5 citations · 27 across the 26 of their papers we have counts for
8 papers · 1 filter
DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
Weilin Cai, Le Qin, Shwai He +3
Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be vi…
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Shwai He, Weilin Cai, Jiayi Huang +1
The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance performance and efficiency. However, u…
What Matters in Transformers? Not All Attention is Needed
Shwai He, Guoheng Sun, Zheyu Shen +1
While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficie…
Loki: Low-rank Keys for Efficient Sparse Attention
Prajwal Singhania, Siddharth Singh, Shwai He +2
Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the sel…
Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
Shwai He, Daize Dong, Liang Ding +1
Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world dep…
Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration
Shwai He, Ang Li, Tianlong Chen
Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource…
PAD-Net: An Efficient Framework for Dynamic Networks
Shwai He, Liang Ding, Daize Dong +3
Dynamic networks, e.g., Dynamic Convolution (DY-Conv) and the Mixture of Experts (MoE), have been extensively explored as they can considerably improve the model's representation p…
Multi-modal Attention Network for Stock Movements Prediction
Shwai He, Shi Gu
Stock prices move as piece-wise trending fluctuation rather than a purely random walk. Traditionally, the prediction of future stock movements is based on the historical trading re…