谷歌Gemini新模型将AI能力注入实体机器人，理解环境并与人类交互，迈向物理世界智能化。
The latest version of Google DeepMind's AI model includes a significant jump into “physical AGI.” But plopping AI into the real world comes with risks…
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…
理论严谨的曲率引导混合方法，有效缓解多模态大模型微调中的灾难性遗忘。
arXiv:2606.24963v1 Announce Type: cross Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on specialized tasks often leads to catastrophi…
开源实现OpenRouter的混合智能体方案，融合多模型提升回答质量，无需配置即可上手的实用工具。
OpenRouter's fusion is great. I built this for my own deep research queries. Model fusion is useful for tool calls and complex prompts that require co…
提出一种基于高效Gromov-Wasserstein的图对数蒸馏方法，解决异构LLM模型融合中的词汇维度独立问题，提升推理效率与性能。
arXiv:2505.13893v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous ope…
提出Token级LLM协作新方法FusionRoute，突破领域模型融合粒度，让小模型协同超越大模型。
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving st…