庞玉栋博客
//

机器学习

47 篇 · 资讯流
  2. arXiv cs.RO（机器人）

    JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents

    Embodied agents must translate multimodal observations and user requests into executable actions while adapting to produ

    原文 ↗
  4. arXiv cs.DB（数据库）

    Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

    Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet eviden

    原文 ↗
  6. arXiv cs.DC（分布式并行）

    DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching

    Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Conseq

    原文 ↗
  7. arXiv cs.DC（分布式并行）

    Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell

    Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evide

    原文 ↗
  8. arXiv cs.LG（机器学习）

    Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs

    Clinical questions often depend on linking a patient's multimodal evidence to external biomedical knowledge, yet existin

    原文 ↗
  10. arXiv cs.DC（分布式并行）

    D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?

    GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but ru

    原文 ↗
  11. arXiv cs.AI（人工智能）

    CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning

    Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-trainin

    原文 ↗
  13. arXiv cs.RO（机器人）

    Managing Context and Communication in Distributed Agentic UAV Swarms

    Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reason

    原文 ↗
  14. arXiv cs.DB（数据库）

    STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling

    Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, an

    原文 ↗
  15. arXiv cs.DC（分布式并行）

    Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware

    Hardware-operable failures (HOFs) interrupt large language model (LLM) training but permit recovery on the same hardware

    原文 ↗