Dorsa Sadigh

papers

2,368

total citations

papers (16)

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

ICLR 2025arXiv

750

citations

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

CVPR 2024arXiv

578

citations

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

ICML 2024arXiv

258

citations

Dorsa Sadigh

papers (16)

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Parallel Sampling of Diffusion Models

Data Quality in Imitation Learning

Inverse Preference Learning: Preference-based RL without a Reward Function

Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality

ELLA: Exploration through Learned Language Abstraction

Training and Inference on Any-Order Autoregressive Models the Right Way

Vision Language Models are In-Context Value Learners

Diverse Conventions for Human-AI Collaboration

HyperSPNs: Compact and Expressive Probabilistic Circuits

What's the Move? Hybrid Imitation Learning via Salient Points

Assistive Teaching of Motor Control Tasks to Humans

papers (16)

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Parallel Sampling of Diffusion Models

Data Quality in Imitation Learning

Inverse Preference Learning: Preference-based RL without a Reward Function

Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality

ELLA: Exploration through Learned Language Abstraction

Training and Inference on Any-Order Autoregressive Models the Right Way

Vision Language Models are In-Context Value Learners

Diverse Conventions for Human-AI Collaboration

HyperSPNs: Compact and Expressive Probabilistic Circuits

What's the Move? Hybrid Imitation Learning via Salient Points

Assistive Teaching of Motor Control Tasks to Humans