Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
Comments 22 pages, 9 figures
作者
Chelsea Finn
Robotics / Machine Learning
Neural Functional Transformers
Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets
A Control-Centric Benchmark for Video Prediction
Comments ICLR 2023
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning
Language-Driven Representation Learning for Robotics
Comments 30 Pages, 15 Figures
Diversify and Disambiguate: Learning From Underspecified Data
Comments ICLR 2023. Code is available at https://github.com/yoonholee/DivDis
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
Comments Accepted by NeurIPS 2022 Track on Datasets and Benchmarks; v2: fixed some issues in FMoW and change the name from "FMoW" to "FMoW-Time"
Learning Options via Compression
Comments Published at NeurIPS 2022
Learning to Reason With Relational Abstractions
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
Comments 16 pages. EMNLP 2022 Camera Ready. See https://ericmitchell.ai/emnlp-2022-concord/ for code and data
R3M: A Universal Visual Representation for Robot Manipulation
Comments Conference on Robot Learning (CoRL) 2022
Giving Feedback on Interactive Student Programs with Meta-Exploration
Comments Advances in Neural Information Processing Systems (NeurIPS 2022). Selected as Oral
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
You Only Live Once: Single-Life Reinforcement Learning
Comments 17 pages
Journal ref Neural Information Processing Systems (NeurIPS) 2022
C-Mixup: Improving Generalization in Regression
Comments Accepted by NeurIPS 2022
Knowledge-Driven New Drug Recommendation
MEMO: Test Time Robustness via Adaptation and Augmentation
Comments NeurIPS '22 camera ready. Code: https://github.com/zhangmarvin/memo
Bayesian Embeddings for Few-Shot Open World Recognition
Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks
Comments Equal advising and contribution for last two authors
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
Comments See website at https://say-can.github.io/ V1. Initial Upload. V2. Added PaLM results. Added study about new capabilities (drawer manipulation, chain of thought prompting, multilingual instructions). Added an ablation study of language model size. Added an open-source version of \algname on a simulated tabletop environment. Improved readability
Autonomous Reinforcement Learning: Formalism and Benchmarking
Offline Reinforcement Learning at Multiple Frequencies
Comments Project website: https://sites.google.com/stanford.edu/adaptive-nstep-returns/
On the Opportunities and Risks of Foundation Models
Comments Authored by the Center for Research on Foundation Models (CRFM) at the Stanford Institute for Human-Centered Artificial Intelligence (HAI). Report page with citation guidelines: https://crfm.stanford.edu/report.html
How to Leverage Unlabeled Data in Offline Reinforcement Learning
Comments ICML 2022
Visual Adversarial Imitation Learning using Variational Models
Improving Out-of-Distribution Robustness via Selective Augmentation
Comments Accepted by ICML 2022
Memory-Based Model Editing at Scale
Comments ICML 2022. Project site at https://sites.google.com/view/serac-editing
