全新循环语言模型Ouro，开启潜在推理新范式，无需显式文本思考也能扩展推理能力。
arXiv:2510.25741v5 Announce Type: replace Abstract: Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-though…
首个专为医学图像理解设计的思维链基准测试，揭示多模态大模型推理缺陷！
arXiv:2601.08758v4 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by …
人机协同干预LLM推理过程，可视化思维链让AI思考透明可控，复杂推理任务更可靠。
arXiv:2509.01412v3 Announce Type: replace Abstract: Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the p…
揭秘思维链训练如何提升大模型智能体性能，实证分析增益落点与机制
arXiv:2606.26935v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown tha…
微软VP Scott Hanselman亲自点赞的开源项目，用本地AI让你用自然语言搜索视频内容
I've been working on Edit Mind for a while now, and today I noticed Scott Hanselman starred it. He's VP of Developer Community at Microsoft. My projec…
探索扩散模型中内生思维链推理新机制，突破MLLM文本编码器的推理瓶颈。
arXiv:2603.12252v4 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusio…
苹果Vision Pro头显助力迪士尼改造EPCOT经典项目，为美国250周年献礼，科技与娱乐的梦幻联动！
IT之家 6 月 13 日消息，科技媒体 Appleinsider 昨日（6 月 12 日）发布博文，报道称迪士尼为迎接美国建国 250 周年，借助苹果 Vision Pro 头显，改造 EPCOT 经典飞行项目 Soarin， 并将其更名为 Soarin' Across America，带领游客飞…
仅用两个推理样本即可实现LLM自一致性？CoT+PoT集成方案，大幅提升推理效率的新突破。
arXiv:2604.17433v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large l…
HybridThinker用压缩记忆与瞬态思考步骤，让大模型链式推理更高效省力。
arXiv:2606.03768v1 Announce Type: new Abstract: Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and m…
AI编码代理Devin创始人直言：从不认为AI应取代人类，而是强调人机协作。
Cognition makes Devin, the first and arguably most successful AI coding agent. But famed coder Wu says it isn't designed to supplant human programmers…
揭秘推理模型“表演性思维链”：模型已确信答案却不暴露内部信念，引发对AI推理真实性的深层思考。
arXiv:2603.05488v4 Announce Type: replace-cross Abstract: We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a mode…
CoT蒸馏提升医学问答准确性，却导致推理步骤质量下降，揭示性能与可解释性间的深层矛盾。
arXiv:2605.28301v1 Announce Type: new Abstract: Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but…
评估多模态大模型操作中心链式思维推理能力的新基准，强调接地与可验证性。
arXiv:2605.19559v1 Announce Type: new Abstract: The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egoce…
这篇论文提出了模块化后训练框架，将视觉语言模型适配到自动驾驶安全关键事件的异常检测，融合元数据、LLM描述与VQA及CoT推理，提升准确性。
arXiv:2603.18178v2 Announce Type: replace Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-cr…
OpenAI研究发现推理模型难以自主控制思维链，这反而强化了可监控性，为AI安全提供新思路。
OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeg…
发现CoT推理长度并非越长越好，提出Insight Replay新方法解决准确率下降问题
arXiv:2605.14457v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large l…
逆向工程Claude AI吉祥物动画，用纯SVG矩形和GSAP在React中复现。从帧捕捉到补间动画，拆解每个时序和缓动，技术控不可错过。
How I rebuilt Claude AI’s mascot animations from scratch, frame by frame, purely in code using SVG and GSAP.
大模型在纵向电子病历推理中常因缺乏精细化统计导致幻觉，COTCAgent通过概率化思维链补全实现预防性咨询，为临床决策支持提供新范式。
arXiv:2605.15016v1 Announce Type: cross Abstract: As large language models empower healthcare, intelligent clinical decision support has developed rap…