1
Weak-to-Strong On-Policy Distillation
挑战传统认知：弱教师如何高效指导强学生？这项研究提出了弱到强的在线策略蒸馏新范式。
arXiv:2607.26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on th…
2
UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging
无监督域对齐新方法，跨模态迁移助力医学影像分析。
arXiv:2607.21546v1 Announce Type: new Abstract: Multimodal based approaches often outperform single modality approaches in downstream tasks as the dif…
3
MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
论文提出MAGIK框架，通过想象力实现类比目标映射的知识迁移，为机器人学习和AI泛化开辟新路径。
arXiv:2506.01623v4 Announce Type: replace Abstract: Humans excel at analogical reasoning - applying knowledge from one task to a related one with mini…
4
Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers
研究用冻结LLM知识做文生图，Mixture-of-Transformers架构实现知识迁移，只靠标准图文对训练。
arXiv:2606.29013v1 Announce Type: new Abstract: Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an importa…
5
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
大模型如何给视觉模型当老师？ICML 2026探讨细粒度知识跨模态迁移，让AI理解更精准。
arXiv:2606.27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pr…
6
Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
大模型结合记忆引导树搜索与跨分支知识迁移，自动合成组合优化求解器，突破传统方法瓶颈。
arXiv:2605.17539v2 Announce Type: replace Abstract: Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where inf…
7
TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
提出TiTok方法，通过对比学习转移Token级知识，让LoRA参数可在不同骨干模型间移植。
arXiv:2510.04682v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely applied in real world scenarios, yet fine-tuning the…