cs.AI（2025-01-16）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models 提出MoE$^2$框架，优化边缘大语言模型协同推理，提升能效与降低延迟。 large language model
2 CyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education CyberMentor：AI驱动的赛博安全教育平台，解决学生多样化需求 large language model
3 CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding CarMem：通过类别限定增强LLM语音助手的长期记忆 large language model
4 A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy 全面综述负责任的大语言模型：固有风险、恶意使用与缓解策略 large language model
5 A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs 提出基于LLM的动态高精度HRA数据收集方法以解决现有方法不足 large language model
6 Aligning Instruction Tuning with Pre-training 提出AITP方法，通过对齐指令微调与预训练分布，提升大语言模型的泛化能力。 large language model
7 SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs SOP-Agent：利用领域SOP赋能通用AI Agent，提升复杂任务处理能力 large language model
8 LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport LAVCap：基于最优传输的LLM音视频描述框架，有效融合视听信息。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models 综述：基于强化学习的大语言模型推理能力研究进展 reinforcement learning large language model
10 Interpretable Droplet Digital PCR Assay for Trustworthy Molecular Diagnostics 提出I2ddPCR，结合神经网络与GPT-4o，实现可解释的液滴数字PCR自动分析。 predictive model large language model multimodal
11 Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning 提出基于渐进自蒸馏的度量学习方法，提升音视频嵌入学习性能 representation learning distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
12 YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks YETI：基于增强现实任务中多模态AI代理的主动干预 scene understanding egocentric large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Monte Carlo Tree Search with Velocity Obstacles for safe and efficient motion planning in dynamic environments 提出基于速度障碍的速度障碍蒙特卡洛树搜索，用于动态环境中的安全高效运动规划。 model predictive control motion planning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页