cs.AI（2024-02-27）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web 提出OmniACT数据集以推动多模态自主代理在桌面和网络任务中的应用 large language model multimodal visual grounding
2 Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning 提出CLIPS以解决模糊指令跟随问题 large language model multimodal instruction following
3 On the Societal Impact of Open Foundation Models 提出开放基础模型的风险评估框架以支持社会影响评估 foundation model
4 SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition 提出SongComposer以解决歌曲创作中的歌词与旋律生成问题 large language model
5 BiVRec: Bidirectional View-based Multimodal Sequential Recommendation 提出BiVRec以解决多模态序列推荐中的信息利用不足问题 multimodal
6 Large Language Model for Participatory Urban Planning 提出基于大语言模型的多代理协作框架以优化参与式城市规划 large language model
7 Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas 综述多智能体与人机合作以解决社会困境问题 large language model
8 Case-Based or Rule-Based: How Do Transformers Do the Math? 提出规则跟随微调技术以解决变换器数学推理问题 large language model
9 Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization 提出Agent-Pro以解决LLM在动态场景中的学习与演化问题 large language model
10 Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides 提出Nissist以解决云服务事件管理中的复杂问题 large language model
11 Insights from the Usage of the Ansible Lightspeed Code Completion Service 提出Ansible Lightspeed以提升IT自动化领域代码生成效率 large language model
12 A Neural Rewriting System to Solve Algorithmic Problems 提出神经重写系统以解决算法问题 large language model
13 Determinants of LLM-assisted Decision-Making 提出LLM辅助决策的影响因素分析框架 large language model
14 Benchmarking Data Science Agents 提出DSEval评估范式以提升数据科学代理的性能 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization 提出行业级深度强化学习框架以优化投资组合 sim-to-real reinforcement learning deep reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页