cs.AI（2024-07-31）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱四：生成式动作 (Generative Motion) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training	RagVL：通过知识增强重排序和噪声注入训练，提升多模态检索增强生成效果	large language model multimodal	✅
2	A Taxonomy of Stereotype Content in Large Language Models	提出大语言模型刻板印象内容分类法以解决偏见问题	large language model
3	KemenkeuGPT: Leveraging a Large Language Model on Indonesia's Government Financial Data and Regulations to Enhance Decision Making	KemenkeuGPT：利用大语言模型增强印尼政府金融数据决策	large language model
4	MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts	MoMa：通过模态感知专家混合加速多模态早期融合预训练。	multimodal
5	Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs	提出SolverLearner框架，用于评估LLM的归纳推理能力并发现其演绎推理短板	large language model
6	CEAR: Automatic construction of a knowledge graph of chemical entities and roles from scientific literature	提出CEAR方法，从科学文献自动构建化学实体与角色知识图谱。	large language model
7	TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities	提出TransferTOD，一个具备迁移能力的通用中文多领域任务型对话系统。	large language model	✅
8	A Performance Study of LLM-Generated Code on Leetcode	评估LLM生成代码在Leetcode上的性能，发现其效率可与人类编写代码媲美甚至更优	large language model
9	Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation	欺骗性AI解释比诚实AI更具说服力，并能放大对错误信息的信任	large language model
10	MetaOpenFOAM: an LLM-based multi-agent framework for CFD	MetaOpenFOAM：基于LLM的多智能体CFD框架，实现自然语言驱动的自动化仿真。	large language model
11	SAKR: Enhancing Retrieval-Augmented Generation via Streaming Algorithm and K-Means Clustering	SAKR：通过流式算法和K-Means聚类增强检索增强生成效果	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Recording First-person Experiences to Build a New Type of Foundation Model	提出一种基于第一人称体验记录的新型基础模型构建方法，旨在更精确地复现人类行为	reinforcement learning foundation model
13	A New Type of Foundation Model Based on Recordings of People's Emotions and Physiology	提出基于个体情绪和生理记录的第一人称视角基础模型	reinforcement learning foundation model
14	Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks	提出NaSA-TD3，利用内在激励解决图像强化学习中复杂机器人任务的探索问题。	reinforcement learning deep reinforcement learning TD3
15	CREW: Facilitating Human-AI Teaming Research	CREW：用于人机协作研究的平台，支持实时决策场景和多学科协作。	reinforcement learning multimodal
16	Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates	提出基于期望行为功利主义义务逻辑的强化学习伦理约束验证与策略更新方法	reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models	提出一种可视化分析方法，用于比较不同净负荷预测模型的性能。	penetration
18	TRGR: Transmissive RIS-aided Gait Recognition Through Walls	提出TRGR以解决墙体穿透下的步态识别问题	penetration

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

#	题目	一句话要点	标签	🔗	⭐
19	Open-Vocabulary Audio-Visual Semantic Segmentation	提出OV-AVSS框架，解决开放词汇音视频语义分割任务，提升零样本泛化能力。	open-vocabulary open vocabulary	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页