cs.AI（2025-05-13）

📊 共 34 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (12 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 Ultrasound Report Generation with Multimodal Large Language Models for Standardized Texts 提出基于多模态大语言模型的超声报告生成框架，实现标准化文本输出。 large language model multimodal
2 Decoding Neighborhood Environments with Large Language Models 利用大型语言模型解码社区环境：无需训练，实现高精度环境要素识别。 large language model
3 Optimized Couplings for Watermarking Large Language Models 针对大语言模型，提出优化耦合的水印方案，提升检测能力并降低文本质量损失。 large language model ✅
4 DeepMath-Creative: A Benchmark for Evaluating Mathematical Creativity of Large Language Models 提出DeepMath-Creative以评估大语言模型的数学创造力 large language model
5 CellTypeAgent: Trustworthy cell type annotation with Large Language Models CellTypeAgent：利用大语言模型实现可信的细胞类型注释 large language model
6 The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News 提出TruEDebate，利用多智能体辩论系统与大语言模型提升假新闻检测的解释性和有效性 large language model
7 Unveiling the Best Practices for Applying Speech Foundation Models to Speech Intelligibility Prediction for Hearing-Impaired People 针对听障人士语音清晰度预测，揭示语音基础模型应用的最佳实践 foundation model
8 Federated Large Language Models: Feasibility, Robustness, Security and Future Directions 综述联邦大语言模型(FLLM)在可行性、鲁棒性、安全性的挑战与未来方向 large language model
9 TrialMatchAI: An End-to-End AI-powered Clinical Trial Recommendation System to Streamline Patient-to-Trial Matching TrialMatchAI：端到端AI临床试验推荐系统，加速患者与试验匹配 large language model chain-of-thought
10 Lost in Transmission: When and Why LLMs Fail to Reason Globally 提出BAPO模型，揭示LLM全局推理失败源于内部通信带宽限制 large language model chain-of-thought
11 Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification 结合CoT、RAG、自洽性和自验证，提升大型语言模型的可靠性 large language model chain-of-thought
12 Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation WebApp1K：提出测试驱动开发基准，评估LLM从测试用例生成代码的能力 large language model instruction following
13 AI and Generative AI Transforming Disaster Management: A Survey of Damage Assessment and Response Techniques 综述AI与生成式AI在灾害管理中的应用，聚焦于灾害评估与响应技术。 multimodal
14 AI-Mediated Code Comment Improvement 提出基于AI的代码注释改进方法，利用大语言模型重写注释以提升质量 large language model
15 Securing RAG: A Risk Assessment and Mitigation Framework 提出RAG安全框架，评估并缓解检索增强生成中的安全风险 large language model
16 VizCV: AI-assisted visualization of researchers' publications tracks VizCV：提出AI辅助的可视化框架，用于分析科研人员的论文发表轨迹。 large language model
17 Resource-Efficient Language Models: Quantization for Fast and Accessible Inference 针对大语言模型，提出后训练量化方法以加速推理并降低资源需求 large language model
18 Evaluating LLM Metrics Through Real-World Capabilities 评估LLM在真实世界能力：弥合基准测试与实际应用差距，Gemini表现突出 large language model
19 Communication Styles and Reader Preferences of LLM and Human Experts in Explaining Health Information 研究LLM与人类专家在健康信息解释中的沟通风格差异及读者偏好 large language model
20 Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions 利用AI革新HPC软件开发：挑战与研究方向探讨 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
21 Foundation Models Knowledge Distillation For Battery Capacity Degradation Forecast 提出基于知识蒸馏的电池容量衰退预测框架，提升跨尺度泛化能力并降低计算成本。 teacher-student distillation foundation model
22 Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections 提出基于深度强化学习的纵向控制策略，提升自动驾驶车辆在信号交叉口的安全性、效率和舒适性。 reinforcement learning deep reinforcement learning DRL
23 Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control 提出基于蒙特卡洛束搜索的Actor-Critic强化学习方法，提升连续控制任务的探索效率。 reinforcement learning policy learning PPO
24 Strategy-Augmented Planning for Large Language Models via Opponent Exploitation 提出基于策略增强规划的LLM智能体，通过对手策略挖掘提升博弈性能 reinforcement learning large language model ✅
25 Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation 提出自适应难度课程学习与专家引导自重构，提升LLM数学推理能力 reinforcement learning imitation learning curriculum learning
26 Improved Algorithms for Differentially Private Language Model Alignment 提出差分隐私语言模型对齐算法，提升隐私保护下的对齐效果 reinforcement learning RLHF DPO
27 Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation 提出基于深度强化学习的电力系统多阶段级联故障缓解策略 reinforcement learning deep reinforcement learning
28 Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning 提出分层多智能体强化学习，提升空战战术决策能力 reinforcement learning deep reinforcement learning
29 Hyperbolic Contrastive Learning with Model-augmentation for Knowledge-aware Recommendation 提出基于双曲对比学习和模型增强的知识感知推荐方法，解决层级结构建模和偏好偏移问题。 preference learning contrastive learning
30 Automated Meta Prompt Engineering for Alignment with the Theory of Mind 提出基于Agent强化学习的元提示工程，提升大语言模型与人类心智理论的对齐 reinforcement learning large language model
31 A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary Regularization 提出基于Mamba的SpectMamba网络，结合置信度二元正则化，用于半监督的歌声旋律提取。 Mamba
32 A Study of Data-driven Methods for Inventory Optimization 研究数据驱动方法在超市库存优化中的应用，对比时间序列、随机森林和深度强化学习算法。 reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
33 Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning 提出WM3C以解决强化学习中的环境泛化问题 manipulation reinforcement learning policy learning
34 A Survey of Deep Learning for Complex Speech Spectrograms 综述深度学习在复数语音语谱图处理中的应用，涵盖网络架构、训练策略及应用。 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页