一作质问持续学习何时真正需要「学习」，揭示任务无关场景下模型无需更新即可泛化，引发对学习本质的再思考。
arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable mo…
用元学习隐式平衡成本与性能，自动选择最佳LLM，降本增效新范式。
arXiv:2606.06178v1 Announce Type: cross Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful m…
AI Agents不再止于单次交互，探索在实地实验中持续学习的潜力与方法。
arXiv:2606.02458v1 Announce Type: new Abstract: Organizations routinely run experiments for A/B testing, yet the data generated from one experiment is…
将信任区域优化与元学习思想巧妙融合，提出持续学习新范式，在防止灾难性遗忘的同时实现高效知识迁移，实验数据丰富。
arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standar…
MetaSICL提出元语音上下文学习方法，让听觉大模型更灵活适配新任务，无需大量微调数据。
arXiv:2601.18904v2 Announce Type: replace-cross Abstract: Auditory Large Language Models (LLMs) have demonstrated strong performance across a wide ran…
提出自进化元认知策略优化方法，让LLM红队测试更智能高效地发现安全漏洞。
arXiv:2605.10067v3 Announce Type: replace-cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). Whil…
元学习在多语言口语单词分类中优于监督学习，新方法初探语言无关性
arXiv:2605.13084v2 Announce Type: replace-cross Abstract: Meta-learning has been shown to have better performance than supervised learning for few-sho…
OpenAI提出简单高效的元学习算法Reptile，通过重复采样任务和SGD更新，实现快速适应新任务
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on i…
OpenAI 揭秘一阶元学习算法，深入分析 MAML 梯度近似的理论基础与优化技巧
用元学习+贝叶斯推断搞定复杂系统根因分析，无需完整因果图即可高效定位故障。
arXiv:2605.08786v2 Announce Type: replace Abstract: Root cause analysis (RCA) in complex systems is challenging due to error propagation across multip…