Trellis Networks for Sequence Modeling
Paper
•
1810.06682
•
Published
•
1
RNN
-
-
ProSG: Using Prompt Synthetic Gradients to Alleviate Prompt Forgetting of RNN-like Language Models
Paper • 2311.01981 • Published • 1 -
Gated recurrent neural networks discover attention
Paper • 2309.01775 • Published • 7 -
Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
Paper • 2305.19190 • Published • 1 -
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 138 -
On the Universality of Linear Recurrences Followed by Nonlinear Projections
Paper • 2307.11888 • Published • 1 -
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Paper • 2310.18780 • Published • 3 -
Cached Transformers: Improving Transformers with Differentiable Memory Cache
Paper • 2312.12742 • Published • 12 -
RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
Paper • 2106.08928 • Published • 1 -
StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
Paper • 2311.14495 • Published • 1 -
Hierarchically Gated Recurrent Neural Network for Sequence Modeling
Paper • 2311.04823 • Published • 1 -
Enhancing Transformer RNNs with Multiple Temporal Perspectives
Paper • 2402.02625 • Published -
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 52 -
Improving Token-Based World Models with Parallel Observation Prediction
Paper • 2402.05643 • Published • 1 -
Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models
Paper • 2404.04478 • Published • 12 -
HGRN2: Gated Linear RNNs with State Expansion
Paper • 2404.07904 • Published • 17 -
GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression
Paper • 2407.12077 • Published • 54