Chelsea Finn

Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval ICLR 2025 CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models CVPR 2025 Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success RSS 2025 FAST: Efficient Action Tokenization for Vision-Language-Action Models RSS 2025 PERSONA: A Reproducible Testbed for Pluralistic Alignment COLING 2025 Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling ICLR 2025 Range, not Independence, Drives Modularity in Biologically Inspired Representations ICLR 2025 $\pi_0.5$: a Vision-Language-Action Model with Open-World Generalization CORL 2025 Learning Long-Context Diffusion Policies via Past-Token Prediction CORL 2025 Curating Demonstrations using Online Experience RSS 2025 π₀: A Vision-Language-Action Flow Model for General Robot Control RSS 2025 RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies CORL 2025 Latent Diffusion Planning for Imitation Learning ICML 2025 Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models ICML 2025 Calibrating Language Models with Adaptive Temperature Scaling EMNLP 2024 Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks CORL 2024 ALOHA Unleashed: A Simple Recipe for Robot Dexterity CORL 2024 OpenVLA: An Open-Source Vision-Language-Action Model CORL 2024 HumanPlus: Humanoid Shadowing and Imitation from Humans CORL 2024 Robotic Control via Embodied Chain-of-Thought Reasoning CORL 2024 Evaluating Real-World Robot Manipulation Policies in Simulation CORL 2024 Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning ICML 2024 PIGEON: Predicting Image Geolocations CVPR 2024 Disentangling Length from Quality in Direct Preference Optimization ACL 2024 Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation RSS 2024 DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset RSS 2024 Analyzing and Mitigating Object Hallucination in Large Vision-Language Models ICLR 2024 An Emulator for Fine-tuning Large Language Models using Small Language Models ICLR 2024 Language Model Detectors Are Easily Optimized Against ICLR 2024 A Critical Evaluation of AI Feedback for Aligning Large Language Models NIPS 2024 Universal Neural Functionals NIPS 2024 Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms NIPS 2024 Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models ICLR 2024 Learning to Explore in POMDPs with Informational Rewards ICML 2024 Efficient imitation learning with conservative world models L4DC 2024 Fine-Tuning Language Models for Factuality ICLR 2024 PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs ICML 2024 Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ICML 2024 RLVF: Learning from Verbal Feedback without Overgeneralization ICML 2024 Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning ICLR 2024 RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches ICLR 2024 Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features ICLR 2024 What Makes Pre-Trained Visual Representations Successful for Robust Manipulation? CORL 2024 Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation CORL 2024 Improving Domain Generalization with Domain Relations ICLR 2024 Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning ICLR 2024 Octo: An Open-Source Generalist Robot Policy RSS 2024 Yell At Your Robot: Improving On-the-Fly from Language Corrections RSS 2024 Efficient Data Collection for Robotic Manipulation via Compositional Generalization RSS 2024 Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs CORL 2024 Open-World Object Manipulation using Pre-Trained Vision-Language Models CORL 2023 Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts ICLR 2023 A Control-Centric Benchmark for Video Prediction ICLR 2023 Surgical Fine-Tuning Improves Adaptation to Distribution Shifts ICLR 2023 Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement ICLR 2023 Language-Driven Representation Learning for Robotics RSS 2023 Permutation Equivariant Neural Functionals NIPS 2023 Supervised Pretraining Can Learn In-Context Reinforcement Learning NIPS 2023 Disentanglement via Latent Quantization NIPS 2023 Direct Preference Optimization: Your Language Model is Secretly a Reward Model NIPS 2023 RoboCLIP: One Demonstration is Enough to Learn Robot Policies NIPS 2023 Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning NIPS 2023 Neural Functional Transformers NIPS 2023 Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets RSS 2023 Contrastive Example-Based Control L4DC 2023 RT-1: Robotics Transformer for Real-World Control at Scale RSS 2023 Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials RSS 2023 Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware RSS 2023 Robot Parkour Learning CORL 2023 BridgeData V2: A Dataset for Robot Learning at Scale CORL 2023 RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control CORL 2023 Waypoint-Based Imitation Learning for Robotic Manipulation CORL 2023 Polybot: Training One Policy Across Robots While Embracing Variability CORL 2023 Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning CORL 2023 MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning CORL 2023 Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions CORL 2023 NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis CVPR 2023 Meta-Learning Online Adaptation of Language Models EMNLP 2023 Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback EMNLP 2023 DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature ICML 2023 Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning ICML 2023 Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning RSS 2022 Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets RSS 2022 MEMO: Test Time Robustness via Adaptation and Augmentation NIPS 2022 LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning NIPS 2022 Giving Feedback on Interactive Student Programs with Meta-Exploration NIPS 2022 Vision-Based Manipulators Need to Also See from Their Hands ICLR 2022 Learning Options via Compression NIPS 2022 When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning NIPS 2022 You Only Live Once: Single-Life Reinforcement Learning NIPS 2022 Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference EMNLP 2022 Extending the WILDS Benchmark for Unsupervised Adaptation ICLR 2022 Do deep networks transfer invariances across classes? ICLR 2022 Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time NIPS 2022 Autonomous Reinforcement Learning: Formalism and Benchmarking ICLR 2022 Fast