MintAct: A Unified Visual Agent for Digital Environments Paper • 2609.22083 • Published 5 days ago • 14
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations Paper • 2606.11188 • Published Jun 9 • 28
SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL Paper • 2504.11455 • Published Apr 15, 2025 • 14