Yiming Dong

Orcid: 0009-0004-7121-7511

According to our database1, Yiming Dong authored at least 20 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers.
CoRR, February, 2026

Probing RLVR training instability through the lens of objective-level hacking.
CoRR, February, 2026

Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-sided and Two-Sided Preconditioning.
CoRR, January, 2026

From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
KISSColor: Kinetic and Intuitive Stroke Stretching for Vector Drawing Colorization.
ACM Trans. Graph., December, 2025

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads.
CoRR, October, 2025

Conda: Column-Normalized Adam for Training Large Language Models Faster.
CoRR, September, 2025

SADA: Safe and Adaptive Inference with Multiple Black-Box Predictions.
CoRR, September, 2025

P/D-Device: Disaggregated Large Language Model between Cloud and Devices.
CoRR, August, 2025

Stepsize anything: A unified learning rate schedule for budgeted-iteration training.
CoRR, May, 2025

On the O(\frac{√d}}{K<sup>1/4</sup>}) Convergence Rate of AdamW Measured by ℓ<sub>1</sub> Norm.
CoRR, May, 2025

Spatiotemporal Local Analysis for Nonlinear Dynamic Process Monitoring.
IEEE Trans. Instrum. Meas., 2025

On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm.
J. Mach. Learn. Res., 2025

Robust quaternion elastic-net for hypercomplex signal recovery.
Digit. Signal Process., 2025

Robust quaternion block orthogonal matching pursuit with its applications.
Digit. Signal Process., 2025

2024
Convergence Rate Analysis of LION.
CoRR, 2024

Reducing Memory Footprint in Deep Network Training by Gradient Space Reutilization.
Proceedings of the Pattern Recognition and Computer Vision - 7th Chinese Conference, 2024

2023
A process monitoring criterion based on weighted contribution of principal components.
Proceedings of the CAA Symposium on Fault Detection, 2023

2021
Gauge Equivariant Transformer.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Efficient Equivariant Network.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021


  Loading...