昨日,ICLR 2023 获奖论文公布!来自北京大学的张博航、罗胜杰、王立威、贺笛获得杰出论文奖,清华大学孔祥哲、中国人民大学高瓴人工智能学院黄文炳、清华大学刘洋获得杰出论文奖提名。
论文 1:Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching 作者:Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong 机构:KAIST、微软亚研 论文链接:https://openreview.net/pdf?id=88nT0j5jAn
论文 2:Rethinking the Expressive Power of GNNs via Graph Biconnectivity 作者:张博航, 罗胜杰, 王立威, 贺笛 机构:北京大学 论文链接:https://openreview.net/pdf?id=r9hNv76KoT3
论文 3:DreamFusion: Text-to-3D using 2D Diffusion 作者:Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall 机构:谷歌研究院、加州大学伯克利分校 论文链接:https://openreview.net/pdf?id=FjNys5c7VyY
论文 4:Emergence of Maps in the Memories of Blind Navigation Agents 作者:Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra 机构:佐治亚理工学院、Meta AI 等 论文链接:https://openreview.net/pdf?id=lTt4KjHSsyl
论文 1:Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning 作者:Zeyuan Allen-Zhu, Yuanzhi Li 机构:Meta、MBZUAI 论文链接:https://openreview.net/pdf?id=Uuf2q9TfXGA
论文 2:Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning 作者:Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown 机构:Meta AI、MIT 论文链接:https://openreview.net/pdf?id=F61FwJTZhb
论文 3:On the duality between contrastive and non-contrastive self-supervised learning 作者:Quentin Garrido, Yubei Chen, Adrien Bardes, Laurent Najman, Yann LeCun 机构:Meta AI 等 论文链接:https://openreview.net/pdf?id=kDEL91Dufpa
论文 4:Conditional Antibody Design as 3D Equivariant Graph Translation 作者:孔祥哲,黄文炳,刘洋 机构:清华大学计算机系,清华大学智能产业研究院,中国人民大学高瓴人工智能学院,北京智源人工智能研究院 论文链接:https://openreview.net/pdf?id=LFHFQbjxIiP
论文 5:Disentanglement with Biological Constraints: A Theory of Functional Cell Types 作者:James C. R. Whittington, Will Dorrell, Surya Ganguli, Timothy Behrens 机构:斯坦福大学、牛津大学、UCL 论文链接:https://openreview.net/pdf?id=9Z_GfhZnGH