cs.AI（2024-07-06）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts	提出LogicVista基准，评估多模态LLM在视觉环境下的逻辑推理能力	large language model multimodal	✅
2	Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?	提出BeyondX基准，揭示大语言模型在多未知数数学问题上的局限性，并提出Formulate-and-Solve策略。	large language model
3	MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning	MFE-ETP：用于具身任务规划的多模态基础模型综合评估基准	foundation model
4	Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing	利用大语言模型，自动化生成高性能计算单元测试	large language model
5	Lucy: Think and Reason to Solve Text-to-SQL	Lucy：结合LLM与自动推理，解决复杂数据库Text-to-SQL难题	large language model
6	Are LLMs Correctly Integrated into Software Systems?	研究揭示LLM与RAG集成软件系统中的缺陷模式并提出改进指南	large language model
7	Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning	仅用Prompt工程实现LLM的工具调用功能，无需微调	large language model
8	Algorithmic Language Models with Neurally Compiled Libraries	提出神经编译库增强算法语言模型，提升LLM的推理与规划能力	large language model

#	题目	一句话要点	标签	🔗	⭐
9	Form Forge: Latent Space Exploration of Architectural Forms via Explicit Latent Variable Manipulation	Form Forge：通过显式潜在变量操纵探索建筑形式的潜在空间	manipulation