Shikai Qiu

29 papers A* 9C 1Misc 1Journal 15Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence.
CoRR
Marc Finzi, Shikai Qiu, Yiding Jiang, Pavel Izmailov, J. Zico Kolter, Andrew Gordon Wilson
2025 A* conf
Customizing the Inductive Biases of Softmax Attention using Structured Matrices.
ICML
Yilun Kuang, Noah Amsel, Sanae Lotfi, Shikai Qiu, Andres Potapczynski, Andrew Gordon Wilson
2025 J jnl
Customizing the Inductive Biases of Softmax Attention using Structured Matrices.
CoRR
Yilun Kuang, Noah Amsel, Sanae Lotfi, Shikai Qiu, Andres Potapczynski, Andrew Gordon Wilson
2025 J jnl
Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales.
CoRR
Shikai Qiu, Zixi Chen, Hoang Phan, Qi Lei, Andrew Gordon Wilson
2025 J jnl
Out-of-Distribution Detection Methods Answer the Wrong Questions.
CoRR
Yucen Lily Li, Daohan Lu, Polina Kirichenko, Shikai Qiu, Tim G. J. Rudner, C. Bayan Bruss, Andrew Gordon Wilson
2025 — conf
Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection.
ICML (Position Papers)
Yucen Lily Li, Daohan Lu, Polina Kirichenko, Shikai Qiu, Tim G. J. Rudner, C. Bayan Bruss, Andrew Gordon Wilson
2025 A* conf
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks.
ICML
Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala
2025 J jnl
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks.
CoRR
Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala
2024 A* conf
Compute Better Spent: Replacing Dense Layers with Structured Matrices.
ICML
Shikai Qiu, Andres Potapczynski, Marc Anton Finzi, Micah Goldblum, Andrew Gordon Wilson
2024 J jnl
Compute Better Spent: Replacing Dense Layers with Structured Matrices.
CoRR
Shikai Qiu, Andres Potapczynski, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson
2024 A* conf
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices.
NeurIPS
Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Charlie Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
2024 J jnl
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices.
CoRR
Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Zixi Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
2024 A* conf
Transferring Knowledge From Large Foundation Models to Small Downstream Models.
ICML
Shikai Qiu, Boran Han, Danielle C. Maddix, Shuai Zhang, Bernie Wang, Andrew Gordon Wilson
2024 J jnl
Transferring Knowledge from Large Foundation Models to Small Downstream Models.
CoRR
Shikai Qiu, Boran Han, Danielle C. Maddix, Shuai Zhang, Yuyang Wang, Andrew Gordon Wilson
2023 A* conf
Function-Space Regularization in Neural Networks: A Probabilistic Perspective.
ICML
Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu, Andrew Gordon Wilson
2023 J jnl
Function-Space Regularization in Neural Networks: A Probabilistic Perspective.
CoRR
Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu, Andrew Gordon Wilson
2023 A* conf
Large Language Models Are Zero-Shot Time Series Forecasters.
NeurIPS
Nate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson
2023 J jnl
Large Language Models Are Zero-Shot Time Series Forecasters.
CoRR
Nate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson
2023 A* conf
Should We Learn Most Likely Functions or Parameters?
NeurIPS
Shikai Qiu, Tim G. J. Rudner, Sanyam Kapoor, Andrew Gordon Wilson
2023 J jnl
Should We Learn Most Likely Functions or Parameters?
CoRR
Shikai Qiu, Tim G. J. Rudner, Sanyam Kapoor, Andrew Gordon Wilson
2023 A* conf
Simple and Fast Group Robustness by Automatic Feature Reweighting.
ICML
Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson
2023 J jnl
Simple and Fast Group Robustness by Automatic Feature Reweighting.
CoRR
Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson
2021 J jnl
Low latency group-sorted QR decomposition algorithm for larger-scale MIMO systems.
IET Commun.
Lirui Chen, Yu Wang, Zuocheng Xing, Shikai Qiu, Qinglin Wang, Yongzhong Li
2020 Misc conf
A Low-Latency Successive Cancellation Hybrid Decoder for Convolutional Polar Codes.
ICASSP
Yu Wang, Shikai Qiu, Lirui Chen, Qinglin Wang, Yang Zhang, Cang Liu, Zuocheng Xing
2020 C conf
A Paralleled Greedy LLL Algorithm for 16×16 MIMO Detection.
ISCAS
Lirui Chen, Yu Wang, Zuocheng Xing, Shikai Qiu, Qinglin Wang, Yang Zhang
2020 J jnl
An Area-Efficient Hybrid Polar Decoder With Pipelined Architecture.
IEEE Access
Yu Wang, Qinglin Wang, Yang Zhang, Shikai Qiu, Zuocheng Xing
2020 J jnl
Efficient MIMO Preprocessor With Sorting-Relaxed QR Decomposition and Modified Greedy LLL Algorithm.
IEEE Access
Lirui Chen, Zuocheng Xing, Yongzhong Li, Shikai Qiu
2019 — conf
Architectural Implications in Graph Processing of Accelerator with Gardenia Benchmark Suite.
ISPA/BDCloud/SocialCom/SustainCom
Yang Zhang, Jie Shen, Zhen Xu, Shikai Qiu, Xuhao Chen
2018 — conf
A Low Latency SCAN-Flip Polar Decoder for 5G Vehicular Communication.
INTSYS
Yu Wang, Lirui Chen, Shikai Qiu, Li Huang, Zuocheng Xing