cs.AI（2024-10-04）

📊 共 16 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗3) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 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 Understanding Reasoning in Chain-of-Thought from the Hopfieldian View 从Hopfield网络视角理解Chain-of-Thought推理，提升鲁棒性与可解释性 large language model chain-of-thought
2 Gradient-based Jailbreak Images for Multimodal Fusion Models 提出基于梯度优化的图像Jailbreak攻击，突破多模态融合模型的防御。 multimodal
3 Towards a Benchmark for Large Language Models for Business Process Management Tasks 构建面向业务流程管理任务的大语言模型基准评测 large language model
4 Enriching Ontologies with Disjointness Axioms using Large Language Models 利用大型语言模型补全本体中类的不相交公理，提升知识图谱推理能力 large language model ✅
5 Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks 研究多模态提示中图文顺序对大语言模型推理性能的影响 large language model
6 TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation TICK：通过生成式检查清单改进LLM评估与生成 large language model instruction following
7 DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search DOTS：通过最优推理轨迹搜索，使LLM具备动态推理能力 large language model
8 On Uncertainty In Natural Language Processing 研究自然语言处理中的不确定性，并提出校准抽样和置信度量化方法。 large language model
9 ProcBench: Benchmark for Multi-Step Reasoning and Following Procedure 提出ProcBench基准以评估多步骤推理能力 large language model ✅
10 Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs 提出基于本体、保障案例和要素表的框架，增强LLM的欧盟AI法案合规性和对抗鲁棒性。 large language model
11 Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs 提出LLM对抗鲁棒性保障框架，应对恶意攻击并满足法规遵从 large language model
12 GraphRouter: A Graph-based Router for LLM Selections GraphRouter：一种基于图的LLM选择路由方法，提升性能并降低成本。 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 Adaptive Masking Enhances Visual Grounding 提出IMAGE：通过自适应掩码增强视觉定位的零样本与少样本学习能力 manipulation masked autoencoder MAE ✅
14 An Approach To Enhance IoT Security In 6G Networks Through Explainable AI 提出基于可解释AI的树模型方法，增强6G网络中物联网安全 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 AutoPenBench: Benchmarking Generative Agents for Penetration Testing AutoPenBench：用于渗透测试生成式Agent的综合评估基准 penetration 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🔗⭐
16 Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection 提出AADG框架以生成音频异常检测基准数据 world model large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页