cs.AI（2025-01-23）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Stock Price Prediction 提出融合金融数据、新闻和社交媒体情感分析的多模态LSTM股票价格预测模型 multimodal
2 Text-to-SQL based on Large Language Models and Database Keyword Search 提出基于大语言模型和数据库关键词搜索的Text-to-SQL方法，提升真实数据库场景下的性能。 large language model
3 Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation 提出ReLLaX框架，优化LLM在推荐系统中对长序列用户行为的理解。 large language model
4 Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models 提出Jailbreak-AudioBench，全面评估和分析大型音频语言模型的越狱攻击威胁 large language model multimodal
5 EICopilot: Search and Explore Enterprise Information over Large-scale Knowledge Graphs with LLM-driven Agents 提出EICopilot以提升企业信息在大规模知识图谱中的搜索与探索效率 large language model chain-of-thought
6 Querying Databases with Function Calling 提出基于函数调用的数据库查询工具，提升LLM访问私有和实时数据的能力 large language model
7 On the Reasoning Capacity of AI Models and How to Quantify It 提出一种新的AI模型推理能力评估框架，揭示模型决策的潜在机制 large language model
8 TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Models TrueReason：集成推理与基础模型的个性化学习系统 large language model
9 Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning 提出CFPRM粗细粒度过程奖励建模，解决数学推理中LLM生成步骤冗余问题 large language model
10 Adaptive Testing for LLM-Based Applications: A Diversity-based Approach 提出基于多样性的自适应测试方法，优化LLM应用Prompt模板测试。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
11 Explainable AI-aided Feature Selection and Model Reduction for DRL-based V2X Resource Allocation 提出基于可解释AI的特征选择与模型简化方法，用于DRL驱动的V2X资源分配。 reinforcement learning deep reinforcement learning DRL
12 Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System 提出SS-MARL框架，提升多智能体系统安全性和可扩展性 reinforcement learning reward shaping

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
13 Toyteller: AI-powered Visual Storytelling Through Toy-Playing with Character Symbols Toyteller：通过角色符号玩具互动，实现AI驱动的可视化故事生成。 motion generation large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 Adaptive Genetic Algorithms for Pulse-Level Quantum Error Mitigation 提出一种自适应遗传算法，用于脉冲级量子误差缓解，提升量子电路保真度。 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页