radarFudan / Curse-of-memoryLinks
Curse-of-memory phenomenon of RNNs in sequence modelling
☆19Updated 5 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 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- ☆31Updated last year
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆32Updated 2 years ago
- ☆23Updated last year
- ☆19Updated 2 years ago
- Code for "Theoretical Foundations of Deep Selective State-Space Models" (NeurIPS 2024)☆15Updated 9 months ago
- ☆49Updated last year
- ☆28Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated last year
- Blog post☆17Updated last year
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 4 years ago
- Parallelizing non-linear sequential models over the sequence length☆54Updated 3 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated last year
- Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces, NeurIPS 2021☆13Updated 3 years ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆33Updated 4 years ago
- ☆56Updated last year
- ☆33Updated 11 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆17Updated last year
- Implementations of various linear RNN layers using pytorch and triton☆52Updated 2 years ago
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆57Updated last year
- [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling☆80Updated last year
- Official Code Repository for the paper "Key-value memory in the brain"☆28Updated 7 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated last year
- ☆34Updated 2 years ago
- Here we will test various linear attention designs.☆61Updated last year
- ☆34Updated last year
- ☆51Updated 2 years ago