1
一个模型场景通吃！它石智航AWE3.7的泛化能力有点狠
从工厂一路干到家庭
2
GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
提出泛化感知的结构化剪枝方法，在压缩大模型规模的同时保持泛化能力，兼顾效率与性能。
arXiv:2603.13418v2 Announce Type: replace-cross Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its perfo…
3
LLM generation novelty through the lens of semantic similarity
从语义相似度视角衡量LLM生成新颖性，突破词汇重叠局限，更精准评估泛化能力。
arXiv:2510.27313v3 Announce Type: replace-cross Abstract: Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it ag…
4
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
利用基础模型的强泛化能力，无需源数据即可高效适应目标域，摆脱传统调阈值和聚类等繁琐操作。
arXiv:2607.17653v1 Announce Type: cross Abstract: Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled…
5
Contrastive Weak-to-strong Generalization
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…
6
Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning
扩散模型技术跨界3D交互，让机器人理解开放世界物体操作方式，知识泛化能力大升级。
arXiv:2508.01651v2 Announce Type: replace Abstract: 3D affordance grounding aims to understand how diverse objects can be manipulated, making it a cor…
7
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
多模态大模型在线编辑遇泛化难题？这项研究提出递归编辑新思路，让知识修正更精准稳定。
arXiv:2607.01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual correction…
8
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
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…
9
Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
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…
10
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
大模型并非万能学习器，这篇论文用实证揭示提示条件模型的性能边界，适合关注AI能力上限的读者。
arXiv:2606.23668v1 Announce Type: new Abstract: Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving ar…
11
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
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…
12
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
提出集体技能树搜索方法，让大模型智能体协同构建结构化技能库，显著提升任务泛化能力与自主决策效率。
arXiv:2606.16774v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks…
13
I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts
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…
14
Counterexample Guided Learning in the Large using Reasoning Agents
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…
15
Language-based Trial and Error Falls Behind in the Era of Experience
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…
16
RT-SDGOD: Real-Time Single-Domain Generalized Object Detection
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…
17
GIFT: Games as Informal Training for Generalizable LLMs
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…
18
Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention
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…
19
MMDG-Bench: A Benchmark for Multimodal Domain Generalization
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…
20
TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control
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…