Stable Looped Models and their Scaling Laws
☆174May 17, 2026Updated 3 months ago
Alternatives and similar repositories for parcae
Users that are interested in parcae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆29May 20, 2026Updated 3 months ago
- ☆95Jun 8, 2026Updated 2 months ago
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence☆69Nov 11, 2025Updated 9 months ago
- ☆80Aug 14, 2026Updated 2 weeks ago
- LoopFormer is an elastic-depth looped Transformer trained on variable-length trajectories, using time/step-size conditioning and a shortc…☆30Mar 28, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆86Aug 19, 2026Updated last week
- ☆15Feb 5, 2026Updated 6 months ago
- ☆79Apr 26, 2026Updated 4 months ago
- Compositional Muon release☆25Jun 5, 2026Updated 2 months ago
- Full model implementation for Flow Equivariant World Models (ICML 2026), world models with memory for dynamic scenes☆56Jul 29, 2026Updated last month
- Attention variant with per-channel multiplicative decay☆50Jun 3, 2026Updated 2 months ago
- Generic library for neural collapse and several derivative works on the phenomenon.☆17Apr 14, 2025Updated last year
- ☆34Apr 8, 2025Updated last year
- ☆70Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆24Dec 6, 2025Updated 8 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆682Feb 15, 2026Updated 6 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆17Apr 30, 2025Updated last year
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆274May 6, 2026Updated 3 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆88May 29, 2026Updated 3 months ago
- ☆22Jan 19, 2024Updated 2 years ago
- ☆14Mar 2, 2025Updated last year
- HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.☆1,920Jun 17, 2026Updated 2 months ago
- Official codebase for "Next-Latent Prediction Transformers Learn Compact World Models"☆158Jun 12, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated 11 months ago
- ☆153Sep 29, 2025Updated 11 months ago
- Delta Attention Residuals - supplementary code and pretrained models☆43May 20, 2026Updated 3 months ago
- [ICML 2026] Set Diffusion: Interpolating Token Orderings between Autoregression and Diffusion for Fast and Flexible Decoding☆26Aug 9, 2026Updated 3 weeks ago
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation☆306Feb 18, 2026Updated 6 months ago
- Bridge incompatible embedding spaces with a single SVD. When your embedding provider deprecates a model, adapt instead of re-embedding.☆36Apr 28, 2026Updated 4 months ago
- Implementation of the Hierarchical Latent Action Model, proposed by Hanjung Kim et al. of Yonsei University☆17May 6, 2026Updated 3 months ago
- [ICLR 2026] GRAPE: Group Representational Position Encoding (https://arxiv.org/abs/2512.07805)☆115Jun 15, 2026Updated 2 months ago
- Official PyTorch implementation of "Latent Reasoning in TRMs is Secretly a Policy Improvement Operator" (ICML 2026)☆26May 29, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- An unbounded n-gram language model on Tiny Shakespeare☆22Jan 21, 2026Updated 7 months ago
- Gecko Architecture☆18Jan 13, 2026Updated 7 months ago
- H-Net: Hierarchical Network with Dynamic Chunking☆878Nov 20, 2025Updated 9 months ago
- ☆51Jul 3, 2026Updated last month
- Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.☆215Jun 1, 2026Updated 2 months ago
- Data pipeline for HRM-Text pretraining☆72May 21, 2026Updated 3 months ago
- Storing the LongCoT-mini results for RLM(GPT-5.2)☆20Apr 26, 2026Updated 4 months ago