109 citations · 178 across the 14 of their papers we have counts for
4 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…
Differential Transformer
Tianzhu Ye, Li Dong, Yuqing Xia +4
Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling no…
FocusLLM: Precise Understanding of Long Context by Dynamic Condensing
Zhenyu Li, Yike Zhang, Tengyu Pan +6
Empowering LLMs with the ability to precisely understand long contexts is crucial for many downstream applications. However, handling long contexts with conventional transformer ar…
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…