Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textu…

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal deco…

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…

A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers prov…

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that…

2024 年诺贝尔物理学奖授予 John Hopfield 与 Geoffrey Hinton，表彰其利用人工神经网络实现机器学习的基础性发现；化学奖同时颁给蛋白质计算先驱。

o1 系列通过强化学习训练模型'先思考再回答'，在数学、代码与科学推理上大幅跃升，开创了推理时扩展（Test-time Compute）的新 Scaling 维度。

Google DeepMind 与 Isomorphic Labs 发布 AlphaFold 3，首次将预测范围从蛋白质结构扩展到 DNA、RNA、配体等全部生命分子及其相互作用。