Chiwun Yang

According to our database, Chiwun Yang authored at least 11 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond.

Yekun Ke, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang

CoRR, 2024

Unlocking the Theory Behind Scaling 1-Bit Neural Networks.

Majid Daliri, Zhao Song, Chiwun Yang

CoRR, 2024

Toward Infinite-Long Prefix in Transformer.

Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang

CoRR, 2024

Attention is Naturally Sparse with Gaussian Distributed Input.

Yichuan Deng, Zhao Song, Chiwun Yang

CoRR, 2024

Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence.

Yichuan Deng, Zhao Song, Chiwun Yang

CoRR, 2024

How to Protect Copyright Data in Optimization of Large Language Models?

Timothy Chu, Zhao Song, Chiwun Yang

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space.

Raghav Addanki, Chenyang Li, Zhao Song, Chiwun Yang

CoRR, 2023

A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer.

Chenyang Li, Zhao Song, Weixin Wang, Chiwun Yang

CoRR, 2023

Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights.

Yichuan Deng, Zhao Song, Shenghao Xie, Chiwun Yang

CoRR, 2023

An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent.

Zhao Song, Chiwun Yang

CoRR, 2023

Fine-tune Language Models to Approximate Unbiased In-context Learning.

Timothy Chu, Zhao Song, Chiwun Yang

CoRR, 2023