Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"
☆18Apr 30, 2025Updated last year
Alternatives and similar repositories for Gather-and-Aggregate
Users that are interested in Gather-and-Aggregate are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆128Sep 13, 2024Updated 2 years ago
- Full pipeline for building LLM, including pretrain, instruction tuning with RLHF, DPO, and distillation☆15Aug 14, 2026Updated 2 months ago
- ☆93Aug 19, 2026Updated 2 months ago
- ☆40Feb 26, 2024Updated 2 years ago
- ☆14Mar 2, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆22Oct 18, 2026Updated 2 weeks ago
- ☆16Aug 7, 2026Updated 3 months ago
- [ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yue…☆18Mar 21, 2025Updated last year
- ☆289Jun 6, 2025Updated last year
- ☆49Sep 9, 2026Updated last month
- [ACL 2026] Official repo for "Native Hybrid Attention for Efficient Sequence Modeling"☆35Sep 17, 2026Updated last month
- ☆51Jul 3, 2026Updated 4 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆44Dec 29, 2025Updated 10 months ago
- A hardware hybrid scheduling tensor engine. Improves performace by 35% for medium workload compared to pure GPU.☆13Jun 22, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for Fast-weight Product Key Memory (FwPKM)☆27Mar 18, 2026Updated 7 months ago
- ☆24Jun 16, 2026Updated 4 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆94Oct 30, 2024Updated 2 years ago
- ☆11Mar 29, 2025Updated last year
- A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks☆38Oct 31, 2024Updated 2 years ago
- This is the official repo of "Scaling Recurrent Neural Networks to a Billion Parameters with Zero-Order Optimization"☆14Jan 8, 2026Updated 9 months ago
- ☆32May 20, 2026Updated 5 months ago
- ☆11May 21, 2026Updated 5 months ago
- Implementation of ViLLA-X, Enhancing Latent Action Modeling in Vision-Language-Action Models☆23Aug 27, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Triton kernels for dynamic causal short convolutions.☆31Jun 4, 2026Updated 5 months ago
- ☆16Oct 21, 2025Updated last year
- [WWW 2026 Oral] MoE-CL:Self-Evolving LLMs via Continual Instruction Tuning☆22Dec 1, 2025Updated 11 months ago
- coloring terminal text with intensities (used for plotting probability, entropy with tokens)☆12Oct 11, 2024Updated 2 years ago
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆32Aug 19, 2025Updated last year
- Fluid Language Model Benchmarking☆29Sep 16, 2025Updated last year
- Retargetable ML compilers for the twenty-first century!☆13Apr 22, 2025Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Apr 22, 2025Updated last year
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆55May 20, 2026Updated 5 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.
- Universal Transformer with Memory Tokens. Pure JAX NNX. TPU-ready.☆13May 12, 2026Updated 5 months ago
- Reinforcement Learning based on Stock Trading with multiple backends.☆12Mar 2, 2024Updated 2 years ago
- Code and data for the paper ”Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a L…☆10Dec 3, 2023Updated 2 years ago
- Implementation of Multiscreen proposed by Ken Nakanishi for "Screening is Enough"☆19May 13, 2026Updated 5 months ago
- A few models converted from caffe to CoreMLs format.☆15Jun 6, 2017Updated 9 years ago
- [AAAI 2026] WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus Images☆16Mar 25, 2026Updated 7 months ago
- PyTorch implementation of models from the Zamba2 series.☆197Jan 23, 2025Updated last year