8 papers
Morphing into Hybrid Attention Models
Disen Lan, Jianbin Zheng, Yuxi Ren +5
Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the e…
Comba: Improving Bilinear RNNs with Closed-loop Control
Jiaxi Hu, Yongqi Pan, Jusen Du +5
Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Del…
MoM: Linear Sequence Modeling with Mixture-of-Memories
Jusen Du, Weigao Sun, Disen Lan +2
Linear sequence modeling methods, such as linear attention, state space modeling, and linear RNNs, offer significant efficiency improvements by reducing the complexity of training…
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Weigao Sun, Jiaxi Hu, Yucheng Zhou +12
Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer m…
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
Yifan Hu, Guibin Zhang, Peiyuan Liu +6
Time series forecasting methods generally fall into two main categories: Channel Independent (CI) and Channel Dependent (CD) strategies. While CI overlooks important covariate rela…
Liger: Linearizing Large Language Models to Gated Recurrent Structures
Disen Lan, Weigao Sun, Jiaxi Hu +2
Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-st…