Stanford AI Lab Showcases Broad Research Portfolio at Virtual NeurIPS 2021
The Stanford AI Lab presents a diverse collection of papers and workshops at the virtual NeurIPS 2021 conference. The research covers critical topics including generative models, sequence modeling, and emergent communication.
The thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) 2021 takes place virtually from December 6th to 14th, featuring a strong presence from the Stanford AI Lab (SAIL). Researchers from SAIL present numerous projects across the main conference, the Datasets and Benchmarks track, and various specialized workshops. Attendees have the opportunity to explore links to papers, videos, and supplementary blogs for all of these contributions.
The presented research highlights several major advancements in deep learning and artificial intelligence. Notable projects include work on improving the compositionality of neural networks, combining recurrent and continuous-time models through linear state space layers, and developing compositional transformers for scene generation. Additional studies explore emergent communication of generalizations and innovative techniques for deep learning on a data diet through early example pruning.
Beyond presenting research papers, members of the SAIL community actively participate as co-organizers for several exciting workshops scheduled for December 13th and 14th. The lab encourages interested individuals to reach out directly to contact authors and workshop organizers to learn more about the cutting-edge work happening at Stanford.