cs.AI（2024-12-21）

📊 共 20 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱八：物理动画 (Physics-based Animation) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Internalized Self-Correction for Large Language Models 提出InSeC：一种基于内部自纠正的大语言模型训练方法 large language model instruction following
2 Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans? 评估社会一致性：人格提示的大语言模型行为是否与人类相似？ large language model
3 Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models 提出基于主题的无角色扮演方法，评估大型语言模型在政治倾向和参与度上的偏见 large language model
4 Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning 提出CDR基准测试，评估多模态语言模型在指南针方向推理上的能力。 multimodal
5 Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions 综述：针对微调大语言模型的隐私攻击、防御及未来方向 large language model
6 Enhancing Conflict Resolution in Language Models via Abstract Argumentation 利用抽象论证增强语言模型在冲突解决中的能力 large language model chain-of-thought
7 Text2midi: Generating Symbolic Music from Captions 提出Text2midi，一种端到端模型，用于从文本描述生成MIDI音乐文件。 large language model multimodal ✅
8 The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Task Shield：通过任务对齐防御LLM Agent中的间接Prompt注入攻击 large language model
9 LearnLM: Improving Gemini for Learning LearnLM：通过教学指令跟随改进Gemini模型，提升教育场景下的AI表现 instruction following
10 TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation TimeRAG：通过检索增强生成提升LLM时间序列预测能力 large language model
11 AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection 提出AIGCodeSet数据集，用于AI生成代码检测，并验证贝叶斯分类器性能。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
12 Deep Reinforcement Learning Based Systems for Safety Critical Applications in Aerospace 基于深度强化学习的航空航天安全关键系统研究 reinforcement learning deep reinforcement learning DRL
13 Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement 提出Mamba-SEUNet，结合Mamba与U-Net用于单声道语音增强任务 Mamba SSM
14 DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction DCOR：通过双重对比学习重构实现属性网络中的异常检测 contrastive learning
15 OpenAI o1 System Card OpenAI o1系列模型：利用大规模强化学习和思维链推理提升安全性和鲁棒性 reinforcement learning chain-of-thought
16 On Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds 提出基于强化学习的eMBB-Agent，提升分片测试床中网络吞吐量 reinforcement learning
17 Effective and Efficient Representation Learning for Flight Trajectories 提出Flight2Vec，有效学习飞行轨迹表征，提升飞行分析任务性能。 representation learning
18 Mathematics and Machine Creativity: A Survey on Bridging Mathematics with AI 综述AI在数学研究中的应用，探索AI赋能数学创造性潜力 reinforcement learning large language model

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

#题目一句话要点标签🔗⭐
19 STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling 提出STAMPsy数据集，用于构建时空感知的混合型心理咨询对话系统。 spatiotemporal TAMP

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
20 FAP-CD: Fairness-Driven Age-Friendly Community Planning via Conditional Diffusion Generation FAP-CD：通过条件扩散生成实现公平驱动的适老化社区规划 spatial relationship

⬅️ 返回 cs.AI 首页 · 🏠 返回主页