像素级多模态大模型新训练范式，掩码—文本一致性循环让模型精修细节，值得细读。
arXiv:2608.01354v1 Announce Type: new Abstract: Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region S…
把物理规律嵌入自监督增强，让科学成像模型学到的特征更可解释、更稳健，是AI4Science方向值得关注的新思路。
arXiv:2607.28868v1 Announce Type: new Abstract: Data augmentations define the invariances learned by self-supervised learning (SSL). Standard augmenta…
不再丢弃大模型输出语义，用自监督生成式嵌入让LLM直接产出向量，重新定义嵌入学习。
arXiv:2603.10913v3 Announce Type: replace Abstract: Fine-tuning LLM-based text embedders via contrastive learning maps inputs and outputs into a new r…
提出一种自监督语义扩散方法，让技能像参数一样被训练与迁移，为AI技能学习开辟新思路。
arXiv:2607.27557v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable general instruction-following capabilities, …
通过合成指令数据扩展预训练规模，突破传统监督训练数据瓶颈的新方法
arXiv:2601.22146v2 Announce Type: replace-cross Abstract: Due to limited supervised training data, large language models (LLMs) are typically pre-trai…
自我引导的测试时训练，专治长上下文LLM的准确率退化难题。
arXiv:2607.09415v1 Announce Type: cross Abstract: Long-context processing has become increasingly important for large language models (LLMs), but simp…
面向视网膜眼底图像的可解释基础模型新探索，直击医疗AI透明性痛点，值得深入研究。
arXiv:2603.18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unl…
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…
从海量网络数据中精准提取有效信号，创新医疗编码器预训练的数据配方，为专业领域模型训练提供新思路。
arXiv:2606.22079v1 Announce Type: cross Abstract: Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encode…
世界模型赋能潜在动作预训练，探索更高效的智能体学习范式。
arXiv:2509.18428v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have gained popularity for learning robotic manipulation…
自监督跨平面方法恢复各向同性体积图像，适用于多种成像模态，提升数据质量与下游分析精度。
arXiv:2606.15967v1 Announce Type: new Abstract: Anisotropic volumetric acquisitions are common in clinical MRI and volume electron microscopy (vEM), w…
自我监督概念发现新方法，用偏好学习破解可解释性与可扩展性的两难困境。
arXiv:2606.14586v1 Announce Type: new Abstract: Current representation learning paradigms force a fundamental compromise: self-supervised methods scal…
视频自监督学习新突破，V-JEPA 2.1巧妙解锁密集特征，大幅提升视频理解性能。
arXiv:2603.14482v3 Announce Type: replace Abstract: We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual re…
用程序化世界模型让LLM智能体在虚拟环境中自我进化，突破静态数据限制。
arXiv:2606.12780v1 Announce Type: cross Abstract: Self-evolving agents are expected to improve through interaction without external supervision, but t…
AI+医学影像新突破：自监督基础模型精准分析3D脑部MRI，助力疾病诊断
arXiv:2606.13315v1 Announce Type: new Abstract: Self-supervised foundation models have shown strong promise in medical imaging. However, existing MRI …
突破医学影像数据瓶颈，通用3D自监督框架助力模型泛化
arXiv:2501.11755v2 Announce Type: replace-cross Abstract: Current self-supervised learning methods for 3D medical imaging rely on simple pretext formu…
自监督数据策展如何保障基础模型鲁棒性？最新研究揭示安全性与可扩展性的关键路径
arXiv:2606.09511v1 Announce Type: new Abstract: Self-supervised data curation provides a pathway to scaling and improving the generalization capabilit…
自监督掩码学习突破标注瓶颈，医疗等场景下用无标签文本提升分类性能。
arXiv:2606.09466v1 Announce Type: new Abstract: Classification tasks require annotated data, which can often be expensive, time-consuming, or even unf…
JEPA预训练方法应用于无线通信领域，探索基础模型的新范式
arXiv:2606.06373v1 Announce Type: cross Abstract: Wireless foundation models have emerged as a promising alternative to building separate models for e…