VITA-Group / SSM-BottleneckLinks
[ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li
☆12Updated 3 months ago
Alternatives and similar repositories for SSM-Bottleneck
Users that are interested in SSM-Bottleneck are comparing it to the libraries listed below
Sorting:
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆17Updated last year
- ☆17Updated 5 months ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated last month
- Unofficial implementation of paper : Exploring the Space of Key-Value-Query Models with Intention☆11Updated 2 years ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated 10 months ago
- Official code for the paper "Attention as a Hypernetwork"☆39Updated last year
- ☆16Updated 2 years ago
- ☆23Updated 9 months ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated 2 weeks ago
- ☆12Updated 4 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"☆14Updated last year
- A minimal re-implementation of orthogonal fine-tuning (OFT) for LLMs. Based on nanoGPT and minLoRA.☆12Updated last year
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆51Updated 6 months ago
- ☆44Updated last year
- ☆13Updated 2 months ago
- A quick test of SIREN on out-of-sample tasks☆13Updated 4 years ago
- Official Implementation of Nabla-GFlowNet (ICLR 2025)☆20Updated last month
- Exploring Diffusion Transformer Designs via Grafting☆33Updated last week
- Official Implementation of the paper: A Complete Recipe for Diffusion Generative Models☆30Updated 7 months ago
- [NeurIPS 2024, spotlight] Multivariate Learned Adaptive Noise for Diffusion Models☆21Updated 6 months ago
- Code for "Implicit Normalizing Flows" (ICLR 2021 spotlight)☆36Updated 4 years ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated 7 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆35Updated last year
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Updated last year
- The official repo of continuous speculative decoding☆27Updated 2 months ago
- Does VLM Classification Benefit from LLM Description Semantics? (AAAI 2025)☆17Updated 5 months ago
- ☆32Updated last year