cs.AI（2025-03-07）

📊 共 16 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	The Society of HiveMind: Multi-Agent Optimization of Foundation Model Swarms to Unlock the Potential of Collective Intelligence	提出基于多智能体优化的HiveMind框架，提升基础模型集群的集体智能	large language model foundation model
2	Ontology Generation using Large Language Models	提出两种Prompting方法，利用大语言模型自动生成高质量OWL本体	large language model
3	Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index	提出INFINITE方法，评估大语言模型在代码生成中的推理性能	large language model
4	Towards Understanding the Use of MLLM-Enabled Applications for Visual Interpretation by Blind and Low Vision People	利用MLLM的视觉解释应用提升盲人和低视力人群的日常体验	large language model multimodal
5	AVA: Attentive VLM Agent for Mastering StarCraft II	提出AVA：一个基于视觉语言模型且具有注意力机制的星际争霸II智能体	foundation model multimodal	✅
6	Enhancing Reasoning with Collaboration and Memory	提出基于协作和记忆增强的大语言模型推理框架，提升复杂推理任务性能	chain-of-thought
7	TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator	TPU-Gen：基于LLM的定制张量处理器生成器，提升设计效率和性能。	large language model
8	Cognitive Bias Detection Using Advanced Prompt Engineering	提出一种基于高级Prompt工程的认知偏差检测方法，提升用户生成内容的客观性。	large language model
9	LLM-based Iterative Approach to Metamodeling in Automotive	提出基于LLM的迭代式元模型构建方法，应用于汽车领域。	large language model
10	Accelerating Earth Science Discovery via Multi-Agent LLM Systems	利用多智能体LLM系统加速地球科学发现	large language model
11	Static Program Analysis Guided LLM Based Unit Test Generation	提出静态程序分析引导的LLM单元测试生成方法，提升测试代码质量。	large language model
12	WritingBench: A Comprehensive Benchmark for Generative Writing	提出WritingBench，一个全面的生成式写作评估基准，并提出查询相关的评估框架。	large language model
13	PromptPex: Automatic Test Generation for Language Model Prompts	PromptPex：一种用于语言模型提示的自动测试生成工具	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	🔗	⭐
14	R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning	R1-Searcher：通过强化学习激励LLM的搜索能力，提升知识密集型任务性能	reinforcement learning distillation large language model
15	R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model	R1-Zero在2B非SFT模型上成功复现视觉推理的“顿悟”现象	reinforcement learning large language model multimodal	✅
16	Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation	提出Path Pooling，一种免训练的结构增强方法，用于高效知识图谱检索增强生成	representation learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页