The Neural Information Processing Systems annual conference (NeurIPS 2021) was held from December 6 to 14, 2021. It is a multi-track interdisciplinary annual meeting on machine learning, computational neuroscience, and other areas that includes invited talks, demonstrations, symposia, and oral and poster presentations of refereed papers. Along with the conference is a professional exposition focusing on machine learning in practice, a series of tutorials, and topical workshops that provide a less formal setting for the exchange of ideas.
There were various Adobe contributions to the conference, including thirteen main conference papers, nine workshop papers, one workshop invited talk, and one area chair. Nearly all of Adobe’s papers are the result of student internships or other collaborations with university students and faculty. Check out the Adobe Research Careers website to learn more about internships and full-time career opportunities.
Main Conference Adobe Co-authored Papers
A Multi-Implicit Neural Representation for Fonts Pradyumna Reddy, Zhifei Zhang, Zhaowen Wang, Matthew Fisher, Niloy J. Mitra, Hailin Jin Automatic Unsupervised Outlier Model Selection Yue Zhao, Ryan Rossi, Leman Akoglu Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, Sanjeev Arora Coresets for Classification – Simplified and Strengthened Tung Mai, Cameron Musco, Anup Rao Does Preprocessing Help Training Over-parameterized Neural Networks? Zhao Song, Shuo Yang, Ruizhe Zhang Evaluating Gradient Inversion Attacks and Defenses in Federated Learning Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, Sanjeev Arora Look at What I’m Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos Reuben Tan, Bryan Plummer, Kate Saenko, Hailin Jin, Bryan Russell MarioNette: Self-Supervised Sprite Learning Dmitriy Smirnov, Michael Gharbi, Matthew Fisher, Vitor Guizilini, Alexei Efros, Justin M. Solomon Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs paper Scatterbrain: Unifying Sparse and Low-rank Attention Approximation Beidi Chen, Tri Dao, Eric Winsor, Zhao Song, Atri Rudra, Christopher SketchGen: Generating Constrained CAD Sketches Wamiq Para, Shariq Bhat, Paul Guerrero, Tom Kelly, Niloy Mitra, Leonidas J. Guibas, Peter Wonka Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation Can Qin, Handong Zhao, Lichen Wang, Huan Wang, Yulun Zhang, Yun Fu UniDoc: Unified Pretraining Framework for Document Understanding Jiuxiang Gu, Jason Kuen, Vlad Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, Tong Sun (all Adobe) Workshop Adobe Co-authored Papers Towards a Shared Rubric for Dataset Annotation Andrew Greene Presented at the Data-Centric AI Workshop Sim-to-Real Interactive Recommendation via Off-Dynamics Reinforcement Learning Junda Wu, Zhuihui Xie, Tong Yu, Qizhi Li, Shuai Li Presented at the Offline Reinforcement Learning Workshop KDSalBox: A toolbox of efficient knowledge-distilled saliency models Ard Kastrati, Zoya Bylinskii, Eli Shechtman Presented at the Shared Visual Representations in Human & Machine Intelligence Workshop Off-Policy Evaluation in Embedded Spaces Jaron Jia Rong Lee, David Arbour, Georgios Theocharous Presented at the Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice Workshop Time-uniform central limit theory with applications to anytime-valid causal inference Ian Waudby-Smith, David Arbour, Ritwik Sinha, Edward Kennedy, Aaditya Ramdas Presented at the Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice Workshop Aesthetic Evaluation of Ambiguous Imagery Xi Wang, Zoya Bylinskii, Aaron Hertzmann, Robert Pepperell Presented at the Machine Learning for Creativity and Design Workshop Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections Victor S Bursztyn, Jennifer Healey, Vishwa Vinay Presented at the Machine Learning for Creativity and Design Workshop Inspiration Retrieval for Visual Exploration Nihal Jain, Praneetha Vaddamanu, Paridhi Maheshwari, Vishwa Vinay, Kuldeep Kulkarni Presented at the Machine Learning for Creativity and Design Workshop User-in-the-Loop Named Entity Recognition via Counterfactual Learning Tong Yu, Junda Wu, Ruiyi Zhang, Handong Zhao, Shuai Li Presented at the Efficient Natural Language and Speech Processing Workshop
Workshop Invited talk
Why does where people look matter? New trends & applications of visual attention modeling Zoya Bylinskii Presented at the Shared Visual Representations in Human & Machine Intelligence Workshop