Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public
☆189May 13, 2026Updated 6 months ago
Alternatives and similar repositories for hyper-connections
Users that are interested in hyper-connections are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆381Feb 17, 2026Updated 8 months ago
- Implementation of Recurrent Independent Mechanisms in Pytorch☆27Apr 6, 2026Updated 7 months ago
- Interactive visualization of Manifold-Constrained Hyper-Connections (mHC) for stable deep network training☆28Jul 4, 2026Updated 4 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆49Sep 2, 2025Updated last year
- Implementation of the fast weight product key memory from Sakana AI☆21Sep 17, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Just a repository that will house some MLPs and their variants, so to avoid having to reimplement them again and again for different proj…☆51Oct 31, 2026Updated 2 weeks ago
- Explorations into NEAT and some of its derivative research☆42Updated this week
- mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations☆96Jan 12, 2026Updated 10 months ago
- Unofficial implementation of Hippoformer, Integrating Hippocampus-inspired Spatial Memory with Transformers☆57Aug 4, 2026Updated 3 months ago
- ☆12Jul 17, 2025Updated last year
- Implementation of the proposed MaskBit from Bytedance AI☆82Nov 12, 2024Updated 2 years ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆145Sep 3, 2026Updated 2 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆299Jun 3, 2025Updated last year
- ☆12Aug 19, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆81Sep 2, 2026Updated 2 months ago
- Implementation of Soft Actor Critic and some of its improvements in Pytorch☆73Updated this week
- Experimental text-to-video generation☆16Aug 30, 2026Updated 2 months ago
- Implementation of TableFormer, Robust Transformer Modeling for Table-Text Encoding, in Pytorch☆39Mar 29, 2022Updated 4 years ago
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆72Jun 2, 2026Updated 5 months ago
- Some utility functions to help myself (and perhaps others) go faster with ML/AI work☆55Nov 6, 2026Updated last week
- Unofficial implementation of GotenNet, new SOTA 3d equivariant transformer, in Pytorch☆68Apr 7, 2025Updated last year
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch☆2,005Nov 4, 2026Updated last week
- Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) - from Gopalakrishnan et al. under Schmidhu…☆74Jun 21, 2026Updated 4 months 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.
- An implementation of PPO in Pytorch☆129Updated this week
- Causal Attention with Lookahead Keys☆28Sep 26, 2025Updated last year
- Implementation of various evolutionary algorithms, starting with evolutionary strategies☆54Updated this week
- ☆51Jul 3, 2026Updated 4 months ago
- Implementation of the MetaController proposed in "Emergent temporal abstractions in autoregressive models enable hierarchical reinforceme…☆107Nov 5, 2026Updated last week
- Implementation of Strassen attention, from Kozachinskiy et al. of National Center of AI in Chile☆41Jul 8, 2025Updated last year
- A 210M text-to-image diffusion transformer trained from scratch on one GPU in 3.5 days: rectified flow on FLUX.2 latents, aspect-ratio bu…☆17Nov 6, 2026Updated last week
- Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT☆33Feb 6, 2026Updated 9 months ago
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆55Nov 25, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Muon in Int8 Precision Made Possible☆21Nov 7, 2026Updated last week
- Explorations into the proposed Streaming Deep Reinforcement Learning, from University of Alberta☆32Updated this week
- Contrastive Reinforcement Learning☆75Updated this week
- Implementation of a Light Recurrent Unit in Pytorch☆51Oct 9, 2026Updated last month
- Implementation of the proposed minGRU in Pytorch☆328Dec 10, 2025Updated 11 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆564Jan 18, 2026Updated 9 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆548May 16, 2025Updated last year
Are these results useful?