Tag
Midjourney is testing a new 'Thinking Mode' for image generation on its Alpha website, claiming improvements in prompt accuracy, typography, and coherence, and inviting user feedback via Discord.
该论文提出"思考惯性"（Thinking Inertia）现象：即使明确指示LLM不要思考，模型仍会持续进行显式推理，且在开放式问题中更严重。作者提出三个衡量"不思考"行为的指标，并在六个模型和多种任务上评估，指出停止推理无法仅靠设置或指令保证。
This article identifies and provides fixes for three bugs encountered when serving the MiMo-V2.6-Flash model with vLLM, including empty responses in streaming mode, reasoning loss in tool loops, and a hidden token output cap.
Benchmarks on a MacBook Pro M5 Max show that disabling thinking mode in Qwen3.8-27B severely degrades output quality, while xhigh thinking mode uses 5.5x more tokens and runs 6x longer.
This paper empirically characterizes uncertainty in thinking-mode visual language models, demonstrating that the thinking chain entropy is a more reliable signal for hallucination detection than conventional answer token distribution, which collapses in these models.
The Gemma 4 Technical Report introduces a new generation of open-weight, natively multimodal language models with diverse architectures, enhanced reasoning capabilities, and improved performance across tasks. The models range from 2.3B to 31B parameters and feature a thinking mode for generating reasoning traces.
Xiaokang Chen shares two prompts, 'Think with Grounding' and 'Think with Pointing', to improve model performance in domains like counting in Thinking mode. These prompts use bounding boxes and points to make the MLLM's reasoning more human-like.
ChatGPT Images 2.0 in "Thinking" mode can turn 1,000-word prompts or 70-page PDFs into ready-to-use infographics, slide decks, and academic posters without manual editing.