941 citations · 2.8k across the 32 of their papers we have counts for
5 papers · 1 filter
Multimodal Latent Language Modeling with Next-Token Diffusion
Yutao Sun, Hangbo Bao, Wenhui Wang +5
Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose…
RedStone: Curating General, Code, Math, and QA Data for Large Language Models
Yaoyao Chang, Lei Cui, Li Dong +13
Pre-training Large Language Models (LLMs) on high-quality, meticulously curated datasets is widely recognized as critical for enhancing their performance and generalization capabil…
You Only Cache Once: Decoder-Decoder Architectures for Language Models
Yutao Sun, Li Dong, Yi Zhu +6
We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i.e., a cross-decoder stacked u…
Multi-Head Mixture-of-Experts
Xun Wu, Shaohan Huang, Wenhui Wang +1
Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activat…
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Shuming Ma, Hongyu Wang, Lingxiao Ma +7
Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in whic…