多模态大模型遗忘新思路，模型合并实现持续去学习，破解隐私与安全难题。
arXiv:2608.04548v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) unlearning methods have been proposed to remove private, sens…
KDD'26前沿论文：锐度感知模型合并结合显著性恢复，突破LLM跨域顺序推荐性能瓶颈。
arXiv:2607.25366v1 Announce Type: cross Abstract: LLM-based Cross-Domain Sequential Recommendation (CDSR) leverages LLMs to enhance target performance…
针对开源LLM模型合并后水印失效的痛点，提出新型耐久水印方案，保障AI内容溯源安全。
arXiv:2607.20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace…
从加权模型平均视角重新审视异构LLM合并，提供理论分析与新方法，适合模型集成研究者。
arXiv:2607.18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted a…
专家训练时长如何影响LLM模型合并效果？这篇ICML 2026 workshop论文揭示关键发现。
arXiv:2607.11997v1 Announce Type: new Abstract: Multi-task model merging combines separately trained expert models into a single model that handles al…
ICML 2026提出“多轮模型合并”新范式，用损失间隙平衡突破后处理合并瓶颈。
arXiv:2606.16501v1 Announce Type: new Abstract: Model merging has become a practical post-training strategy for building a single multi-task large lan…
移除系统提示后，里约大模型自曝真实身份——原来是 Nex-N2_pro 与 Qwen 的合并产物，并非“本土”原创。
Article URL: https://github.com/nex-agi/Nex-N2/issues/4 Comments URL: https://news.ycombinator.com/item?id=48528371 Points: 196 # Comments: 113
针对LLM模型合并的供应链漏洞，提出统一鲁棒的攻击方法RogueMerge，揭示第三方任务向量的安全威胁。
arXiv:2606.03344v1 Announce Type: cross Abstract: Model merging composes specialized capabilities into a single LLM by aggregating task vectors source…
揭示模型合并对MoE路由的破坏机制，提出无需训练的高效校准方案，为混合专家模型优化提供新思路。
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multipl…
生物多模态大模型合并新方法，利用嵌入空间信号实现跨模态融合，推动科学发现。
arXiv:2603.14405v2 Announce Type: replace Abstract: Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for…
从几何视角理解损失景观中的模型合并，CVPR最新研究揭示关键规律。
arXiv:2605.26693v1 Announce Type: cross Abstract: Model merging offers a promising avenue for knowledge integration and parallel development without r…
新方法追踪模型合并中的秩1子空间，为语言模型预训练提速增效。
arXiv:2605.26484v1 Announce Type: new Abstract: Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet it…
一键直达差分隐私模型融合最新研究，arXiv免费提供全文下载与引用管理，助你紧跟学术前沿。
arXiv:2604.20985v2 Announce Type: replace Abstract: In machine learning, privacy requirements at inference or deployment time often evolve due to chan…
提出通过模型合并解耦数据混合搜索与训练，高效扩展LLM预训练的数据配比策略。
arXiv:2602.00747v2 Announce Type: replace-cross Abstract: Determining an effective data mixture is a key factor in Large Language Model (LLM) pre-trai…