cs.AI（2024-07-05）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games 研究表明大型语言模型在非零和博弈中存在策略决策偏差，影响其性能 large language model chain-of-thought
2 EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context EventChat：面向中小企业，基于大语言模型的休闲活动对话推荐系统及其用户评估 large language model
3 Jailbreak Attacks and Defenses Against Large Language Models: A Survey 针对大型语言模型越狱攻击与防御的综述研究，旨在提升LLM安全性。 large language model
4 Enabling On-Device LLMs Personalization with Smartphone Sensing 提出基于智能手机传感的端侧LLM个性化框架，解决隐私、延迟和成本问题 large language model multimodal
5 Smart Vision-Language Reasoners 提出Smart VLM，提升视觉-语言模型在多模态推理任务上的性能。 multimodal visual grounding ✅
6 Evaluating Language Models for Generating and Judging Programming Feedback 评估开源LLM在编程反馈生成与质量评估中的能力，媲美专有模型 large language model
7 Code Hallucination 提出HallTrigger，高效触发大语言模型代码幻觉，揭示软件开发风险。 large language model
8 Towards Automated Functional Equation Proving: A Benchmark Dataset and A Domain-Specific In-Context Agent 提出FEAS：一种用于自动函数方程证明的领域特定上下文学习Agent large language model
9 When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings 利用“传话游戏”和文化吸引子评估多轮交互中大型语言模型的演化 large language model
10 Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs 提出Waterfall框架，实现对LLM生成文本的鲁棒、可扩展水印和溯源。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents AriGraph：利用情景记忆学习知识图谱世界模型，提升LLM Agent能力 world model large language model
12 Reinforcement Learning for Unsupervised Video Summarization with Reward Generator Training 提出一种基于强化学习和奖励生成器的无监督视频摘要方法，提升摘要质量。 reinforcement learning
13 Hybrid-Generative Diffusion Models for Attack-Oriented Twin Migration in Vehicular Metaverses 提出混合生成扩散模型，解决车载元宇宙中面向攻击的车载孪生迁移问题 reinforcement learning deep reinforcement learning
14 Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents 提出Autoverse可进化游戏语言，用于学习鲁棒的具身智能体 reinforcement learning imitation learning

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

#题目一句话要点标签🔗⭐
15 Improving ensemble extreme precipitation forecasts using generative artificial intelligence 提出基于生成式AI的集合后处理方法，提升极端降水概率预报能力 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页