lucidrains / h-net-dynamic-chunkingLinks
Implementation of the dynamic chunking mechanism in H-net by Hwang et al. of Carnegie Mellon
☆64Updated 3 weeks ago
Alternatives and similar repositories for h-net-dynamic-chunking
Users that are interested in h-net-dynamic-chunking are comparing it to the libraries listed below
Sorting:
- Implementation of a multimodal diffusion transformer in Pytorch☆103Updated last year
- Implementation of the proposed MaskBit from Bytedance AI☆82Updated 10 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆178Updated last year
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆132Updated this week
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆125Updated 3 weeks ago
- Official code implementation for the work Preference Alignment with Flow Matching (NeurIPS 2024)☆58Updated 10 months ago
- [ICML 2025] Gaussian Mixture Flow Matching Models (GMFlow)☆135Updated 3 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- ☆149Updated 5 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 6 months ago
- Flash Attention Triton kernel with support for second-order derivatives☆75Updated this week
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆89Updated 2 months ago
- The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows☆85Updated 3 weeks ago
- Explore how to get a VQ-VAE models efficiently!☆52Updated last month
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆121Updated 10 months ago
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆140Updated last month
- Code accompanying the paper "Generalized Interpolating Discrete Diffusion"☆99Updated 3 months ago
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆101Updated last week
- Explorations into improving ViTArc with Slot Attention☆42Updated 10 months ago
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆52Updated 7 months ago
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆150Updated 7 months ago
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆249Updated 3 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆90Updated 2 weeks ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 8 months ago
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated last year
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆92Updated 6 months ago
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆53Updated 9 months ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆67Updated 3 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆123Updated 9 months ago
- Autoregressive Image Generation☆32Updated 3 months ago