LLM领域新突破：神经元感知主动少样本学习，精准挑选标注样本，大幅节省人力成本。
arXiv:2607.02423v1 Announce Type: cross Abstract: Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable …
多模态大模型暗藏隐式少样本学习能力，DCD框架帮你拆解、对比、决策。
arXiv:2607.00125v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images,…
推翻重排序必有益的假设，提出无训练门控机制：只有不确定性高时再重排序，反而提升性能。
arXiv:2606.31087v1 Announce Type: cross Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance. …
对比BERT与少样本LLM在德语气候新闻框架检测中的表现，揭示两种方法的优劣与适用场景。
arXiv:2606.26489v1 Announce Type: new Abstract: News media play a central role in shaping public perceptions of climate change, and whether coverage e…
LLM与GNN协同教学攻克少样本图学习难题，双模型互补超越单打独斗。
arXiv:2606.11583v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media…
大语言模型新策略CEF-Log，结合上下文增强与少样本思维链，精准检测恶意日志并生成法医级解释。
arXiv:2606.08649v1 Announce Type: cross Abstract: Forensic analysis of web server logs demands both accurate detection and human-readable explanations…
首个科米-亚兹瓦语-俄语平行语料库，为LLM在极低资源语言上的零样本/少样本翻译提供系统评估标准。
arXiv:2606.06420v1 Announce Type: new Abstract: We present the first Komi-Yazva--Russian parallel corpus together with an explicit evaluation protocol…
听觉大模型新突破，FSA-GRPO方法教会模型巧用少样本演示，大幅提升推理与适应能力。
arXiv:2606.02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource…
将双曲几何融入ViT，打造紧凑架构，为低数据医学影像带来新思路
arXiv:2606.00906v1 Announce Type: new Abstract: Compact Vision Transformers are attractive for medical imaging in low-data and resource-constrained se…
无需训练即可实现零样本/少样本异常检测，智能体模型AnomalyAgent开辟新范式
arXiv:2605.30140v1 Announce Type: new Abstract: Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot an…
大模型能否零样本或少样本搞定表格分类？这篇新基准LLMTabBench给出了答案。
arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on l…
用图结构记忆经验，破解LLM奖励预测中标签不足的难题，创新方法值得关注。
arXiv:2603.19310v3 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model…
LLM如何构建强大表征，实现小样本高效监督学习？这篇论文给出了系统性答案。
arXiv:2603.11679v3 Announce Type: replace Abstract: As real-world datasets become more complex and heterogeneous, supervised learning is often bottlen…
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…
用随机少样本指导提升RLVR在困难问题上的样本效率，大模型训练新思路。
arXiv:2605.15012v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved great success in developing Large…