awesome-latent-refinement

Research on models and agents that improve reasoning and planning through iterative latent computation.
https://github.com/matinaghaei/awesome-latent-refinement

Last synced: 22 days ago
JSON representation

🎮 Reinforcement-Learned Latent Refinement

⏱️ Compute in RL

![arXiv - Link-blue.svg)](https://rajghugare19.github.io/computation-rl/index.html)

🗺️ Model-Free Planning

![arXiv - Boxoban-green.svg)](https://github.com/google-deepmind/boxoban-levels)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=ORxjH9kTp8)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=DzGe40glxs)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=aAshH4kQ1v)

♻️ Recurrent Reasoning Agents

![arXiv

🔗 Related Awesome Lists

🚫 Excluded (RL)

🧬 Supervised Latent Refinement

🧠 Dedicated Reasoners

![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=Tsp2PL7-GQ)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=PPjSKy40XUB)
![arXiv - GitHub-green.svg)](https://github.com/sapientinc/HRM)
![arXiv - GitHub-green.svg)](https://github.com/SamsungSAILMontreal/TinyRecursiveModels)
![arXiv - GitHub-green.svg)](https://github.com/machinestein/Deep-Improvement-Supervision)
![arXiv - GitHub-green.svg)](https://github.com/arcprize/hierarchical-reasoning-model-analysis)
![arXiv
![arXiv - GitHub-green.svg)](https://github.com/ml-jku/SE-RRM)
![arXiv
![arXiv - GitHub-green.svg)](https://github.com/wwwwwwwwz/DenoisingRecursionModels)

🔁 Looped Language Models

![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=Itxz7S4Ip3)
![arXiv - GitHub-green.svg)](https://github.com/seal-rg/recurrent-pretraining)
![arXiv
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=din0lGfZFd)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=jBSye8M3FQ)
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=z62rRFnNaX)
![arXiv
![arXiv - Link-blue.svg)](https://ouro-llm.github.io/)
![arXiv - GitHub-green.svg)](https://github.com/mcleish7/retrofitting-recurrence)
![arXiv - GitHub-green.svg)](https://github.com/thu-nics/TaH)
![arXiv
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=RzYXb5YWBs)
![arXiv
![arXiv
![arXiv
![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=fyWD8DDPKE)
![arXiv
![arXiv - GitHub-green.svg)](https://github.com/OSU-NLP-Group/Loop-Think-Generalize)
![arXiv

🦾 Vision-Language-Action Models

![arXiv - Paper-8E44AD.svg)](https://openreview.net/forum?id=hsIm52gD9p)