Non-official implementation of "Attention as an RNN" from https://arxiv.org/pdf/2405.13956, efficient associative parallel prefix scan and recurrent version implemented.
☆27Jul 27, 2024Updated last year
Alternatives and similar repositories for Attention-as-RNN
Users that are interested in Attention-as-RNN are comparing it to the libraries listed below
Sorting:
- ☆17Jul 24, 2023Updated 2 years ago
- A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advan…☆30Feb 22, 2026Updated last week
- Torch MinGRU implementation based on "Were RNNs All We Needed?"☆21Dec 5, 2024Updated last year
- PyTorch Implementation of the paper "MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition" pu…☆27Sep 18, 2025Updated 5 months ago
- ☆17Feb 1, 2026Updated last month
- ☆20Jan 4, 2026Updated last month
- Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context☆41Aug 16, 2024Updated last year
- ☆11Nov 13, 2025Updated 3 months ago
- This repository provides a method to dynamically change the clock output frequency, phase shift, and duty cycle of the mixed-mode clock m…☆14Nov 4, 2020Updated 5 years ago
- A nonparametric variational information bottleneck (NVIB) layer in Pytorch☆11Apr 15, 2025Updated 10 months ago
- Alpha mining with DEAP-based genetic programming.☆11Jul 7, 2023Updated 2 years ago
- Implementation of BIMRL: Brain Inspired Meta Reinforcement Learning - Roozbeh Razavi et al. (IROS 2022)☆10Dec 1, 2022Updated 3 years ago
- Accepted at WWW 25 Industrial Track (oral)☆18Jun 6, 2025Updated 8 months ago
- Fast, free, easy, and object-agnostic video anonymization☆11Dec 12, 2020Updated 5 years ago
- Official implementation of the UMDQN algorithm presented in the scientific research paper entitled "Distributional Reinforcement Learning…☆11Jun 3, 2022Updated 3 years ago
- factory.ai FACTORY_API_KEY switch and query☆27Dec 6, 2025Updated 2 months ago
- Code for optimal execution☆12Oct 29, 2020Updated 5 years ago
- Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, O…☆12Jan 31, 2023Updated 3 years ago
- Source code for Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach (NeurIPS 2023)☆10Dec 12, 2023Updated 2 years ago
- an implementation of paper"Retentive Network: A Successor to Transformer for Large Language Models" https://arxiv.org/pdf/2307.08621.pdf☆11Jul 25, 2023Updated 2 years ago
- [ICLR 2025 SynthData Workshop Spotlight] Empowering LLMs in Decision Games through Algorithmic Data Synthesis☆26Apr 27, 2025Updated 10 months ago
- Implementation of accurate coresets for known problems from the field of machine learning.☆11Nov 21, 2019Updated 6 years ago
- WordPress plugin to add useful decoration features to the Gutenberg RichText editor toolbar.☆10Updated this week
- Clustered Compositional Embeddings☆11Oct 25, 2023Updated 2 years ago
- 可用于中文开放领域信息抽取的数据集☆14Nov 15, 2021Updated 4 years ago
- Quantities in Typescript, Idris influenced☆10Dec 19, 2025Updated 2 months ago
- KMean Coreset evaluation and computation.☆12Jun 6, 2017Updated 8 years ago
- Official code for the paper: "Perception and Semantic Aware Regularization for Sequential Confidence Calibration （CVPR2023）"☆10May 15, 2024Updated last year
- Code to accompany the paper Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice☆10Aug 10, 2021Updated 4 years ago
- This repository is the official implementation of Low-Rank Modular Reinforcement Learning via Muscle Synergy.☆11Oct 27, 2022Updated 3 years ago
- A node module for allowing programmatic control of the useful Packer.IO tool☆16Nov 18, 2016Updated 9 years ago
- [COLM 2025: 1st Workshop on the Application of LLM Explainability to Reasoning and Planning] Latent Chain-of-Thought? Decoding the Depth-…☆17Oct 4, 2025Updated 4 months ago
- The officalimplement of dLLM-Factory☆26Jul 12, 2025Updated 7 months ago
- This repo contains the official code release of the Neural Experts paper, published in NeurIPS 2024.☆13Dec 3, 2024Updated last year
- Official PyTorch implementation of CD-MOE☆12Mar 29, 2025Updated 11 months ago
- Prioritized Sequence Experience Replay☆10Aug 16, 2021Updated 4 years ago
- Implementation prototype of the Deep Deterministic Off-Policy Gradient (DD-OPG) method.☆11Jun 12, 2019Updated 6 years ago
- Automatically create an importmap script.☆14Oct 20, 2024Updated last year
- UCPR: User-Centric Path Reasoning towards Explainable Recommendation, SIGIR 2021☆12Jun 18, 2022Updated 3 years ago