Chelsea Finn

59

Papers

1,371

Total Citations

Papers (59)

Unsupervised Learning for Physical Interaction through Video Prediction

NeurIPS 2016arXiv

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

NeurIPS 2025arXiv

Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling

SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Learning to Explore in POMDPs with Informational Rewards

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction

NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis

Learning Predictive Models from Observation and Interaction

RLVF: Learning from Verbal Feedback without Overgeneralization

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning

PIGEON: Predicting Image Geolocations

Meta-learning with an Adaptive Task Scheduler

Information is Power: Intrinsic Control via Information Capture

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

Noether Networks: meta-learning useful conserved quantities

Autonomous Reinforcement Learning via Subgoal Curricula

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

Efficiently Identifying Task Groupings for Multi-Task Learning

COMBO: Conservative Offline Model-Based Policy Optimization

C-Mixup: Improving Generalization in Regression

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

You Only Live Once: Single-Life Reinforcement Learning

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

Learning Options via Compression

Giving Feedback on Interactive Student Programs with Meta-Exploration

LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning

MEMO: Test Time Robustness via Adaptation and Augmentation

Permutation Equivariant Neural Functionals

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Disentanglement via Latent Quantization

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Neural Functional Transformers

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control

Online Meta-Learning

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

Probabilistic Model-Agnostic Meta-Learning

Meta-Learning with Implicit Gradients

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Guided Meta-Policy Search

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Weakly-Supervised Reinforcement Learning for Controllable Behavior

Continual Learning of Control Primitives : Skill Discovery via Reset-Games

Gradient Surgery for Multi-Task Learning

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

MOPO: Model-based Offline Policy Optimization

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Continuous Meta-Learning without Tasks

Visual Adversarial Imitation Learning using Variational Models