cs.AI（2025-08-30）

📊 共 13 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) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting 提出BALM-TSF以解决多模态时间序列预测中的模态失衡问题 large language model multimodal ✅
2 SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces 提出SIGMUS以解决城市多模态数据整合问题 large language model multimodal
3 A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services 提出成本效益分析框架以评估本地LLM部署的经济可行性 large language model
4 Access Paths for Efficient Ordering with Large Language Models 提出LLM ORDER BY语义操作符以优化大语言模型排序效率 large language model
5 FlexLink: Boosting your NVLink Bandwidth by 27% without accuracy concern 提出FlexLink以提升NVLink带宽27%解决通信瓶颈问题 large language model
6 KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache 提出KVComp以解决长文本生成中的KV缓存管理问题 large language model
7 Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs 提出基于大语言模型的建筑平面图草图生成方法 large language model
8 Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models 提出基于扰动差异一致性的后门样本检测方法 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning 提出SABR框架以解决自适应码率控制的泛化问题 reinforcement learning behavior cloning
10 FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance 提出FinFlowRL框架以解决金融领域自适应随机控制问题 reinforcement learning policy learning
11 Social World Models 提出S3AP以提升AI对社交动态的理解能力 world model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
12 NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks 提出NEWSAGENT以评估多模态智能体在新闻写作中的应用 manipulation multimodal
13 Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats 提出Sentinel以解决联邦学习中的拜占庭攻击问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页