Model Editing at Scale ICLR 2022 Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations ICML 2022 How to Leverage Unlabeled Data in Offline Reinforcement Learning ICML 2022 Improving Out-of-Distribution Robustness via Selective Augmentation ICML 2022 Robust Policy Learning over Multiple Uncertainty Sets ICML 2022 A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning ICML 2022 Memory-Based Model Editing at Scale ICML 2022 C-Mixup: Improving Generalization in Regression NIPS 2022 Meta-Learning with Fewer Tasks through Task Interpolation ICLR 2022 CoMPS: Continual Meta Policy Search ICLR 2022 Offline Reinforcement Learning at Multiple Frequencies CORL 2022 R3M: A Universal Visual Representation for Robot Manipulation CORL 2022 Do As I Can, Not As I Say: Grounding Language in Robotic Affordances CORL 2022 Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models JMLR 2022 Offline Reinforcement Learning from Images with Latent Space Models L4DC 2021 Visual Adversarial Imitation Learning using Variational Models NIPS 2021 Meta-learning with an Adaptive Task Scheduler NIPS 2021 Information is Power: Intrinsic Control via Information Capture NIPS 2021 Conservative Data Sharing for Multi-Task Offline Reinforcement Learning NIPS 2021 Noether Networks: meta-learning useful conserved quantities NIPS 2021 Autonomous Reinforcement Learning via Subgoal Curricula NIPS 2021 Differentiable Annealed Importance Sampling and the Perils of Gradient Noise NIPS 2021 Adaptive Risk Minimization: Learning to Adapt to Domain Shift NIPS 2021 Efficiently Identifying Task Groupings for Multi-Task Learning NIPS 2021 COMBO: Conservative Offline Model-Based Policy Optimization NIPS 2021 Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks CORL 2021 A Workflow for Offline Model-Free Robotic Reinforcement Learning CORL 2021 Scaling Up Multi-Task Robotic Reinforcement Learning CORL 2021 BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning CORL 2021 Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation CORL 2021 Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction CVPR 2021 Meta-learning Symmetries by Reparameterization ICLR 2021 SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments ICLR 2021 Model-Based Visual Planning with Self-Supervised Functional Distances ICLR 2021 Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills ICML 2021 Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021 WILDS: A Benchmark of in-the-Wild Distribution Shifts ICML 2021 Just Train Twice: Improving Group Robustness without Training Group Information ICML 2021 Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices ICML 2021 Offline Meta-Reinforcement Learning with Advantage Weighting ICML 2021 Deep Reinforcement Learning amidst Continual Structured Non-Stationarity ICML 2021 Learning Generalizable Robotic Reward Functions from “In-The-Wild” Human Videos RSS 2021 Model Based Reinforcement Learning for Atari ICLR 2020 On the Expressivity of Neural Networks for Deep Reinforcement Learning ICML 2020 Goal-Aware Prediction: Learning to Model What Matters ICML 2020 Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings ICML 2020 Continual Learning of Control Primitives : Skill Discovery via Reset-Games NIPS 2020 Weakly-Supervised Reinforcement Learning for Controllable Behavior NIPS 2020 Learning Predictive Models from Observation and Interaction ECCV 2020 Learning to Interactively Learn and Assist AAAI 2020 Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning CORL 2020 MELD: Meta-Reinforcement Learning from Images via Latent State Models CORL 2020 Learning Latent Representations to Influence Multi-Agent Interaction CORL 2020 Reinforcement Learning with Videos: Combining Offline Observations with Interaction CORL 2020 Continuous Meta-Learning without Tasks NIPS 2020 Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors NIPS 2020 MOPO: Model-based Offline Policy Optimization NIPS 2020 One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL NIPS 2020 Gradient Surgery for Multi-Task Learning NIPS 2020 Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation ICLR 2020 Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards ICLR 2020 VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation ICLR 2020 Meta-Learning without Memorization ICLR 2020 Unsupervised Learning via Meta-Learning ICLR 2019 Reasoning About Physical Interactions with Object-Oriented Prediction and Planning ICLR 2019 Unsupervised Curricula for Visual Meta-Reinforcement Learning NIPS 2019 Guided Meta-Policy Search NIPS 2019 Meta-Inverse Reinforcement Learning with Probabilistic Context Variables NIPS 2019 Language as an Abstraction for Hierarchical Deep Reinforcement Learning NIPS 2019 Meta-Learning with Implicit Gradients NIPS 2019 Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables ICML 2019 Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning ICLR 2019 Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL ICLR 2019 Online Meta-Learning ICML 2019 Entity Abstraction in Visual Model-Based Reinforcement Learning CORL 2019 Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning CORL 2019 RoboNet: Large-Scale Multi-Robot Learning CORL 2019 Learning a Prior over Intent via Meta-Inverse Reinforcement Learning ICML 2019 Improvisation through Physical Understanding: Using Novel Objects As Tools with Visual Foresight RSS 2019 Unsupervised Visuomotor Control through Distributional Planning Networks RSS 2019 End-To-End Robotic Reinforcement Learning without Reward Engineering RSS 2019 Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm ICLR 2018 Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning CORL 2018 Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control ICML 2018 One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning RSS 2018 Stochastic Variational Video Prediction ICLR 2018 Probabilistic Model-Agnostic Meta-Learning NIPS 2018 Recasting Gradient-Based Meta-Learning as Hierarchical Bayes ICLR 2018 Few-Shot Goal Inference for Visuomotor Learning and Planning CORL 2018 One-Shot Visual Imitation Learning via Meta-Learning CORL 2017 Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks ICML 2017 Self-Supervised Visual Planning with Temporal Skip Connections CORL 2017 End-to-End Training of Deep Visuomotor Policies JMLR 2016 Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization ICML 2016 Unsupervised Learning for Physical Interaction through Video Prediction NIPS 2016