InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis Paper • 2509.10441 • Published Sep 12 • 30
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning Paper • 2509.07980 • Published Sep 9 • 101
Common Pile v0.1 Raw Data Collection 8TB of public domain and openly licensed text • 30 items • Updated Aug 14 • 21
view article Article nanoVLM: The simplest repository to train your VLM in pure PyTorch +5 May 21 • 235
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation Paper • 2506.09790 • Published Jun 11 • 53
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models Paper • 2506.04180 • Published Jun 4 • 33
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't Paper • 2503.16219 • Published Mar 20 • 52