SakanaAI / continuous-thought-machinesLinks
Continuous Thought Machines, because thought takes time and reasoning is a process.
β1,176Updated this week
Alternatives and similar repositories for continuous-thought-machines
Users that are interested in continuous-thought-machines are comparing it to the libraries listed below
Sorting:
- A Self-adaptation Frameworkπ that adapts LLMs for unseen tasks in real-time!β1,123Updated 5 months ago
- Pretraining code for a large-scale depth-recurrent language modelβ801Updated this week
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorchβ1,412Updated last month
- Code for BLT research paperβ1,736Updated last month
- Self-Adapting Language Modelsβ697Updated 3 weeks ago
- Training Large Language Model to Reason in a Continuous Latent Spaceβ1,185Updated 5 months ago
- Automating the Search for Artificial Life with Foundation Models!β427Updated 6 months ago
- Dream 7B, a large diffusion language modelβ839Updated 3 weeks ago
- Darwin GΓΆdel Machine: Open-Ended Evolution of Self-Improving Agentsβ1,520Updated last month
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the inputβ798Updated last month
- Implementing DeepSeek R1's GRPO algorithm from scratchβ1,469Updated 2 months ago
- Large Concept Models: Language modeling in a sentence representation spaceβ2,246Updated 5 months ago
- Official Repository of Absolute Zero Reasonerβ1,601Updated 2 weeks ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.β316Updated 8 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.β1,840Updated 2 weeks ago
- Open-source implementation of AlphaEvolveβ3,208Updated this week
- Official PyTorch implementation for "Large Language Diffusion Models"β2,572Updated last month
- β363Updated last month
- Muon is an optimizer for hidden layers in neural networksβ1,092Updated this week
- MLGym A New Framework and Benchmark for Advancing AI Research Agentsβ529Updated 3 weeks ago
- β2,157Updated last week
- procedural reasoning datasetsβ960Updated last week
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"β555Updated last year
- Build your own visual reasoning modelβ395Updated last week
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchβ1,427Updated 2 months ago
- System 2 Reasoning Link Collectionβ843Updated 4 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modelingβ888Updated 2 months ago
- Atom of Thoughts for Markov LLM Test-Time Scalingβ579Updated last month
- noise_step: Training in 1.58b With No Gradient Memoryβ220Updated 6 months ago
- prime is a framework for efficient, globally distributed training of AI models over the internet.β779Updated last month