Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
Reinforcement learning (RL) with dense rewards and imitation learning (IL) with human-generated trajectories are the most widely used approaches for training modern embodied agents. RL requires…
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images…
RCT Rejection Sampling for Causal Estimation Evaluation
Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the…
CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchies
Various NLP tasks require a complex hierarchical structure over nodes, where each node is a cluster of items. Examples include generating entailment graphs, hierarchical cross-document coreference…
CARE: Extracting Experimental Findings From Clinical Literature
Extracting fine-grained experimental findings from literature can provide massive utility for scientific applications. Prior work has focused on developing annotation schemas and datasets for…
LongBoX: Evaluating Transformers on Long-Sequence Clinical Tasks
Many large language models (LLMs) for medicine have largely been evaluated on short texts, and their ability to handle longer sequences such as a complete electronic health record (EHR) has not been…
The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to prompt and more capable in complex settings. RLHF at its core is…
Papeos: Augmenting Research Papers with Talk Videos
Research consumption has been traditionally limited to the reading of academic papers—a static, dense, and formally written format. Alternatively, pre-recorded conference presentation videos, which…
Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
Efficiently reviewing scholarly literature and synthesizing prior art are crucial for scientific progress. Yet, the growing scale of publications and the burden of knowledge make synthesis of…
Entangled Preferences: The History and Risks of Reinforcement Learning and Human Feedback
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the…