11 papers
Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
Ji Zhao, Yufei Gu, Shitong Shao +3
As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibiti…
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
Zhijian Zhuo, Yutao Zeng, Ya Wang +5
Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, m…
Conda: Column-Normalized Adam for Training Large Language Models Faster
Junjie Wang, Pan Zhou, Yiming Dong +6
Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimi…
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
Zihao Huang, Yu Bao, Qiyang Min +8
While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-lay…
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Yike Yuan, Ziyu Wang, Zihao Huang +4
Diffusion models have emerged as mainstream framework in visual generation. Building upon this success, the integration of Mixture of Experts (MoE) methods has shown promise in enh…
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
Hongzhi Huang, Defa Zhu, Banggu Wu +4
Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-…