view article Article TutorMoments: Do AI tutors know when to help and when to hold back? allenai β’ Aug 7 β’ 31
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency Paper β’ 2506.08343 β’ Published Jun 10, 2025 β’ 54
view post Post 1836 Qwen is on fire this week π₯They just released Qwen3-MT π a translation model supports 92 languages. Demo is available on the hub. Qwen/Qwen3-MT-Demoβ¨ Highly Customizable: Supports custom terms, domain prompts, and translation memory for accurate, context-aware results.β¨ Fast and affordable: $0.5 per million tokens. See translation π₯ 6 6 + Reply