Alibaba/Qwen

Latest AI news, models and releases from Alibaba/Qwen. ['CodeQwen1.5', 'Cotype Light 3', 'Cotype Pro 3', 'Fun-Realtime-TTS', 'Hanguang', 'Hanguang 800', 'HappyOyster 1.0', 'ICN Switch 1.0', 'not specified', 'Panjiu', 'Qianwen', 'Qoder Security', 'QVQ-72B-Preview', 'QVQ-Max', 'Qwen', 'Qwen 2', 'Qwen2.5', 'Qwen2.5-0.5B', 'Qwen2.5-14B', 'Qwen2.5-14B-Instruct-1M', 'Qwen2.5-1.5B', 'Qwen2.5-32B', 'Qwen2.5-3B', 'Qwen-2.5 72B', 'Qwen2.5-72B', 'Qwen2.5-7B', 'Qwen2.5-7B-Instruct-1M', 'Qwen2.5-Coder', 'Qwen2.5-Coder-0.5B', 'Qwen2.5-Coder-0.5B-Instruct', 'Qwen2.5-Coder-14B', 'Qwen2.5-Coder-1.5B', 'Qwen2.5-Coder-1.5B-Instruct', 'Qwen2.5-Coder-32B', 'Qwen2.5-Coder-32B-Instruct', 'Qwen2.5-Coder-3B', 'Qwen2.5-Coder-3B-Instruct', 'Qwen2.5-Coder-7B', 'Qwen2.5-Coder-7B-Instruct', 'Qwen2.5-Coder-Instruct']

Official site ↗

Models 🇺🇸 ⚡

From GPT-2 to gpt-oss: Analyzing Architectural Advances and Comparison with Qwen3

OpenAI released gpt-oss-120b and gpt-oss-20b, their first open-weight models since GPT-2. The architecture features Mixture-of-Experts, Grouped Query Attention, RoPE, SwiGLU, and MXFP4 optimization for local inference. Comparisons with GPT-2 and Qwen3 highlight advances in width vs depth trade-offs and attention sinks.

OpenAI

Alibaba/Qwen

GSPO: Scalable Reinforcement Learning for Language Models

Alibaba Qwen proposes Group Sequence Policy Optimization (GSPO), a new RL algorithm that addresses instability in existing methods like GRPO. GSPO uses sequence-level optimization to improve training efficiency, stability, and compatibility with Mixture-of-Experts models, contributing to the performance of Qwen3 models.

Alibaba/Qwen

Alibaba Qwen27.07 · 17:05

Show more ↓