1
Post-Training Augmentation Invariance
提出训练后的数据增强不变性方法，提升模型泛化能力，不依赖额外训练成本。
arXiv:2505.11702v3 Announce Type: replace Abstract: This work develops a framework for post-training augmentation invariance, in which our goal is to …
2
Can Large Language Models Generalize Procedures Across Representations?
揭秘LLM能否在不同任务表示间泛化过程，ICML 2026收录的前沿研究
arXiv:2602.03542v2 Announce Type: replace Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such a…
3
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
提出后门遗忘泛化新路径，让大模型摆脱未知触发器威胁，捍卫LLM安全防线。
arXiv:2606.03785v1 Announce Type: new Abstract: Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can gene…
4
Evaluating Real-World Generalizability of Algorithm Selection Models
评估算法选择模型在真实场景中的泛化能力，揭示理论与实际性能差距的关键研究
arXiv:2606.02016v1 Announce Type: new Abstract: Algorithm Selection (AS) aims to automatically identify the most suitable optimization algorithm for a…
5
Discrepancy Minimization Improves Cross-Hospital Robustness in Digital Pathology
新方法通过差异最小化提升数字病理模型在不同医院数据上的鲁棒性，解决领域偏移难题。
arXiv:2605.25175v1 Announce Type: new Abstract: Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifi…
6
Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure
揭秘冻结视觉模型训练中噪声数据的陷阱：小损失策略为何失效？跨数据集基准带来新洞察。
arXiv:2605.22591v1 Announce Type: new Abstract: Frozen Vision Foundation Models (VFMs) with lightweight classification heads are increasingly used in …
7
ARROW: Augmented Replay for RObust World models
提出ARROW增强回放框架，显著提升世界模型在分布外场景的鲁棒性。
arXiv:2603.11395v2 Announce Type: replace Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previousl…