1
2
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
跨域复用网页操作技能，用可迁移交互模式拓展智能体能力边界
arXiv:2606.17645v1 Announce Type: new Abstract: Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads…
3
Transfer Learning for FHIR Questionnaire Terminology Binding
用迁移学习精准匹配FHIR问卷项与LOINC代码，解决医疗互操作性中的编码难题
arXiv:2606.15449v1 Announce Type: cross Abstract: Electronic prior authorization workflows require FHIR Questionnaire items to carry LOINC codes, yet …
4
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
提出推理时对齐迁移新方法，跨词汇混合logit无需额外训练即可转移对齐能力，为大模型高效部署提供新思路。
arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comp…
5
Muon Learns More Robust and Transferable Features than Adam
Muon优化器比Adam学习到更鲁棒和可迁移的特征，为深度学习训练提供新选择。
arXiv:2606.09658v1 Announce Type: new Abstract: Muon has recently emerged as a state-of-the-art optimizer for pretraining Large Language Models (LLMs)…
6
Causal Transfer in Medical Image Analysis
因果迁移学习如何提升医学图像分析的鲁棒性和可解释性？这篇论文给出系统性探索。
arXiv:2603.24388v2 Announce Type: replace Abstract: Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or i…
7
RAM: Reachability Across Morphologies
提出一种跨形态可达性方法，让不同结构机器人共享运动知识，推动通用机器人技能迁移。
arXiv:2606.09108v1 Announce Type: cross Abstract: Many stages of the robotic lifecycle, from morphology synthesis to operation, rely fundamentally on …
8
Mining Useful General Data for Low-Resource Domain Adaptation
利用通用数据解决低资源领域大模型适配难题，为领域迁移提供新思路
arXiv:2511.07380v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarc…
9
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
从智能体轨迹中提炼可迁移技能，提出一种基于局部经验的知识蒸馏新方法，助力通用智能体学习。
arXiv:2603.25158v5 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually author…
10
DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer
提出DuDi双信号蒸馏框架，用跨语言口头器提升多语言NLP模型的迁移效率
arXiv:2606.04694v1 Announce Type: new Abstract: Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade s…
11
LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models
大语言模型为跨语言主题建模注入新动力，提出LLM-XTM框架有效提升多语言主题一致性与迁移能力。
arXiv:2605.03299v2 Announce Type: replace Abstract: Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet exi…
12
Domain Adaptation with a Single Vision-Language Embedding
利用单一视觉语言嵌入实现高效域适应，方法简洁且效果显著。
arXiv:2410.21361v2 Announce Type: replace-cross Abstract: Domain adaptation has been extensively investigated in computer vision but still requires ac…
13
PromptEmbedder:: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
双LLM软提示新框架实现高效文本嵌入，迁移性更强、计算成本更低，值得NLP研究者关注
arXiv:2605.28066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current ad…
14
Trust Region Continual Learning as an Implicit Meta-Learner
将信任区域优化与元学习思想巧妙融合，提出持续学习新范式，在防止灾难性遗忘的同时实现高效知识迁移，实验数据丰富。
arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standar…
15
One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
提出一步贝尔曼对齐方法，理论上证明能实现高效的在线强化学习迁移。
arXiv:2601.21924v2 Announce Type: replace Abstract: We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where …
16
Leveraging pretrained RGB denoisers for hyperspectral image restoration
不用重新训练，直接调用预训练RGB去噪器就能修复高光谱图像，省时省成本
arXiv:2605.24769v1 Announce Type: cross Abstract: Hyperspectral image restoration faces several challenges, including limited training data, strong se…
17
Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
冻结深层、训练浅层，可解释的层分配策略让持续预训练更高效
arXiv:2605.11416v2 Announce Type: replace Abstract: Selective layer-wise updates are essential for low-cost continued pre-training of Large Language M…
18
Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning
跨领域离线强化学习新方法，用对齐贝尔曼备份解决域间转移难题。
arXiv:2605.22376v1 Announce Type: new Abstract: Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain …
19
Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains
多智能体LLM跨域协作新突破，可迁移拓扑先验让协作更高效。
arXiv:2605.17359v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have shown strong potential for complex reasoning…
20
Transfer Learning for Customized Car Racing Environments
用迁移学习攻克定制赛车环境训练难题，提升模型适应性与效率。
arXiv:2605.17928v1 Announce Type: cross Abstract: Transfer Learning, a technique where a model/agent can use the knowledge/expertise that it gained fr…