cs.AI（2025-06-21）

📊 共 15 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) (2) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Expanding Relevance Judgments for Medical Case-based Retrieval Task with Multimodal LLMs	利用多模态LLM扩展医学案例检索任务的相关性判断，显著降低标注成本。	large language model multimodal
2	PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models	提出PhysUniBench：一个本科生水平的物理推理多模态模型评测基准。	large language model multimodal	✅
3	Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models	Cite Pretrain：通过持续预训练实现大语言模型的免检索知识归属	large language model
4	Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges	提出CTFAgent框架，增强大语言模型在CTF挑战中的知识应用和交互能力	large language model
5	Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models	提出WISE：利用LLM和结构化流程，从关联开放数据中进行上下文感知的科学知识抽取。	large language model
6	Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems	针对大语言模型推荐系统，提出模型并行与数据并行混合优化方案，提升训练效率。	large language model
7	CARTS: Collaborative Agents for Recommendation Textual Summarization	CARTS：一种用于推荐文本摘要的协同Agent框架，提升标题相关性和用户参与度。	large language model chain-of-thought
8	Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown	提出基于图知识检索与推理的多智能体方法，提升MLLM在未知领域的性能	large language model multimodal
9	Bayesian Social Deduction with Graph-Informed Language Models	提出基于图结构的语言模型，用于增强LLM在阿瓦隆游戏中的社会推理能力	large language model	✅
10	AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction	AnyMAC：通过预测下一代理实现灵活的多智能体级联协作	large language model
11	Beyond Syntax: Action Semantics Learning for App Agents	提出动作语义学习(ASL)框架，提升App智能体在智能手机应用操作中的泛化能力。	large language model
12	Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and Experience	提出战略随机化以提升大语言模型的决策能力	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning	CultureMERT：通过持续预训练提升跨文化音乐表征学习	representation learning foundation model
14	Reflective Verbal Reward Design for Pluralistic Alignment	提出反思性语言奖励设计，解决RLHF中个体偏好被抑制的问题。	reinforcement learning RLHF reward design

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Residual Connection-Enhanced ConvLSTM for Lithium Dendrite Growth Prediction	提出残差连接增强的ConvLSTM模型，用于锂枝晶生长预测。	spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页