PAPER·2 days agoCoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action ModelarXiv
PAPER·2 days agoReasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning ModelsHugging Face Papers
PAPER·3 days agoFrom Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic SearchHugging Face Papers
TECH·July 20, 2026Alibaba Previews Qwen3.8-Max, a 2.4 Trillion-Parameter Multimodal Model, Days After Moonshot’s Kimi K3 Open-Weight LaunchMarkTechPost
CODING·June 2, 2026Qwen3-Coder-Next review 2026: 80B params, 3B active, and the cheapest credible coding agent APIDev.to