Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published 28 days ago • 199
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents Paper • 2605.25624 • Published May 25 • 34
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling Paper • 2606.02578 • Published Jun 1 • 5