LIVE · refreshes every 20 min

updated Aug 26, 22:02 UTC

110010.art / topic

Hugging Face

Mar 27

Mar 27, 2025 QVQ-Max released as first version of visual reasoning model that can understand and reason about images and videos to provide solutions Qwen (Alibaba) → story

Mar 26

Mar 26, 2025 Qwen2.5 Omni released as flagship end-to-end multimodal model for text, image, audio, and video perception with real-time streaming responses Qwen (Alibaba) → story

Mar 23

Mar 23, 2025 Qwen2.5-VL-32B-Instruct released under Apache 2.0 with reinforcement learning optimizations and 32B parameters. Qwen (Alibaba) → story

Mar 5

Mar 5, 2025 QwQ-32B explores scaling reinforcement learning to enhance model reasoning capabilities Qwen (Alibaba) → story

Jan 26

Jan 26, 2025 Qwen2.5-VL released in 3 sizes (3B, 7B, 72B) for Hugging Face and ModelScope, with base and instruct models; includes visual understanding capabilities Qwen (Alibaba) → story

Jan 20

Jan 20, 2025 Global-batch load balance improves MoE LLM training efficiency; technical discussion from Hugging Face Modelscope Discord notes it as a near-free lunch Qwen (Alibaba) → story

Jan 13

Jan 13, 2025 Towards Effective Process Supervision in Mathematical Reasoning Qwen (Alibaba) → story

Dec 24

Dec 24, 2024 QVQ: To See the World with Wisdom Qwen (Alibaba) → story

Nov 27

Nov 27, 2024 QwQ: Reflect Deeply on the Boundaries of the Unknown Qwen (Alibaba) → story

Nov 11

Nov 11, 2024 Qwen2.5-Coder series open-sources the “Powerful”, “Diverse”, and “Practical” open-code LLMs, including Qwen2.5-Coder-32B-Instruct as a state-of-the-art open-source code model. Qwen (Alibaba) → story

Sep 18

Sep 18, 2024 Qwen2.5 released as the latest addition to the Qwen family, touted as a large open-source release Qwen (Alibaba) → story

← 1 2 3 4 →