AI BriefingQwen news
The latest AI and developer news from Qwen, with short summaries.
Visit website →Qwen Releases 'Qwen-Image-2.1', a 7B Parameter Unified Image Model
Qwen has released Qwen-Image-2.1, an open-source image model with 7 billion parameters that integrates generation and editing.
PickQwen Releases 'Qwen3.8-LiveTranslate' with Real-Time Speaker Diarization and Source-Translation Synchronization
Qwen has released Qwen3.8-LiveTranslate, a real-time interpretation model featuring speaker timbre preservation and source-translation synchronization.
PickQwen Releases Qwen3.8-Omni-Flash with Enhanced Real-Time Audio-Visual Interaction and Agent Capabilities
Qwen has released Qwen3.8-Omni-Flash, featuring enhanced real-time audio-visual interaction and agent capabilities, along with related open-source tools.
Qwen Releases 'E-Commerce Bench' in Collaboration with Taobao to Evaluate Long-Term Operational Capabilities
The Qwen team, in collaboration with Taobao, released E-Commerce Bench, a long-term operational agent benchmark based on one year of real market data.
PickQwen-Drive-1.0, Vision-Language Foundation Model for Autonomous Driving Released
The Qwen team released Qwen-Drive-1.0, a vision-language foundation model dedicated to autonomous driving that integrates 3D perception and motion planning.
PickQwen3.8-Flash-Next: A New Architecture for Ultimate Cost Efficiency
Qwen3.8-Flash-Next demonstrates superior performance compared to existing models at 1/9 the cost.
PickQwen3.8-Max: A New Standard for Coding and Collaboration
Qwen has unveiled the 2.4T-parameter Qwen3.8-Max and announced an upcoming open-weight release.
Qwen-AgentWorld: A Language World Model for General-Purpose Agents
The Qwen team has released Qwen-AgentWorld, a native language world model that simulates 7 domains.
PickQwen-Robot Suite: A Foundation Model Family for Physical World Intelligence
The Qwen team has unveiled three robot foundation models that connect vision-language understanding to physical action.
PickQwen-RobotManip: Achieving Scaling of Robot Manipulation Foundation Models Through Alignment
Qwen-RobotManip is a VLA foundation model with outstanding generality, trained on 38,100 hours of large-scale data through data alignment techniques.
PickQwen-RobotWorld: An Infinite World for Embodied Agents
Qwen-RobotWorld is a next-generation Embodied World Model that uses natural language as an interface to jointly train across diverse robot embodiments and environments.
PickQwen-RobotNav: A Scalable Navigation Model Designed for Agentic Navigation Systems
Qwen-RobotNav is a scalable unified model that can adjust observation context to fit diverse navigation tasks.
PickQwen3.7-Plus: Multimodal Agentic Intelligence
Qwen3.7-Plus is a multimodal agentic model that unifies vision and language, moving seamlessly between GUI and CLI.
PickQwen-VLA: Going Beyond Understanding the World to Directly Acting in It
Qwen-VLA is a general-purpose VLA model that goes beyond visual understanding to perform continuous robot actions and trajectory prediction.
Qwen3.7: The Agentic Frontier
Qwen3.7-Max has unveiled its agentic, coding, and long-horizon autonomous execution performance.
Qwen3.5-LiveTranslate: From Sound to Sight, Translation Gets More Accurate
Qwen has unveiled Qwen3.5-LiveTranslate, a real-time interpretation model that leverages visual context as well.
Qwen-Scope: Decoding Intelligence and Unlocking Potential
Qwen has released Qwen-Scope, an SAE-based interpretability tool built on Qwen3 and Qwen3.5.
FlashQLA: A CP- and Backward-Friendly Fused Linear Attention Kernel Library for GDN
FlashQLA optimizes GDN Chunked Prefill with CP and fused kernels, achieving up to 3x speedup over FLA Triton.
Qwen3.6-27B: Flagship-Level Coding Realized with a 27B Dense Model
Qwen has open-sourced Qwen3.6-27B, a 27B dense multimodal model.
Qwen3.6-Max-Preview: Smarter, Sharper, and Still Evolving
Qwen3.6-Max-Preview has been released as a preview with improvements in coding, knowledge, and instruction following.