PC-ALM
☆249Nov 11, 2026Updated last week
Alternatives and similar repositories for pc-alm
Users that are interested in pc-alm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Speedrun for pretraining without backpropagation☆453Nov 5, 2026Updated 2 weeks ago
- Pretraining Transformers Without Backpropagation☆323Oct 6, 2026Updated last month
- ☆57Oct 20, 2026Updated last month
- ☆16Nov 12, 2026Updated last week
- Code and paper reproductions for MLPs Are Hebbians☆34Jul 22, 2026Updated 3 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.
- Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)☆1,150Updated this week
- Public code release for "Medial Axis Preconditioning for Knot Untangling and Volume-Filling Curves" by Yuta Noma, Alec Jacobson, and Kara…☆11Jan 4, 2026Updated 10 months ago
- The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery☆734Updated this week
- ☆98Jun 3, 2026Updated 5 months ago
- Pretraining Recurrent Networks without Recurrence☆78Jun 7, 2026Updated 5 months ago
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation☆325Feb 18, 2026Updated 9 months ago
- CroissAttn: FP4 attention forward and backward, with analysis of stochastic rounding, zero-sum softmax gradients, and sampled centering.☆16Oct 25, 2026Updated 3 weeks ago
- ☆153Nov 5, 2026Updated 2 weeks ago
- Building scalable looped models☆194Oct 23, 2026Updated 3 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Probe the fractal convergence landscape of reasoning models☆90Oct 21, 2026Updated last month
- Hilbert Operator for Progressive Encoding (HOPE), and Dispersed Elastic Fine-Tuning (DEFT).☆29Oct 27, 2026Updated 3 weeks ago
- Official codebase for "Next-Latent Prediction Transformers Learn Compact World Models"☆220Jun 12, 2026Updated 5 months ago
- Official Code for LpWM: A Case for Sparse Representations in World Models☆32Aug 26, 2026Updated 2 months ago
- A tiny, fully-reproducible JEPA world model that learns the physics of a bouncing DVD logo in representation space, dreams its future, an…☆36Jun 13, 2026Updated 5 months ago
- A drop-in replacement for the standard Categorical Cross-Entropy (CCE) loss that significantly improves OOD and Calibration performance w…☆52Apr 6, 2026Updated 7 months ago
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated last month
- OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.☆477Nov 11, 2026Updated last week
- ☆12Sep 22, 2026Updated last month
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆11Mar 4, 2025Updated last year
- ⚡ Official code for “Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus”…☆25Aug 13, 2026Updated 3 months ago
- Halo is an open-source framework built by White Circle for training large language and multimodal models☆867Updated this week
- Flow Map Speculative Decoding☆59Nov 3, 2026Updated 2 weeks ago
- CUDA Craftax-Classic: 7x faster RL training than JAX☆81Sep 10, 2026Updated 2 months ago
- ☆16Jul 21, 2025Updated last year
- ☆16Nov 4, 2026Updated 2 weeks ago
- Continuous Thought Machines, because thought takes time and reasoning is a process.☆2,049Dec 29, 2025Updated 10 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆25Jun 6, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated last month
- PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning☆669Apr 21, 2026Updated 7 months ago
- optimize neuro-centric parameters instead of weights to solve RL tasks☆14Oct 2, 2023Updated 3 years ago
- MoJev: typed, calibrated decisions in one forward pass.☆30Sep 23, 2026Updated last month
- A pure Rust implementation of Google's DiffusionGemma model☆37Sep 18, 2026Updated 2 months ago
- GPU-accelerated geospatial operations for Apple silicon, built on MLX☆12Oct 20, 2026Updated last month
- NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers.☆68Nov 13, 2026Updated last week
Are these results useful?