医疗影像中选预训练模型总靠试错？本文系统检验了迁移性估计指标在医学场景下的鲁棒性，帮你少走弯路。
arXiv:2608.09999v1 Announce Type: cross Abstract: In transfer learning, the choice of source model largely influences the performance on a target data…
以隐马尔可夫模型为例，揭示从预训练大语言模型中提取可解释算法的前沿方法。
arXiv:2607.22646v1 Announce Type: cross Abstract: Large language models (LLMs) display a striking ability to predict next observations from Hidden Mar…
提出一种原地扩展分词器的方案，解决预训练大模型因后期语言加入导致的 token 效率低下问题，降低延迟与能耗。
arXiv:2607.15232v1 Announce Type: cross Abstract: A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-trainin…
不用标注数据就能生成训练任务，这套元学习新方法让模型学会举一反三更省力。
arXiv:2607.02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled dat…
颠覆知识蒸馏常规认知：预训练表征只有等价类意义，匹配坐标是伪命题
arXiv:2607.03572v1 Announce Type: cross Abstract: Knowledge distillation is usually framed as a choice of what to match in the teacher - its logits, h…
听音辨故障！用CLAP模型从引擎声识别汽车问题，0.93准确率还懂说“不确定”，AI落地超实用。
Article URL: https://github.com/adam-s/car-diagnosis Comments URL: https://news.ycombinator.com/item?id=48749868 Points: 4 # Comments: 0
最新ECCV 2026录用论文，探索如何对预训练视觉Transformer的表示进行可控操作，为视觉AI带来新的灵活性。
arXiv:2604.02327v2 Announce Type: replace Abstract: Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that c…
大规模推荐系统如何更懂用户？TokenMinds用预训练用户令牌和嵌入，解锁更精准的用户理解新思路。
arXiv:2606.25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer fr…
挑战测试时训练新范式：用语言模型自监督的下一词预测信号作为内循环目标，无需额外损失函数。
arXiv:2606.21803v1 Announce Type: new Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed pr…
自动化选择视觉语言模型预训练方案，提升多模态任务效率
arXiv:2502.00241v2 Announce Type: replace-cross Abstract: Incorporating multiple modalities into large language models (LLMs) is a powerful way to enh…
未开微调先知性能？新方法TuneAhead实现提前预测，节省训练成本。
arXiv:2606.17660v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance dep…
ViT也能开口说话？全新生成式语言-图像预训练框架，让视觉与语言深度融合！
arXiv:2605.00809v2 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-traini…
利用预训练模型零样本能力，解决足球场景下训练样本少的单目深度估计难题，方法新颖且实用。
arXiv:2606.10628v1 Announce Type: new Abstract: We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predic…
专为土耳其语优化的BERT模型SindBERT，填补低资源语言NLP空白
arXiv:2510.21364v2 Announce Type: replace Abstract: Transformer models have revolutionized NLP, yet many morphologically rich languages remain underre…
无需额外训练，即可让预训练ViT弹性适配不同计算约束，实现高效推理与精度平衡的创新方法。
arXiv:2510.17700v2 Announce Type: replace Abstract: Vision foundation models achieve remarkable performance but are only available in a limited set of…
覆盖350种语言的单语模型Goldfish，大幅提升低资源语言NLP能力。
arXiv:2408.10441v3 Announce Type: replace Abstract: For many low-resource languages, the only available language models are large multilingual models …
提出奖励引导解码框架，让预训练模型无需参数更新即可激发面向任务行为，补齐评估环节的缺失拼图。
arXiv:2605.28020v1 Announce Type: new Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-t…
提出轻量级选择器捕捉logit shift趋势，高效平衡持续学习中的“可塑-稳定”矛盾
arXiv:2605.27469v1 Announce Type: cross Abstract: Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks…