大家好,欢迎收听“Hugging Face 每日AI论文速递”。今天是2024年8月27日,我们将带您快速浏览13篇热门AI论文,内容涵盖模型优化、基准测试、视频生成技术等多个前沿领域。现在,让我们立即进入今天的论文速递。
[00:23] 🚀 SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher(SwiftBrush v2:使您的一步扩散模型优于其教师模型)
[00:58] 🔧 SWE-bench-java: A GitHub Issue Resolving Benchmark for Java(SWE-bench-java:一个针对Java的GitHub问题解决基准)
[01:43] 🏆 K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences(K-Sort Arena:基于K-wise人类偏好的生成模型高效可靠基准测试)
[02:17] 🎵 Foundation Models for Music: A Survey(音乐基础模型综述)
[02:56] 🔄 LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs(LlamaDuo:从服务大型语言模型到小型本地模型的无缝迁移LLMOps管道)
[03:39] 🎥 Training-free Long Video Generation with Chain of Diffusion Model Experts(无需训练的长视频生成与链式扩散模型专家)
[04:11] 🎮 Learning to Move Like Professional Counter-Strike Players(学习专业反恐精英玩家的移动行为)
[04:46] 🌐 LLaVaOLMoBitnet1B: Ternary LLM goes Multimodal!(LLaVaOLMoBitnet1B:三元大型语言模型走向多模态!)
[05:18] 📱 MobileQuant: Mobile-friendly Quantization for On-device Language Models(MobileQuant:适用于移动设备的语言模型量化方法)
[05:53] 📈 Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler(Power Scheduler:一种与批量大小和令牌数量无关的学习率调度器)
[06:25] 🎥 TVG: A Training-free Transition Video Generation Method with Diffusion Models(TVG:一种无需训练的过渡视频生成方法与扩散模型)
[07:03] 🔍 Efficient Detection of Toxic Prompts in Large Language Models(大型语言模型中有毒提示的高效检测)
[07:34] 👤 MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement(MagicMan:利用3D感知扩散模型和迭代细化技术生成人类高质量多视角图像)

【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递

空空如也
暂无小宇宙热门评论