The International Conference on Learning Representations (ICLR), the premier gathering of professionals dedicated to the advancement of the many branches of artificial intelligence (AI) and deep learning—announced 4 award-winning papers, and 5 honorable mention paper winners. As the first in-person gathering since the pandemic, ICLR 2023 is happening this week as a five-day hybrid conference from 1-5 May in Kigali, Africa, live-streamed in CAT timezone.
Several reviewers, senior area chairs and area chairs reviewed 4,938 submissions and accepted 1,574 papers which is a 44% increase from 2022 .
The four Outstanding Paper Awards go to:
- Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching by Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong
- Rethinking the Expressive Power of GNNs via Graph Biconnectivity by Bohang Zhang, Shengjie Luo, Liwei Wang, Di He
- DreamFusion: Text-to-3D using 2D Diffusion by Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall
- Emergence of Maps in the Memories of Blind Navigation Agents by Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra
The five Honorable Mention Paper Awards go to:
- Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning by Zeyuan Allen-Zhu, Yuanzhi Li
- Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning by Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown
- On the duality between contrastive and non-contrastive self-supervised learning by Quentin Garrido, Yubei Chen, Adrien Bardes, Laurent Najman, Yann LeCun
- Conditional Antibody Design as 3D Equivariant Graph Translation by Xiangzhe Kong, Wenbing Huang, Yang Liu
- Disentanglement with Biological Constraints: A Theory of Functional Cell Types by James C. R. Whittington, Will Dorrell, Surya Ganguli, Timothy Behrens
“ICLR 2023 is the first major AI conference to be held in Africa and the first in-person ICLR conference since the pandemic. Besides showcasing the community’s latest research progress in deep learning and artificial intelligence, we have actively engaged with local and regional AI communities for education and outreach”, Said Yan Liu, ICLR 2023 general chair, “we have initiated a series of special events, such as Kaggle@ICLR 2023, which collaborates with Zindi on machine learning competitions to address societal challenges in Africa, and Indaba X Rwanda, featuring talks, panels and posters by AI researchers in Rwanda and other African countries. I am excited that ICLR not only serves as the signature conference of deep learning and AI in the research community, but also leads to efforts in improving scientific inclusiveness and addressing societal challenges in Africa via AI. ”
Global participants at ICLR span a wide range of backgrounds, from academic and industrial researchers to entrepreneurs and engineers, to graduate students and postdoctorates. ICLR continues to pursue inclusivity and efforts to reach a broader audience, employing activities such as mentoring programs and hosting social meetups on a global scale. Attendees explore global, cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Sign up for the free insideBIGDATA newsletter.
Join us on Twitter: https://twitter.com/InsideBigData1
Join us on LinkedIn: https://www.linkedin.com/company/insidebigdata/
Join us on Facebook: https://www.facebook.com/insideBIGDATANOW