一篇探讨对比学习框架下弱到强泛化的新论文，理论分析和实验验证结合，为AI大模型泛化研究提供新视角。
arXiv:2510.07884v2 Announce Type: replace-cross Abstract: Weak-to-strong generalization provides a promising paradigm for scaling large language model…
扰动分析揭示：大模型在分子领域是否真正具备泛化能力？最新研究带来关键验证。
arXiv:2607.01800v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains bet…
利用CNN训练中的不确定性作为数据增强新策略，为提升模型泛化能力提供创新思路。
arXiv:2509.05238v2 Announce Type: replace-cross Abstract: Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance w…
探究LLM在生成式推荐中的记忆机制，揭示其对推荐系统泛化能力的影响与优化训练策略
arXiv:2606.17276v1 Announce Type: cross Abstract: Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recentl…
用《2001太空漫游》经典台词警示：LLM进入汽车环境面临哪些安全风险？这篇论文系统性评估并给出框架。
arXiv:2606.14327v1 Announce Type: cross Abstract: This paper appraises recent frameworks within AI development to integrate LLMs into control tasks in…
用推理智能体在大型数据集中实现反例引导学习，提升模型鲁棒性与泛化能力。
arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is…
大语言模型在语言任务中称王，但面对符号、空间等非语言环境却表现不佳，研究揭示其本质局限
arXiv:2601.21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to u…
新方法RT-SDGOD专攻实时目标检测在天气、成像变化下的分布偏移难题，从问题定义层面提升泛化能力
arXiv:2606.09367v1 Announce Type: new Abstract: In real-world deployment under strict real-time constraints, weather and imaging variations induce sig…
用游戏取代传统死板训练数据，让LLM在非正式互动中学会更强泛化能力，一篇脑洞大开的预训练新思路。
arXiv:2601.05633v2 Announce Type: replace Abstract: Recent LLMs excel at formal tasks such as mathematical reasoning and code generation, but still st…
一次训练，到处复用：路由注意力机制让上下文学习泛化能力飞跃，ICML 2026亮点论文。
arXiv:2509.22854v2 Announce Type: replace Abstract: Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL be…
首个多模态领域泛化基准，覆盖多种跨模态场景，助力模型稳健性评估。
arXiv:2606.00891v1 Announce Type: new Abstract: Multi-modal Domain Generalization (MMDG) seeks to leverage complementary modalities to enhance model r…
通用LLM智能体TrafficClaw统一物理环境中实现城市交通控制，突破现实部署与泛化瓶颈
arXiv:2604.17456v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown strong capabilities in long-horizon reasoning, tool u…
评估大语言模型语义泛化能力的新方法，利用短语结构区分记忆与真正理解，直击预训练数据偏差挑战。
arXiv:2501.04661v3 Announce Type: replace-cross Abstract: The web-scale of pretraining data has created an important evaluation challenge: to disentan…
测试时训练首次应用于监督因果学习，破解分布外泛化难题的新范式。
arXiv:2605.30015v1 Announce Type: cross Abstract: Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised…
从问题原型中聚类蒸馏出可泛化的优化技能，让算法学会举一反三，大幅提升求解效率。
arXiv:2605.29829v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems fro…
一种通过扰动隐藏表示来增强深度学习模型泛化性的新方法，值得关注。
arXiv:2605.29525v1 Announce Type: new Abstract: Deep neural networks process data through a cascade of representations: input features, hidden activat…
机器人设计试错如何转化为通用技能？这篇论文提出“搜索即记忆”新范式，让零散试验成为可迁移能力。
arXiv:2605.25832v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot des…
零样本图学习新突破：自适应子图去噪结合大语言模型，告别一刀切，显著提升传统GNN泛化能力
arXiv:2603.02938v2 Announce Type: replace-cross Abstract: Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarci…
超声心动图基础模型能否在真实临床场景中保持性能？CardioBench新基准系统评估实验室与临床数据间的泛化差距。
arXiv:2510.00520v2 Announce Type: replace Abstract: Foundation models are reshaping medical imaging, yet their application in echocardiography remains…