2021 NeurIPS에서 서울대학교 논문이 18편 채택되어 역대 최고 기록을 경신하였다. 공과대학에서는 기계공학부 박종우 교수팀, 컴퓨터공학부 김건희 교수팀, 송현오 교수팀, 전병곤 교수팀, 장병탁 교수팀에서 각 1편, 전기정보공학부 문태섭 교수팀, 윤성로 교수팀, 한보형 교수팀에서 총 4편, 산업공학과 이재욱 교수팀의 2편이 채택되었다. 자연과학대학에서는 수리과학부 류경석 교수팀, 통계학과 조명희 교수팀이, 융합과학기술대학원 지능정보학과에서는 이교구 교수팀과 전동석 교수팀에서 각 1편을 발표한다. 또한 컴퓨터공학부 이경재 학생등 서울대 대학원생과 기업이 협업한 논문 3편이 채택되어 주목을 받았다. 

2021 NeurIPS 채택 논문 

• Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods (Seohong Park, Jaekyeom Kim and Gunhee Kim) #김건희 교수팀
• A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast (J. Lee, C. Park, E. K. Ryu) #류경석 교수팀
• SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning (Sungmin Cha, Beomyoung Kim, Youngjoon Yoo, and Taesup Moon) #문태섭 교수팀
• Neighborhood Reconstructing Autoencoders (Yonghyeon Lee, Hyeokjun Kwon, Frank Park) #박종우 교수팀
• Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble (Gaon An, Seungyong Moon, Jang-Hyun Kim, Hyun Oh Song) #송현오 교수팀
• Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation (Jungbeom Lee, Jooyoung Choi, Jisoo Mok, Sungroh Yoon) #윤성로 교수팀
• Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations (Hyeong-Seok Choi, Juheon Lee, Wansoo Kim, Jie Hwan Lee, Hoon Heo, Kyogu Lee) #이교구 교수팀
• Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples (Sungyoon Lee, Woojin Lee, Jinseong Park, Jaewook Lee) #이재욱 교수팀
• Parameter-free HE-friendly Logistic Regression (Junyoung Byun, Woojin Lee,  Jaewook Lee) #이재욱 교수팀
• Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning (Kibeom Kim, Min Whoo Lee, Yoonsung Kim, JeHwan Ryu, Minsu Lee, Byoung-Tak Zhang) #장병탁 교수팀
• Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection (S. Woo, J. Park, J. Hong, and D. Jeon) #전동석 교수팀
• Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Parograms (Taebum Kim, Eunji Jeong, Geon-Woo Kim, Yunmo Koo, Sehoon Kim, Gyeong-In Yu, Byung-Gon Chun) #전병곤 교수팀 
• Doubly Robust Thompson Sampling with Linear Payoffs (Wonyoung Kim, Gi-Soo Kim, Myunghee Cho Paik) #조명희 교수팀
• Learning Student-Friendly Teacher Networks for Knowledge Distillation (Dae Young Park, Moon-Hyun Cha, Changwook Jeong, Daesin Kim, and Bohyung Han) #한보형 교수팀
• Learning Debiased and Disentangled Representations for Semantic Segmentation (Sanghyeok Chu, Dongwan Kim, and Bohyung Han) #한보형 교수팀
• SWAD: Domain Generalization by Seeking Flat Minima (Junbum Cha (Kakao Brain) · Sanghyuk Chun (NAVER AI Lab) · Kyungjae Lee (서울대학교) · Han-Cheol Cho (Intel Korea) · Seunghyun Park (Clova AI Research, Naver Corp.) · Yunsung Lee (Korea University) · Sungrae Park (UPSTAGE))
• Neural Bootstrapper (Minsuk Shin (University of South Carolina) · Hyungjoo Cho (서울대학교) · Hyun-seok Min (Tomocube) · Sungbin Lim (UNIST))
• MERLOT: Multimodal Neural Script Knowledge Models (Rowan Zellers (University of Washington) · Ximing Lu (Department of Computer Science, University of Washington) · Jack Hessel (Cornell University) · Youngjae Yu (서울대학교) · Jae Sung Park (University of Washington) · Jize Cao (Department of Computer Science, University of Washington) · Ali Farhadi (University of Washington, Allen Institute for Artificial Intelligence) · Yejin Choi (University of Washington))