cs.AI（2024-11-30）

📊 共 13 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) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization	LAMBDA：通过搜索空间量化覆盖自动驾驶系统多模态关键场景	multimodal
2	Fairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions	提出一种多模态临床预测中缓解交叉偏见的方法，提升公平性。	multimodal
3	Empowering the Deaf and Hard of Hearing Community: Enhancing Video Captions Using Large Language Models	利用大型语言模型增强视频字幕，提升聋哑人及听力障碍者社区的视频内容可访问性。	large language model
4	Leveraging LLM for Automated Ontology Extraction and Knowledge Graph Generation	OntoKGen：利用LLM自动提取本体并生成知识图谱，解决RAM领域知识获取难题。	large language model chain-of-thought
5	Benchmark Real-time Adaptation and Communication Capabilities of Embodied Agent in Collaborative Scenarios	提出MonTA框架，提升具身智能体在协同场景中的实时适应与沟通能力	large language model
6	Unified Parameter-Efficient Unlearning for LLMs	提出LLMEraser，用于LLM中高效、统一的参数高效解学习	large language model
7	A Flexible Method for Behaviorally Measuring Alignment Between Human and Artificial Intelligence Using Representational Similarity Analysis	利用表征相似性分析，灵活衡量人与AI在行为上的对齐程度	large language model
8	Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective	综述：基于查询视角的知识图谱神经符号推理研究	large language model
9	FullStack Bench: Evaluating LLMs as Full Stack Coders	FullStack Bench：一个用于评估LLM全栈代码能力的综合性基准测试	large language model
10	Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphs	提出LENIE，利用LLM增强知识图谱语义信息，提升节点重要性评估。	large language model	✅
11	DroidCall: A Dataset for LLM-powered Android Intent Invocation	DroidCall：用于LLM驱动的Android Intent调用的数据集	large language model	✅
12	Aligning LLM+PDDL Symbolic Plans with Human Objective Specifications through Evolutionary Algorithm Guidance	提出基于进化算法引导的LLM+PDDL方法，提升符号规划与人类目标规范的对齐	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	🔗	⭐
13	Federated Progressive Self-Distillation with Logits Calibration for Personalized IIoT Edge Intelligence	提出基于Logits校准和渐进自蒸馏的联邦学习方法FedPSD，用于个性化IIoT边缘智能。	distillation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页