Adobe Research at NeurIPS 2021

December 19, 2021

Examples of multi-implicit neural representation for high fidelity font reconstruction and generation with zoom-in box highlighting corners (baselines vs. our results shown in this NeurIPS 2021 paper.

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 

Area Chairs

Georgios Theocharous 

Related Posts