radarFudan / Curse-of-memory
Curse-of-memory phenomenon of RNNs in sequence modelling
☆19Updated this week
Alternatives and similar repositories for Curse-of-memory:
Users that are interested in Curse-of-memory are comparing it to the libraries listed below
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆64Updated 11 months ago
- ☆23Updated 6 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 7 months ago
- ☆20Updated last year
- ☆27Updated 8 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆17Updated last year
- ☆21Updated 2 years ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated last year
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- Official code for the paper "Attention as a Hypernetwork"☆25Updated 9 months ago
- ☆31Updated 5 months ago
- ☆32Updated last year
- [ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yue…☆11Updated last week
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Updated last year
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated 4 months ago
- Blog post☆17Updated last year
- ☆51Updated 2 years ago
- ☆18Updated 10 months ago
- ☆22Updated 3 years ago
- ☆33Updated 3 years ago
- ☆11Updated last year
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆51Updated 9 months ago
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆48Updated 2 years ago
- Mixture of Attention Heads☆43Updated 2 years ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 9 months ago
- STABILIZING GRADIENTS FOR DEEP NEURAL NETWORKS VIA EFFICIENT SVD PARAMETERIZATION☆16Updated 6 years ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆26Updated 11 months ago
- ☆17Updated 2 months ago
- ☆18Updated 8 months ago