Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR Paper • 2504.11101 • Published Apr 15
IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards Paper • 2508.04632 • Published Aug 6 • 2
Intern-S1: A Scientific Multimodal Foundation Model Paper • 2508.15763 • Published Aug 21 • 256