SciForma: Structure-Faithful Generation of Scientific Diagrams Paper • 2607.18091 • Published 3 days ago • 17
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published 2 days ago • 56
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation Paper • 2605.14333 • Published May 14 • 35
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos Paper • 2602.06949 • Published Feb 6 • 37
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models Paper • 2602.03392 • Published Feb 3 • 59