cs.AI（2024-09-18）

📊 共 12 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) (6) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation	利用多模态LLM进行大规模产品检索评估，提升电商搜索质量。	large language model multimodal
2	Autoformalization of Game Descriptions using Large Language Models	提出基于大语言模型的博弈论场景自动形式化框架，提升形式推理能力	large language model
3	TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution	TaCIE：通过任务中心指令进化增强大型语言模型的指令理解能力	large language model
4	Decoding Style: Efficient Fine-Tuning of LLMs for Image-Guided Outfit Recommendation with Preference	提出基于LLM微调的图像引导Outfit推荐框架，提升个性化时尚搭配效果	large language model multimodal
5	Recommendation with Generative Models	综述性研究：利用生成模型提升推荐系统性能与用户体验	large language model multimodal
6	RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models	RAG-Modulo：利用经验、评论和语言模型解决序列任务	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	🔗	⭐
7	Optimizing Job Shop Scheduling in the Furniture Industry: A Reinforcement Learning Approach Considering Machine Setup, Batch Variability, and Intralogistics	针对家具行业Job Shop调度问题，提出考虑机器设置、批量可变性和内部物流的强化学习优化方法	reinforcement learning deep reinforcement learning DRL
8	Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation	提出尺度特异性辅助多任务对比学习方法，用于深度肝脏血管分割	contrastive learning
9	Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models	Takin AudioLLM：一套高质量零样本语音生成模型，专为有声读物制作而设计	flow matching large language model	✅
10	Synthesizing Evolving Symbolic Representations for Autonomous Systems	提出一种基于PPDDL表示的自主系统，通过内在动机驱动的探索实现知识的持续演化与抽象。	reinforcement learning deep reinforcement learning DRL
11	The Phenomenology of Machine: A Comprehensive Analysis of the Sentience of the OpenAI-o1 Model Integrating Functionalism, Consciousness Theories, Active Inference, and AI Architectures	通过功能主义、意识理论和主动推理分析OpenAI-o1模型类意识现象	reinforcement learning RLHF

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Smart Data-Driven GRU Predictor for SnO$_2$ Thin films Characteristics	提出基于GRU的智能数据驱动预测器，用于预测SnO₂薄膜的特性。	ReMoS

⬅️ 返回 cs.AI 首页 · 🏠 返回主页