cs.AI（2024-02-06）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning	提出知识增强学习以提升众筹成功的跨模态一致性	multimodal
2	Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction	提出多模态序列再现框架以比较人类与大型语言模型的抽象能力	large language model multimodal
3	Progress and Opportunities of Foundation Models in Bioinformatics	综述基础模型在生物信息学中的应用与挑战	foundation model multimodal
4	SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark	提出SceMQA基准以解决科学多模态问答评估不足问题	large language model multimodal
5	A call for embodied AI	提出具身人工智能以推动通用人工智能的发展	embodied AI large language model
6	Self-Discover: Large Language Models Self-Compose Reasoning Structures	提出SELF-DISCOVER以解决复杂推理问题	large language model chain-of-thought
7	Embedding Large Language Models into Extended Reality: Opportunities and Challenges for Inclusion, Engagement, and Privacy	将大型语言模型嵌入扩展现实以促进包容性与参与感	large language model
8	QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model	提出QuantAgent以解决量化投资领域的知识整合问题	large language model
9	Limits of Large Language Models in Debating Humans	探讨大型语言模型在与人类辩论中的局限性	large language model
10	MolTC: Towards Molecular Relational Modeling In Language Models	提出MolTC以解决分子关系建模中的信息利用不足问题	large language model chain-of-thought	✅
11	Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors	利用视频语言模型作为行为评估者以捕捉不良代理行为	embodied AI	✅
12	Monitoring the evolution of antisemitic discourse on extremist social media using BERT	提出无监督在线机器学习方法监测极端社交媒体上的反犹太主义话语演变	large language model
13	Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy	提出三元框架以解决AI科学家安全性问题	large language model
14	RevOrder: A Novel Method for Enhanced Arithmetic in Language Models	提出RevOrder以提升语言模型的算术运算能力	large language model
15	Can Generative Agents Predict Emotion?	提出一种新架构以提升生成代理的情感预测能力	large language model
16	Multi-line AI-assisted Code Authoring	提出多行AI辅助代码编写工具以提升开发者效率	large language model
17	LLM Agents can Autonomously Hack Websites	LLM代理能够自主进行网站黑客攻击	large language model
18	Position: Stop Making Unscientific AGI Performance Claims	提出警示以避免对AGI性能的非科学性声明	large language model
19	CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimation	提出CADReN以解决跨图节点重要性估计问题	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	🔗	⭐
20	The Essential Role of Causality in Foundation World Models for Embodied AI	提出因果性在基础世界模型中的重要性以解决具身AI问题	world model world models embodied AI
21	Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction	提出R2-Play以增强决策变换器的多任务能力	reinforcement learning decision transformer generalist agent
22	Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning	提出联合内在动机方法以解决多智能体深度强化学习中的稀疏奖励问题	reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents	提出逻辑规范引导的动态任务采样以解决强化学习样本复杂性问题	manipulation reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页