radarFudan / Curse-of-memoryLinks
Curse-of-memory phenomenon of RNNs in sequence modelling
☆19Updated 3 months ago
Alternatives and similar repositories for Curse-of-memory
Users that are interested in Curse-of-memory are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆33Updated 2 years ago
- ☆32Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- ☆23Updated 11 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated last month
- Blog post☆17Updated last year
- ☆20Updated 2 years ago
- ☆49Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆125Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated last year
- Code for "Theoretical Foundations of Deep Selective State-Space Models" (NeurIPS 2024)☆15Updated 7 months ago
- Parallelizing non-linear sequential models over the sequence length☆53Updated 2 months ago
- ☆33Updated 4 years ago
- ☆33Updated 2 years ago
- Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces, NeurIPS 2021☆13Updated 3 years ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- ☆27Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago
- ☆33Updated 10 months ago
- ☆56Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆40Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated 11 months ago
- [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling☆79Updated last year
- ☆22Updated 3 years ago
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆56Updated last year
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆17Updated last year
- ☆51Updated 2 years ago