多模态大模型遗忘难题新解法，POPS用提示优化参数抖动高效恢复已遗忘知识。
arXiv:2607.06649v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tas…
用概率提示应对持续学习中的灾难性遗忘，ECCV 2026 新方法值得关注
arXiv:2607.04711v1 Announce Type: new Abstract: Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint su…
用对抗提示调优与生成破解单域泛化难题，CVPR 2025新思路不容错过。
arXiv:2606.21736v1 Announce Type: new Abstract: Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unse…
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…
EMNLP 2025新研究：用多模态大模型提示与个性化偏好对齐，提升封面图像生成质量。
arXiv:2605.27374v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new…
仅用LLM和对比估计提示就能预测点互信息，PromptNCE方法简洁高效，值得关注。
arXiv:2605.21776v1 Announce Type: new Abstract: Estimating mutual information from text usually requires training a task-specific critic, which limits…
提出查询感知的可学习图池化标记作为大语言模型提示，增强图结构数据处理能力
arXiv:2501.17549v2 Announce Type: replace Abstract: Graph-structured data plays a vital role in numerous domains, such as social networks, citation ne…
提出中性参考提示方法，直击视觉语言模型基类-新类权衡这一核心难题，为迁移学习提供全新解决思路。
arXiv:2605.15615v1 Announce Type: cross Abstract: Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-…