Picture for Osbert Bastani

Osbert Bastani

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity

Jun 05, 2024
Viaarxiv icon

DrEureka: Language Model Guided Sim-To-Real Transfer

Add code
Jun 04, 2024
Viaarxiv icon

One-Shot Safety Alignment for Large Language Models via Optimal Dualization

Add code
May 29, 2024
Viaarxiv icon

Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction

May 24, 2024
Viaarxiv icon

Stochastic Online Conformal Prediction with Semi-Bandit Feedback

Add code
May 22, 2024
Viaarxiv icon

Stochastic Bandits with ReLU Neural Networks

Add code
May 12, 2024
Viaarxiv icon

Uncertainty in Language Models: Assessment through Rank-Calibration

Apr 04, 2024
Viaarxiv icon

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Add code
Mar 19, 2024
Figure 1 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 2 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 3 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 4 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Viaarxiv icon

Generative Adversarial Bayesian Optimization for Surrogate Objectives

Add code
Feb 09, 2024
Viaarxiv icon

Eureka: Human-Level Reward Design via Coding Large Language Models

Add code
Oct 19, 2023
Viaarxiv icon