Plain-language Observatory summaries connected to authors, institutions, technologies and the original scholarly record.
The Observatory publishes a short educational summary and significance note, never the paper body. Read the linked original for methods, results, limitations and citations.
Image: RT-2 project authors / Google DeepMind01vision-language-action modelsAnthony Brohan, Noah Brown, Justice Carbajal, et al.
The paper describes vision-language-action models that represent robot actions alongside visual and language inputs.
Image: Diffusion Policy project authors — Cheng Chi, Zhenjia Xu, Siyuan Feng, Eric Cousineau, Yilun Du, Benjamin Burchfiel, Russ Tedrake, and Shuran Song02imitation learningCheng Chi, Zhenjia Xu, Siyuan Feng, et al.
The work applies diffusion models to generate robot action sequences from observations.