cs.AI（2024-10-20）

📊 共 13 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Jailbreaking and Mitigation of Vulnerabilities in Large Language Models 综述大型语言模型越狱攻击与防御策略，促进安全部署。 large language model multimodal
2 Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training 提出敏感度Dropout（SenD）以降低大语言模型训练中的幻觉现象 large language model
3 Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations 利用GPT-4模拟社会调查，探索大型语言模型中的社会期望偏差 large language model
4 Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs 揭示并利用RAG中MoE-LLM的核心专家，提升检索增强生成效果 large language model
5 The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks 利用LLM漏洞防御LLM驱动的网络攻击，成功率高达90% large language model
6 A Survey of Hallucination in Large Visual Language Models 综述性研究：针对大型视觉语言模型幻觉问题的成因、缓解方法与评估基准进行全面分析 large language model
7 Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game 提出MPTT框架，引导LLM在“谁是卧底”游戏中探索多视角团队策略 large language model
8 HyQE: Ranking Contexts with Hypothetical Query Embeddings HyQE：利用假设查询嵌入提升检索增强系统中上下文排序性能 large language model ✅
9 Economic Anthropology in the Era of Generative Artificial Intelligence 融合经济人类学知识，提升生成式AI对多元经济体系的理解 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
10 Generative Models, Humans, Predictive Models: Who Is Worse at High-Stakes Decision Making? 评估大型生成模型在复发预测高风险决策中的表现，结果表明其不如人类和预测模型。 predictive model
11 Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing 提出基于异构图强化学习的HGRL-TA框架，解决空间众包中依赖感知的多任务分配问题。 reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 Improving Voice Quality in Speech Anonymization With Just Perception-Informed Losses 提出感知驱动损失函数，提升语音匿名化中语音质量 VQ-VAE

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

#题目一句话要点标签🔗⭐
13 Fractional-order spike-timing-dependent gradient descent for multi-layer spiking neural networks 提出分数阶STDP梯度下降算法，提升脉冲神经网络在时序数据上的学习能力。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页