Collaborating with language models for embodied reasoning (2023 · 36 citations)
Large language models reason well and adapt to new tasks through in-context learning, but they cannot perceive or act in an environment.
Distilling Internet-Scale Vision-Language Models into Embodied Agents (2023 · 9 citations)
Language-conditioned embodied agents must link words to what they perceive and do. The paired trajectory–language data needed for this is costly to collect, often ambiguous, and tied to one agent's design. The authors propose using a pretrained generative vision-language model as an automatic annotator.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Unsupervised Predictive Memory in a Goal-Directed Agent ↗arXiv (Cornell University) · no summary yetGreg Wayne et al.2018 · 140 citations
Collaborating with language models for embodied reasoningarXiv:2302.00763Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, et al.2023 · 36 citations
Distilling Internet-Scale Vision-Language Models into Embodied AgentsarXiv:2301.12507Theodore Sumers, Kenneth Marino, Arun Ahuja, et al.2023 · 9 citations

Co-authors here

4 co-authors with a page, the most papers together first.

Papers of our library cite their works 3,557 times (of the 149,439 papers whose bibliographies we read); 898 citing papers with a page here →.

Updated 3 November 2026