Submitted by taesiri 49 Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation Qwen 4
Submitted by XUANMING ZHANG 25 Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding Qwen 32 13
Submitted by Xiong-Hui Chen 27 Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System Qwen 127 2
Submitted by Xiong-Hui Chen 30 Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models Qwen 118 2
Submitted by Zhenghao Xing 19 Native Active Perception as Reasoning for Omni-Modal Understanding Qwen 60 3
Submitted by taesiri 14 Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification Qwen 46
Submitted by taesiri 47 Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation Qwen 2
Submitted by xianghao 7 Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization Qwen 2