12 citations · 39 across the 7 of their papers we have counts for
7 papers
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Zhanpeng Zeng, Cole Hawkins, Mingyi Hong +4
Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a fu…
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
Shuhuai Ren, Aston Zhang, Yi Zhu +5
This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic infor…
SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning
M Saiful Bari, Aston Zhang, Shuai Zheng +4
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of t…
SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing
Chaoyang He, Shuai Zheng, Aston Zhang +4
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost. MoE selects different sets of parameters (i.e., expe…
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
Haotao Wang, Aston Zhang, Yi Zhu +4
Existing out-of-distribution (OOD) detection methods are typically benchmarked on training sets with balanced class distributions. However, in real-world applications, it is common…
Removing Batch Normalization Boosts Adversarial Training
Haotao Wang, Aston Zhang, Shuai Zheng +3
Adversarial training (AT) defends deep neural networks against adversarial attacks. One challenge that limits its practical application is the performance degradation on clean samp…
MiCS: Near-linear Scaling for Training Gigantic Model on Public Cloud
Zhen Zhang, Shuai Zheng, Yida Wang +5
Existing general purpose frameworks for gigantic model training, i.e., dense models with billions of parameters, cannot scale efficiently on cloud environment with various networki…