用最优传输理论动态放置专家副本，从拓扑感知角度根治MoE训练负载失衡，值得算法工程师细读。
Article URL: https://arxiv.org/abs/2608.03676 Comments URL: https://news.ycombinator.com/item?id=49330030 Points: 1 # Comments: 0
图拓扑感知+软提示，攻克不完整知识图谱推理难题，学术干货满满。
arXiv:2604.12503v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but rem…
引入拓扑感知与LLM的自动化特征工程新方法，提升特征质量与模型性能。
arXiv:2607.23286v1 Announce Type: cross Abstract: Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program…
跨房间3D场景理解遇上拓扑感知多模态大模型，突破单一空间局限，推动空间智能新边界。
arXiv:2607.06534v1 Announce Type: new Abstract: Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in si…
对比评估与拓扑感知结合，让LLM智能体能自主进化技能库，复杂任务适应性显著提升。
arXiv:2606.13317v1 Announce Type: new Abstract: Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill doc…
提出拓扑感知层剪枝方法，有效降低大视觉语言模型的计算与内存成本，助力高效部署。
arXiv:2604.16502v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in natural language understandi…
拓扑感知多智能体框架自进化解决微服务根因分析，应对噪声、级联故障和拓扑漂移三大挑战
arXiv:2605.15611v1 Announce Type: new Abstract: Root cause analysis (RCA) in microservices is challenging due to (i) noisy and heterogeneous multimoda…