cs.AI（2025-06-28）

📊 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) (4)

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

#题目一句话要点标签🔗⭐
1 MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning 提出MARBLE：一个用于多模态空间推理与规划的硬基准测试。 multimodal
2 Beyond Code: The Multidimensional Impacts of Large Language Models in Software Development 利用ChatGPT禁令的自然实验，量化LLM对开源软件开发者生产力、知识共享和技能提升的多维影响。 large language model
3 Generating Privacy Stories From Software Documentation 提出基于LLM的隐私故事生成方法，从软件文档中提取隐私需求 large language model chain-of-thought
4 A Data Science Approach to Calcutta High Court Judgments: An Efficient LLM and RAG-powered Framework for Summarization and Similar Cases Retrieval 提出基于LLM和RAG的框架，高效总结和检索加尔各答高等法院判决 large language model
5 Positioning AI Tools to Support Online Harm Reduction Practice: Applications and Design Directions 探索LLM在减少药物滥用危害信息提供中的应用与设计方向 large language model
6 Improving Rationality in the Reasoning Process of Language Models through Self-playing Game 提出基于自博弈的Critic-Discernment Game，提升LLM推理过程的合理性。 large language model
7 Performance Measurements in the AI-Centric Computing Continuum Systems 针对AI计算连续体系统，论文探讨了性能测量指标的演进与选择标准。 large language model
8 Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation 量化提升代码生成LLM鲁棒性：对抗攻击与噪声扰动双重视角 large language model
9 RAILS: Retrieval-Augmented Intelligence for Learning Software Development RAILS：检索增强智能用于学习软件开发，解决LLM代码补全中的导入错误问题。 large language model
10 P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code P4OMP：利用检索增强提示将串行C/C++代码转换为OpenMP并行代码 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 Offline Reinforcement Learning for Mobility Robustness Optimization 利用离线强化学习优化移动鲁棒性，提升蜂窝网络性能 reinforcement learning offline RL offline reinforcement learning
12 ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models ReasonBridge：通过高效推理迁移，提升开源语言模型的推理能力 distillation large language model instruction following
13 SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning 提出SPEAR框架，通过强化学习和突触操作估计实现脉冲神经网络的结构化剪枝。 reinforcement learning
14 WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing WavShape：面向公平与隐私保护的语音表征信息论学习框架 representation learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页