Soon Hoe Lim

22 papers A* 4A 2Journal 16
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Kinetic-Energy Perspective of Flow Matching.
CoRR
Ziyun Li, Huancheng Hu, Soon Hoe Lim, Xuyu Li, Fei Gao, Enmao Diao, Zezhen Ding, Michalis Vazirgiannis, Henrik Boström
2026 J jnl
Is Flow Matching Just Trajectory Replay for Sequential Data?
CoRR
Soon Hoe Lim, Shizheng Lin, Michael W. Mahoney, N. Benjamin Erichson
2025 J jnl
Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting.
Trans. Mach. Learn. Res.
Soon Hoe Lim, Yijin Wang, Annan Yu, Emma Hart, Michael W. Mahoney, Xiaoye Sherry Li, N. Benjamin Erichson
2025 J jnl
EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching.
CoRR
Ziyun Li, Ben Dai, Huancheng Hu, Henrik Boström, Soon Hoe Lim
2025 J jnl
FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems.
CoRR
N. Benjamin Erichson, Vinicius Mikuni, Dongwei Lyu, Yang Gao, Omri Azencot, Soon Hoe Lim, Michael W. Mahoney
2025 A conf
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback.
AISTATS
N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney
2025 J jnl
On The Hidden Biases of Flow Matching Samplers.
CoRR
Soon Hoe Lim
2025 A* conf
Tuning Frequency Bias of State Space Models.
ICLR
Annan Yu, Dongwei Lyu, Soon Hoe Lim, Michael W. Mahoney, N. Benjamin Erichson
2024 J jnl
Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting.
CoRR
Soon Hoe Lim, Yijin Wang, Annan Yu, Emma Hart, Michael W. Mahoney, Xiaoye S. Li, N. Benjamin Erichson
2024 A conf
NoisyMix: Boosting Model Robustness to Common Corruptions.
AISTATS
N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Francisco Utrera, Ziang Cao, Michael W. Mahoney
2024 J jnl
Tuning Frequency Bias of State Space Models.
CoRR
Annan Yu, Dongwei Lyu, Soon Hoe Lim, Michael W. Mahoney, N. Benjamin Erichson
2022 A* conf
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent.
NeurIPS
Soon Hoe Lim, Yijun Wan, Umut Simsekli
2022 J jnl
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent.
CoRR
Soon Hoe Lim, Yijun Wan, Umut Simsekli
2022 J jnl
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback.
CoRR
N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney
2022 A* conf
Noisy Feature Mixup.
ICLR
Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera, Winnie Xu, Michael W. Mahoney
2022 J jnl
NoisyMix: Boosting Robustness by Combining Data Augmentations, Stability Training, and Noise Injections.
CoRR
N. Benjamin Erichson, Soon Hoe Lim, Francisco Utrera, Winnie Xu, Ziang Cao, Michael W. Mahoney
2021 J jnl
Noisy Feature Mixup.
CoRR
Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera, Winnie Xu, Michael W. Mahoney
2021 A* conf
Noisy Recurrent Neural Networks.
NeurIPS
Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney
2021 J jnl
Noisy Recurrent Neural Networks.
CoRR
Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney
2021 J jnl
Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory.
J. Mach. Learn. Res.
Soon Hoe Lim
2020 J jnl
Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory.
CoRR
Soon Hoe Lim
2017 J jnl
Bose polaron as an instance of quantum Brownian motion.
Quantum
Aniello Lampo, Soon Hoe Lim, Miguel Ángel García-March, Maciej Lewenstein