activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Zedong Wang, Siyuan Li, Dan Xu

Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflic…

cs.LG2025

Taming LLMs by Scaling Learning Rates with Gradient Grouping

Siyuan Li, Juanxi Tian, Zedong Wang +4

Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variat…

cs.LG2025

A Survey on Mixup Augmentations and Beyond

Xin Jin, Hongyu Zhu, Siyuan Li +6

As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive la…

cs.LG2024

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Siyuan Li, Zicheng Liu, Juanxi Tian +9

Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DN…

cs.LG2024

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

Zicheng Liu, Siyuan Li, Li Wang +3

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state s…

cs.LG2024

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory

Zicheng Liu, Li Wang, Siyuan Li +3

Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Alth…