UBC Computer Science has 13 accepted papers at NeurIPS 2022 conference
9 professors from the Computer Science department at the University of British Columbia (and their co-authors) have had 13 papers in total accepted for the 2022 conference on Neural Information Processing Systems (NeurIPS).
NeurIPS is the premiere conference that celebrates the work being done in artificial intelligence and machine learning, and will take place November 28th through December 9th 2022.
This year there were 10,411 full paper submissions to NeurIPS, of which the program committee accepted 25.6% for presentation at the conference.
13 of them are from UBC Computer Science, and also one of the competitions is co-organized by a UBC CS professor. Notably, several of the UBC papers are amongst the top two per cent to be accepted for oral presentations at the conference, designated below with an asterisk.
The UBC computer science professors for each paper below have a link to their personal website, and the names highlighted in orange are UBC students.
*Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Bowen Baker, Ilge Akkaya, Peter Zhokov, Joost Huizing, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, Jeff Clune
Understanding the Evolution of Linear Regions in Deep Reinforcement Learning
Setareh Cohan, Nam Hee Kim, David Rolnick, Michiel van de Panne
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints
Xingzhe He, Bastian Wandt, Helge Rhodin
Iterative Scene Graph Generation
Siddhesh Khandelwal, Leonid Sigal
FasterRisk: Fast and Accurate Interpretable Risk Scores
Jiachang Liu, Chudi Zhong, Boxuan Li, Margo Seltzer, Cynthia Rudin
*Exploring the Whole Rashomon Set of Sparse Decision Trees
Rui Xin, Chudi Zhong, Zhi Chen, Takuya Takagi, Margo Seltzer, Cynthia Rudin
Group GAN
Ali Seyfi, Jean-Francois Rajotte, Raymond Ng
Evaluating Graph Generative Models with Contrastively Learned Features
Hamed Shirzad, Kaveh Hassani, Danica J. Sutherland
Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels
Mohamad Amin Mohamadi, Wonho Bae, Danica J. Sutherland
A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models
Lijia Zhou, Frederic Koehler, Pragya Sur, Danica J. Sutherland, Nati Srebro
Flexible Diffusion Modeling of Long Videos
William Harvey, Saeid Naderiparizi, Vaden Masrani, Christian Weilbach, Frank Wood
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Jason Yoo, Frank Wood
TUSK: Task-Agnostic Unsupervised Keypoints
Yuhe Jin, Weiwei Sun, Jan Hosang, Eduard Trulls, Kwang Moo Yi
In addition, UBC professor Giuseppe Carenini is a co-organizer of one of the 25 competitions associated with NeurIPS:
NL4Opt: Formulating Optimization Problems Based on Their Natural Language Descriptions Rindra Ramamonjison, Amin Banitalebi-Dehkordi, Giuseppe Carenini, Bissan Ghaddar, Timothy Yu, Zirui Zhou, Yong Zhang