nreHieW / minVAR
Minimal Implementation of Visual Autoregressive Modelling (VAR)
☆29Updated last week
Alternatives and similar repositories for minVAR:
Users that are interested in minVAR are comparing it to the libraries listed below
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated 9 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆44Updated 3 weeks ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 7 months ago
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆35Updated last month
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆57Updated last month
- Official code for the paper "Attention as a Hypernetwork"☆25Updated 9 months ago
- NeuMeta transforms neural networks by allowing a single model to adapt on the fly to different sizes, generating the right weights when n…☆42Updated 4 months ago
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆16Updated 3 weeks ago
- Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆15Updated 2 months ago
- ☆32Updated 5 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆55Updated 10 months ago
- Official code implementation for the work Preference Alignment with Flow Matching (NeurIPS 2024)☆45Updated 4 months ago
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆50Updated 2 months ago
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.