SCHOOL OF COMPUTING SCIENCE
SFU at NeurIPS: 7 Computing Science papers accepted for NeurIPS conference
Seven papers from the SFU School of Computing Science were accepted for this year's conference on Neural Information Processing Systems (NeurIPS).
Researchers at SFU Computing Science are dedicated to advancing the field of machine learning (ML), from innovative applications to foundational theory. Their groundbreaking work spans areas such as visual computing, language processing, reinforcement learning, and beyond. By publishing extensively, collaborating across disciplines, and engaging with the global ML community, SFU professors and students are fostering a rich, collaborative ecosystem that pushes the boundaries of what is possible in ML.
Once again, our researchers have an exceptional showing at NeurIPS 2024, with five papers in the main track, and two in the datasets and benchmarks track. We have one spotlight paper presentation —a distinction awarded to the top 2.08% of submissions at the conference. This year's NeurIPS will take place right here in SFU’s home city: beautiful Vancouver, BC, Canada, at the Vancouver Convention Centre, from Tuesday, Dec. 10, to Sunday, Dec. 15. It’s another fantastic reason for authors to be excited!
Parallel to NeurIPS, SFU is also hosting a series of mornings talks from 9 speakers from Dec 11th to 13th in SFU's downtown campus (roughly 10 minutes walk from the convention center). This special SFU event is organized by Wuyang Chen and features talks and social events designed to complement the NeurIPS experience. See our event page for more details.
The team of researchers from SFU Computing Science will also present three workshop papers and organize three workshops at the conference. Additionally, Assistant Professor Angelica Lim will give a talk at the Women in Machine Learning Workshop on December 10.
NeurIPS is one of the most prestigious annual conferences in machine learning and artificial intelligence. It attracts leading researchers, practitioners, and industry professionals from around the globe, providing a platform to present groundbreaking research, participate in workshops, and discuss the future of AI and computational sciences. The conference features invited talks, demonstrations, symposia, and oral and poster presentations of peer-reviewed papers. Alongside the conference, there is a professional exposition focusing on machine learning in practice, a series of tutorials, and topical workshops that offer a more informal setting for exchanging ideas.
SFU’s School of Computing Science has consistently excelled at NeurIPS, with an impressive 12 papers accepted for the 2023 conference.
Below is a list of all seven papers accepted for this year’s conference:
1. Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
Wuyang Chen, Jialin Song, Pu Ren, Shashank Subramanian, Dmitriy Morozov, Michael Mahoney
2. Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvari, Dale Schuurmans
3. ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process
Kiyohiro Nakayama, Mikaela Angelina Uy, Yang You, Ke Li, Leonidas Guibas
4. 3D Gaussian Splatting as Markov Chain Monte Carlo
Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Yang-Che Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
5. CRAYM: Neural Field Optimization via Camera RAY Matching
Liqiang Lin, Wenpeng Wu, Chi-Wing Fu, Hao Zhang, Hui Huang
6. InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang
7. BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
Zahra Gharaee, Scott Lowe, ZeMing Gong, Pablo Millan Arias, Nicholas Pellegrino, Austin T. Wang, Joakim Bruslund Haurum, Iuliia Zarubiieva, Lila Kari, Dirk Steinke, Graham Taylor, Paul Fieguth, Angel Chang