FarnoushRJ / MambaLRP
[NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models".
☆37Updated 4 months ago
Alternatives and similar repositories for MambaLRP:
Users that are interested in MambaLRP are comparing it to the libraries listed below
- More dimensions = More fun☆21Updated 7 months ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆48Updated 9 months ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆214Updated 9 months ago
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆37Updated 8 months ago
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆124Updated last month
- This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguo…☆40Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆61Updated 5 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆122Updated last year
- State Space Models☆66Updated 10 months ago
- ☆29Updated 7 months ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- [NeurIPS 2023] Factorized Contrastive Learning: Going Beyond Multi-view Redundancy☆66Updated last year
- Personal implementation of ASIF by Antonio Norelli☆25Updated 9 months ago
- Recycling diverse models☆44Updated 2 years ago
- Official implementation for "Targeted Cause Discovery with Data-Driven Learning"☆23Updated 6 months ago
- ☆52Updated 5 months ago
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆63Updated 2 months ago
- Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning☆40Updated 10 months ago
- TorchDR - PyTorch Dimensionality Reduction☆95Updated last month
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆33Updated last month
- PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)☆71Updated last year
- Official implementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".☆31Updated last year
- Implementations of various linear RNN layers using pytorch and triton☆50Updated last year
- I2M2: Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning (NeurIPS 2024)☆17Updated 4 months ago
- ☆32Updated 11 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆53Updated 6 months ago
- [ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation☆38Updated last week
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆98Updated 6 months ago
- Minimal Implementation of Visual Autoregressive Modelling (VAR)☆28Updated this week
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆52Updated 3 months ago