Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis Paper • 2603.06507 • Published Mar 6 • 1
view article Article How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs 5 days ago • 40
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels Paper • 2603.19312 • Published 30 days ago • 25
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 Feb 20 • 501
When Models Manipulate Manifolds: The Geometry of a Counting Task Paper • 2601.04480 • Published Jan 8 • 4