cs.AI（2024-08-21）

📊 共 22 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding ProteinGPT：用于蛋白质性质预测和结构理解的多模态LLM large language model multimodal ✅
2 Leveraging Chemistry Foundation Models to Facilitate Structure Focused Retrieval Augmented Generation in Multi-Agent Workflows for Catalyst and Materials Design 利用化学基础模型，促进多智能体工作流中结构聚焦的检索增强生成，用于催化剂和材料设计。 large language model foundation model
3 Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environments 提出用于日常动态时空推理的多模态数据集与评测基准 embodied AI multimodal
4 Exploring Large Language Models for Feature Selection: A Data-centric Perspective 探索基于大型语言模型（LLM）的特征选择方法，并从数据中心视角进行分析。 large language model
5 Estimating Contribution Quality in Online Deliberations Using a Large Language Model 利用大型语言模型评估在线讨论中贡献质量，提升效率并保持质量。 large language model
6 Efficient Detection of Toxic Prompts in Large Language Models 提出ToxicDetector以解决大语言模型中的有害提示检测问题 large language model
7 Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests UTGen利用大语言模型提升自动生成单元测试的可理解性，从而改善软件工程师的bug修复效率。 large language model
8 Mutagenesis screen to map the functions of parameters of Large Language Models 通过诱变筛选法探索大语言模型参数与功能的映射关系 large language model
9 Probabilistic Medical Predictions of Large Language Models 对比LLM生成概率与隐式概率，揭示其在医疗预测中的可靠性问题 large language model
10 Defending against Jailbreak through Early Exit Generation of Large Language Models 提出基于早期退出的EEG-Defender防御方法，以抵御大语言模型的越狱攻击 large language model
11 Applying and Evaluating Large Language Models in Mental Health Care: A Scoping Review of Human-Assessed Generative Tasks 综述性研究：评估大型语言模型在心理健康护理中生成任务的应用 large language model
12 DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework DreamFactory：基于多智能体框架的多场景长视频生成 large language model chain-of-thought
13 BearLLM: A Prior Knowledge-Enhanced Bearing Health Management Framework with Unified Vibration Signal Representation BearLLM：基于先验知识增强的统一振动信号表征轴承健康管理框架 large language model multimodal ✅
14 Matmul or No Matmul in the Era of 1-bit LLMs 针对1-bit LLM的计算与内存瓶颈，提出Amdahl定律的适配分析方法。 large language model
15 Drama Engine: A Framework for Narrative Agents Drama Engine：用于叙事代理的、基于多智能体原则的大语言模型交互框架 large language model
16 SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering 提出SCANS方法，通过激活向量引导缓解大语言模型过度安全问题 large language model
17 Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning 提出模型标签学习MLL，实现小模型零样本选择与复用 foundation model
18 Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework 提出一种推理时缓解框架，系统性分析并缓解视觉语言模型中的谄媚现象。 multimodal

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

#题目一句话要点标签🔗⭐
19 LARR: Large Language Model Aided Real-time Scene Recommendation with Semantic Understanding 提出LARR，利用大语言模型增强实时场景推荐的语义理解能力 contrastive learning large language model
20 Advances in Preference-based Reinforcement Learning: A Review 综述性论文：回顾基于偏好的强化学习最新进展，提升可扩展性和效率。 reinforcement learning
21 Automating Thought of Search: A Journey Towards Soundness and Completeness AutoToS：自动化Thought of Search，实现规划问题求解的完备性和可靠性 world model large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
22 CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher CIPHER：面向渗透测试的智能助手，提升伦理研究效率 penetration large language model ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页