cs.AI（2025-05-05）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models	FormalMATH：构建大规模形式化数学推理基准，揭示LLM在数学证明中的局限性。	large language model chain-of-thought
2	Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play	Voila：用于实时自主交互和语音角色扮演的语音-语言基础模型	large language model foundation model
3	Beyond the model: Key differentiators in large language models and multi-agent services	大型语言模型竞争焦点转向生态优化，关注数据、效率与评估	large language model foundation model
4	Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks	提出基于LMM的车辆网络任务型语义通信框架，提升恶劣信道下的问答精度。	large language model multimodal
5	From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation	利用空间条件扩散模型，实现星载SAR图像到机载SAR图像的多尺度合成。	foundation model
6	Advancing Email Spam Detection: Leveraging Zero-Shot Learning and Large Language Models	利用零样本学习和大型语言模型改进电子邮件垃圾邮件检测	large language model
7	The Multimodal Paradox: How Added and Missing Modalities Shape Bias and Performance in Multimodal AI	多模态悖论：模态增减如何影响多模态AI的偏差与性能	multimodal
8	Large Language Model Partitioning for Low-Latency Inference at the Edge	提出资源感知的LLM Transformer头划分算法，降低边缘设备推理延迟。	large language model
9	Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning	提出RDD：一种通用的、可扩展的依赖递归分解推理方法	large language model chain-of-thought
10	Evaluating the Impact of AI-Powered Audiovisual Personalization on Learner Emotion, Focus, and Learning Outcomes	提出AI驱动的个性化视听学习系统，提升学习者专注力、情绪调节和学习效果	large language model multimodal
11	LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery	LISAt：面向卫星图像的语言指令分割助手，提升复杂场景理解能力。	foundation model multimodal	✅
12	Incentivizing Inclusive Contributions in Model Sharing Markets	提出iPFL，激励数据持有者在模型共享市场中进行包容性贡献，解决去中心化私有数据利用问题。	large language model instruction following
13	Perspective-Aware AI in Extended Reality	提出PAiR框架，将视角感知AI融入XR，实现基于用户身份的可解释、情境感知体验。	multimodal
14	BLAB: Brutally Long Audio Bench	提出BLAB：一个面向长音频理解的极具挑战性的评测基准	multimodal
15	Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study	大规模实证研究揭示公共LLM部署中的安全漏洞与风险	large language model
16	HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking	提出HyperTree Planning，通过层级思考增强LLM在复杂规划任务中的推理能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks	提出对抗知识蒸馏(AKD)方法，提升代码大模型在编程任务上的对齐效果。	distillation large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Towards Machine Learning-based Model Predictive Control for HVAC Control in Multi-Context Buildings at Scale via Ensemble Learning	提出基于集成学习的机器学习模型预测控制方法，用于大规模多场景建筑暖通空调控制。	model predictive control reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页