Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation Paper • 2606.26907 • Published 20 days ago • 49 • 4
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding Paper • 2606.21906 • Published 25 days ago • 25 • 13
Native Active Perception as Reasoning for Omni-Modal Understanding Paper • 2606.19341 • Published 28 days ago • 19 • 3
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation Paper • 2606.17030 • Published 30 days ago • 47 • 2
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling Paper • 2606.12370 • Published Jun 10 • 21 • 4