Offical implementation of "MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map" (NeurIPS2024 Oral)
☆36Jan 18, 2025Updated last year
Alternatives and similar repositories for MetaLA
Users that are interested in MetaLA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implement spike-drive using OR residual connection and propose SynA attention for natural pruning.(Under Review)☆13Mar 31, 2024Updated 2 years ago
- This is simple code of SpikedAttention (Neurips 2024)☆23Mar 30, 2025Updated last year
- [TNNLS 2024] Implementation of "TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks"☆62Apr 16, 2024Updated 2 years ago
- Offical implementation of "Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation …☆234May 10, 2024Updated 2 years ago
- [Neural Networks] SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation☆31Apr 11, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Offical implementation of "Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training" (IEEE T-PAMI2025)☆117May 20, 2025Updated last year
- The code of SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models☆24Mar 25, 2026Updated 5 months ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆17Jul 18, 2024Updated 2 years ago
- Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagatio…☆49Apr 16, 2026Updated 5 months ago
- ☆39Jan 20, 2025Updated last year
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆33Aug 4, 2024Updated 2 years ago
- ☆15Mar 20, 2025Updated last year
- ☆23Nov 6, 2022Updated 3 years ago
- 🔥 A minimal training framework for scaling FLA models☆415Apr 22, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Offical implementation of High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference C…☆23Feb 3, 2026Updated 7 months ago
- [TrimKV] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs - [DBTrimKV] Make Each Token Count: Towards Improving Lo…☆21Jul 26, 2026Updated last month
- ☆24Nov 19, 2024Updated last year
- Offical code of "QKFormer: Hierarchical Spiking Transformer using Q-K Attention"☆150May 25, 2026Updated 3 months ago
- This repository presents the source code for the paper "MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Qu…☆26Sep 1, 2026Updated 2 weeks ago
- [ICML 2026] Improving GPT via a simple normalization strategy☆15May 22, 2026Updated 3 months ago
- ☆71Jul 8, 2025Updated last year
- [ICLR 2025] Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization☆25Oct 5, 2025Updated 11 months ago
- Offical implementation of "Inherent Redundancy in Spiking Neural Networks" (ICCV2023)☆29Jan 7, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Efficient PScan implementation in PyTorch☆17Jan 2, 2024Updated 2 years ago
- 📄 Evidence Retrieval and Claim Verification for the FEVER shared task using Transformer Networks☆12Feb 21, 2020Updated 6 years ago
- Official Code Repository for the paper "Key-value memory in the brain"☆34Feb 25, 2025Updated last year
- Offical implementation of "Quantized Spike-driven Transformer" (ICLR2025)☆34Dec 23, 2025Updated 8 months ago
- Pytorch implementation of ANN-SNN representation similarity analysis (TMLR 2023)☆13Apr 25, 2023Updated 3 years ago
- [ECCV 2024] Official implementation of the paper "EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-worl…☆38Oct 9, 2025Updated 11 months ago
- ☆37Dec 31, 2025Updated 8 months ago
- MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention (NeurIPS'25 Spotlight)☆27Feb 22, 2026Updated 6 months ago
- ☆33Nov 11, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [CVPR 2025] LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs☆15Jun 20, 2025Updated last year
- A list of papers about point cloud based place recognition, also known as loop closure detection in SLAM (processing)☆10Jan 30, 2024Updated 2 years ago
- 2019~2021年间Zero-shot/Data-free知识蒸馏的论文合集☆11Sep 8, 2021Updated 5 years ago
- Research about dataflow architecture☆15Nov 30, 2023Updated 2 years ago
- Code accompanying paper "Coordinated Proximal Policy Optimization"☆10Mar 26, 2022Updated 4 years ago
- An event based dataset loader under one common python API.☆10Mar 22, 2022Updated 4 years ago
- Official Implementation of "Circuit Transformer: A Transformer That Preserves Logical Equivalence"☆28Mar 13, 2025Updated last year