Osbert Bastani

Conformal Constrained Policy Optimization for Cost-Effective LLM Agents AAAI 2026 Conformal Structured Prediction ICLR 2025 Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity ICLR 2025 Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization ICML 2025 Stochastic Online Conformal Prediction with Semi-Bandit Feedback ICML 2025 Vision Language Models are In-Context Value Learners ICLR 2025 Generative Adversarial Model-Based Optimization via Source Critic Regularization NIPS 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NIPS 2024 TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction NAACL 2024 Uncertainty in Language Models: Assessment through Rank-Calibration EMNLP 2024 DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset RSS 2024 Environment Curriculum Generation via Large Language Models CORL 2024 Stochastic Bandits with ReLU Neural Networks ICML 2024 DrEureka: Language Model Guided Sim-To-Real Transfer RSS 2024 Eureka: Human-Level Reward Design via Coding Large Language Models ICLR 2024 PAC Prediction Sets Under Label Shift ICLR 2024 Learning Performance-Improving Code Edits ICLR 2024 Angelic Patches for Improving Third-Party Object Detector Performance CVPR 2023 Robust Subtask Learning for Compositional Generalization ICML 2023 VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training ICLR 2023 LIV: Language-Image Representations and Rewards for Robotic Control ICML 2023 PAC Prediction Sets for Large Language Models of Code ICML 2023 Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching L4DC 2023 Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism INTERSPEECH 2023 Uniformly Conservative Exploration in Reinforcement Learning AISTATS 2023 Practical Adversarial Multivalid Conformal Prediction NIPS 2022 Sequential Covariate Shift Detection Using Classifier Two-Sample Tests ICML 2022 Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching ICML 2022 Regret Bounds for Risk-Sensitive Reinforcement Learning NIPS 2022 Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints NIPS 2022 PAC Prediction Sets for Meta-Learning NIPS 2022 Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates CORL 2022 Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning AAAI 2022 Counterfactual Explanations for Natural Language Interfaces ACL 2022 Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression NIPS 2022 PAC Prediction Sets Under Covariate Shift ICLR 2022 Understanding Robust Generalization in Learning Regular Languages ICML 2022 Abstract Value Iteration for Hierarchical Reinforcement Learning AISTATS 2021 Compositional Reinforcement Learning from Logical Specifications NIPS 2021 Learning Models for Actionable Recourse NIPS 2021 Conservative Offline Distributional Reinforcement Learning NIPS 2021 Program Synthesis Guided Reinforcement Learning for Partially Observed Environments NIPS 2021 Algorithms for Fairness in Sequential Decision Making AISTATS 2021 Few-Shot Novel Concept Learning for Semantic Parsing EMNLP 2021 Likelihood-Based Diverse Sampling for Trajectory Forecasting ICCV 2021 PAC Confidence Predictions for Deep Neural Network Classifiers ICLR 2021 Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings ICML 2021 Safe Reinforcement Learning via Statistical Model Predictive Shielding RSS 2021 Robust and Stable Black Box Explanations ICML 2020 Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems AISTATS 2020 Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation AISTATS 2020 Neurosymbolic Transformers for Multi-Agent Communication NIPS 2020 Generating Programmatic Referring Expressions via Program Synthesis ICML 2020 PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction ICLR 2020 Synthesizing Programmatic Policies that Inductively Generalize ICLR 2020 Learning Neurosymbolic Generative Models via Program Synthesis ICML 2019 A Composable Specification Language for Reinforcement Learning Tasks NIPS 2019 Verifiable Reinforcement Learning via Policy Extraction NIPS 2018 Measuring Neural Net Robustness with Constraints NIPS 2016