Courses
- Deep Multi-task and Meta Learning
CS 330 (Aut)
2022-23 Courses
- Deep Multi-task and Meta Learning
CS 330 (Aut) - Deep Reinforcement Learning
CS 224R (Spr)
2021-22 Courses
- Deep Multi-task and Meta Learning
CS 330 (Aut)
- Deep Multi-task and Meta Learning
Stanford Advisees
-
Doctoral Dissertation Reader (AC)
Anna Goldie, Effie Li, Michael Lingelbach, Garrett Thomas -
Postdoctoral Faculty Sponsor
Yuejiang Liu -
Master's Program Advisor
Christopher Chou, Vanessa Felix, Parker Kasiewicz, Alycia Lee, Olivia Lee, Denis Liu, Karthik Pythireddi, Stella Su, David Wendt, Zachary Witzel, Sophie Wu, Zhiyu Xie, Kaien Yang, Michael Yang, Yiwen Zhang -
Doctoral Dissertation Co-Advisor (AC)
Saurabh Kumar, Henrik Marklund -
Doctoral (Program)
Kaylee Burns, Annie Chen, Zipeng Fu, Tian Gao, Kyle Hsu, Sasha Khazatsky, Moo Kim, Yoonho Lee, Rafael Rafailov, Lucy Shi, Anikait Singh, Yonatan Urman, Jonathan Yang
All Publications
-
Bayesian Embeddings for Few-Shot Open World Recognition.
IEEE transactions on pattern analysis and machine intelligence
2024; 46 (3): 1513-1529
Abstract
As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from small amounts of information. This stands in stark contrast to modern machine learning systems that are typically designed with a known set of classes and a large number of examples for each class. In this work we extend embedding-based few-shot learning algorithms to the open-world recognition setting. We combine Bayesian non-parametric class priors with an embedding-based pre-training scheme to yield a highly flexible framework which we refer to as few-shot learning for open world recognition (FLOWR). We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets. Our results show, compared to prior methods, strong classification accuracy performance and up to a 12% improvement in H-measure (a measure of novel class detection) from our non-parametric open-world few-shot learning scheme.
View details for DOI 10.1109/TPAMI.2022.3201541
View details for PubMedID 36063507
-
A Fast and Accurate Machine Learning Autograder for the Breakout Assignment
ASSOC COMPUTING MACHINERY. 2024: 736-742
View details for DOI 10.1145/3626252.3630759
View details for Web of Science ID 001181240800108
-
Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models
ASSOC COMPUTING MACHINERY. 2023: 287-296
View details for DOI 10.1145/3600211.3604690
View details for Web of Science ID 001117838100023
-
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
View details for Web of Science ID 001220600001015
-
Neural Functional Transformers
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
View details for Web of Science ID 001227224000011
-
Permutation Equivariant Neural Functionals
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
View details for Web of Science ID 001227224007034
-
Train Offline, Test Online: A Real Robot Learning Benchmark
IEEE. 2023: 9197-9203
View details for DOI 10.1109/ICRA48891.2023.10160594
View details for Web of Science ID 001048371101123
-
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
IEEE COMPUTER SOC. 2023: 17907-17917
View details for DOI 10.1109/CVPR52729.2023.01717
View details for Web of Science ID 001062531302021
-
Disentanglement via Latent Quantization
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
View details for Web of Science ID 001220818801008
-
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
View details for Web of Science ID 001220818800032
-
Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning
RSS FOUNDATION-ROBOTICS SCIENCE & SYSTEMS FOUNDATION. 2022
View details for Web of Science ID 000827625700009
-
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022: 19645-19657
View details for Web of Science ID 000900130200031
-
Robust Policy Learning over Multiple Uncertainty Sets
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000900130205028
-
How to Leverage Unlabeled Data in Offline Reinforcement Learning
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000900130206039
-
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000900130207034
-
Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models
JOURNAL OF MACHINE LEARNING RESEARCH
2022; 23
View details for Web of Science ID 001003314000001
-
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
RSS FOUNDATION-ROBOTICS SCIENCE & SYSTEMS FOUNDATION. 2022
View details for Web of Science ID 000827625700063
-
Memory-Based Model Editing at Scale
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000900064905041
-
Improving Out-of-Distribution Robustness via Selective Augmentation
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000900130206027
-
Batch Exploration With Examples for Scalable Robotic Reinforcement Learning
IEEE ROBOTICS AND AUTOMATION LETTERS
2021; 6 (3): 4401–8
View details for DOI 10.1109/LRA.2021.3068655
View details for Web of Science ID 000639767800019
-
Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones
IEEE ROBOTICS AND AUTOMATION LETTERS
2021; 6 (3): 4915-4922
View details for DOI 10.1109/LRA.2021.3070252
View details for Web of Science ID 000642765100002
-
How to train your robot with deep reinforcement learning: lessons we have learned
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
2021; 40 (4-5): 698-721
View details for DOI 10.1177/0278364920987859
View details for Web of Science ID 000648404100003
-
WILDS: A Benchmark of in-the-Wild Distribution Shifts
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104605062
-
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
IEEE. 2021: 1274-1280
View details for DOI 10.1109/IROS51168.2021.9636628
View details for Web of Science ID 000755125501008
-
Offline Meta-Reinforcement Learning with Advantage Weighting
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000768182703084
-
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000768182701045
-
Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos
RSS FOUNDATION-ROBOTICS SCIENCE & SYSTEMS FOUNDATION. 2021
View details for Web of Science ID 000684604200012
-
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104606087
-
Just Train Twice: Improving Group Robustness without Training Group Information
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104606074
-
Catformer: Designing Stable Transformers via Sensitivity Analysis
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104602046
-
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104601047
-
Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
IEEE COMPUTER SOC. 2021: 2318-2328
View details for DOI 10.1109/CVPR46437.2021.00235
View details for Web of Science ID 000739917302051
-
Scalable Multi-Task Imitation Learning with Autonomous Improvement
IEEE. 2020: 2167-2173
View details for Web of Science ID 000712319501084
-
OmniTact: A Multi-Directional High-Resolution Touch Sensor
IEEE. 2020: 618-624
View details for Web of Science ID 000712319500072
-
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866903039
-
Unsupervised Curricula for Visual Meta-Reinforcement Learning
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866902018
-
Unsupervised Visuomotor Control through Distributional Planning Networks
MIT PRESS. 2019
View details for Web of Science ID 000570976800020
-
One-Shot Composition of Vision-Based Skills from Demonstration
IEEE. 2019: 2643–50
View details for Web of Science ID 000544658402035