理论揭示：判别模型的条件分布等价性如何约束内部表示的唯一性，为理解模型表征相似性提供新视角
arXiv:2602.15438v3 Announce Type: replace-cross Abstract: For a broad family of discriminative models that includes autoregressive language models, id…
一篇证明域迁移通过单一对齐可变得可识别的理论论文，解决内容混淆难题
arXiv:2605.17918v1 Announce Type: new Abstract: Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image…
提出一种可识别token对应方法用于世界模型，强化智能体对环境结构的泛化理解
arXiv:2605.16457v1 Announce Type: new Abstract: Transformer-based world models have shown strong performance in visual reinforcement learning, but oft…