cs.AI（2025-01-31）

📊 共 21 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Imitation Game for Adversarial Disillusion with Multimodal Generative Chain-of-Thought Role-Play 提出基于模仿博弈的多模态生成式思维链角色扮演对抗攻击防御框架 multimodal chain-of-thought
2 Multimodal MRI-Ultrasound AI for Prostate Cancer Detection Outperforms Radiologist MRI Interpretation: A Multi-Center Study 多模态MRI-超声AI用于前列腺癌检测，优于放射科医生MRI判读 multimodal
3 Augmented Intelligence for Multimodal Virtual Biopsy in Breast Cancer Using Generative Artificial Intelligence 利用生成式AI增强乳腺癌多模态虚拟活检的智能辅助诊断 multimodal
4 Synthetic User Behavior Sequence Generation with Large Language Models for Smart Homes 提出基于大语言模型的IoTGen框架，用于生成智能家居用户行为序列数据，提升下游模型泛化性。 large language model
5 MINDSTORES: Memory-Informed Neural Decision Synthesis for Task-Oriented Reinforcement in Embodied Systems 提出MINDSTORES以解决现有LLM规划能力不足的问题 embodied AI large language model
6 Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game 通过变色龙游戏评估LLM在信息控制、推理和策略制定方面的能力 large language model
7 We're Different, We're the Same: Creative Homogeneity Across LLMs 揭示大语言模型在创意生成上的同质性：不同模型，相似结果 large language model
8 LLM Cyber Evaluations Don't Capture Real-World Risk 提出LLM网络安全风险评估框架，弥合能力评估与真实世界影响之间的差距 large language model
9 SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling SETS：利用自验证与自纠正提升大模型测试时推理能力 large language model
10 Analysis of LLMs vs Human Experts in Requirements Engineering 对比LLM与专家在需求工程中的表现：LLM在需求获取方面更优 large language model
11 LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation LLM-RecG：一种语义偏差感知的零样本序列推荐框架 large language model
12 Language Games as the Pathway to Artificial Superhuman Intelligence 提出基于语言游戏的ASI演进框架，突破数据再生产陷阱 large language model
13 SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment 探索AI辅助软件开发中的幻觉与安全风险，为LLM部署提供洞见 large language model
14 Can AI Solve the Peer Review Crisis? A Large Scale Cross Model Experiment of LLMs' Performance and Biases in Evaluating over 1000 Economics Papers 利用大规模实验评估LLM在经济学论文评审中的表现与偏差，探索AI辅助同行评审 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
15 Jackpot! Alignment as a Maximal Lottery 提出基于最大彩票的对齐方法，提升LLM在人类反馈学习中的鲁棒性 reinforcement learning RLHF large language model
16 In Pursuit of Predictive Models of Human Preferences Toward AI Teammates 探究人类对AI队友偏好的预测模型，用于Hanabi合作博弈 reinforcement learning predictive model
17 An Empirical Game-Theoretic Analysis of Autonomous Cyber-Defence Agents 提出基于潜在奖励塑造和多响应预言机的深度强化学习网络攻防博弈分析框架 reinforcement learning deep reinforcement learning DRL
18 Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning 提出基于客观指标的XRL评估方法，用于调试智能体行为和支持人机协作。 reinforcement learning
19 SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments SHARPIE：用于人机交互强化学习实验的模块化通用框架 reinforcement learning
20 Enabling Autonomic Microservice Management through Self-Learning Agents 提出ServiceOdyssey，通过自学习Agent实现微服务自治管理 curriculum learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning 提出Safety Chain-of-Thought，增强LLM防御对抗性攻击的能力 manipulation large language model chain-of-thought

⬅️ 返回 cs.AI 首页 · 🏠 返回主页