筛选结果
210 篇排序
13:22EN → 简体中文AI 音乐的三种方式:Soundraw、Synthesizer V 与 MusicLMMatthew Berman · Forward Future一段 2023 年演示探索生成器乐、可编辑的合成歌声,以及早期文字生成音乐研究。
45:03EN → 简体中文Emad Mostaque 的赌注:开放的小模型,而非一个巨型大脑主持 Sarah Guo, Elad GilStability AI 创始人在 No Priors 节目上讲述,为什么基础模型应当是公共基础设施,为什么小模型能胜过巨型模型,以及这对媒体、医学和 AGI 意味着什么。
8:19EN → 简体中文2023 年的 Leonardo.Ai:生成图像、混搭模型与编辑画布Matthew Berman · Forward FutureMatthew Berman 演示 Leonardo.Ai 早期图像生成界面,从风格模型和设置讲到社区混搭、自定义训练和测试版画布。功能和价格自 2023 年 2 月这次演示以来已有变化。
6:00EN → 简体中文Nothing, Forever:AI 生成喜剧与电视的未来Matthew Berman · Forward FutureMatthew Berman 讨论这部程序生成的 Seinfeld 致敬作品、其尴尬的喜剧效果、审核挑战及对未来媒体的启示。
3:08EN → 简体中文David Guetta 使用 AI 生成 Eminem 声音及其引发的问题Matthew Berman, David Guetta · Forward FutureMatthew Berman 讨论 DJ 演出中播放的合成歌声,并思考同意、创作使用和可能的法律争议。
48:52EN → 简体中文用户要的是更好的画笔,Runway 却做出了一键绿幕抠像主持 Sarah Guo, Elad GilRunway 首席执行官 Cristobal Valenzuela 谈为什么模型不等于产品,为什么电影人会去折腾一个每秒只能处理四帧的工具,以及在没人会因此丧命的场景里,为什么 80% 就够用。
1:09:11EN → 简体中文别做成自动驾驶:Gavin Miller 谈把主导权留给创作者的 AI嘉宾 Gavin Miller · 主持 Lex FridmanAdobe 研究院(Adobe Research)负责人在与 Lex Fridman 的对话中说明,为什么智能默认值、可修复的错误和研究院式的小赌注,比全自动的 Photoshop 更重要。
1:08:37EN → 简体中文蒙特利尔的一家酒吧,然后是一夜写代码:Ian Goodfellow 谈 GAN 为何奏效嘉宾 Ian Goodfellow · 主持 Lex FridmanLex Fridman 与 Ian Goodfellow 对谈,聊 2014 年生成对抗网络(GAN)的发明、作为安全问题的对抗样本(adversarial examples),以及机器要像人一样掌握一个事实,还需要建造什么。
48:58EN → 简体中文NotebookLM 那档意外走红的播客:一个 20% 项目、一支极小团队,和可再混剪的 AI 编辑器主持 Lenny RachitskyRaiza Martin 讲 Audio Overviews 如何变成病毒式演示、Google Labs 如何让小团队像创业公司一样发版,以及产品下一步往哪走。
53:02ENAdobe's Firefly Bet: A Billion Beta Images, Creative Control, and Trust at Scale主持 Jacob EffronAdobe's Alexandre explains how Firefly moved from research to product, how Adobe balances creative control with generative speed, and why trust and feedback loops are central to its AI strategy.
1:03:24ENWhy Sora Bet on People, Not Just Pixels主持 Jacob EffronThe Sora team explains how a video model became a social creation network, what cameos revealed about human creativity, and why the next frontier is world simulation.
58:19ENRunway's Chris Valenzuela on Why Taste Beats Tools in Generative Media主持 Jacob EffronChris Valenzuela, CEO of Runway, explains why generative media is still early, how taste and iteration shape the work, and what has to change before AI media becomes a new art form.
1:02:57ENVirtual Biopsies in One Second: How a Seven-Year-Old CycleGAN Is Beating Newer Models in the Clinic主持 Nathan LabenzTanishq Mathew Abraham explains how deep learning turns label-free 3D tissue images into virtual H&E stains fast enough to guide tumor surgery.
51:45ENCameras Optional: HeyGen's Joshua Xu on Avatars, Orchestration and Building Ahead of the Models主持 Jacob EffronHeyGen co-founder and CEO Joshua Xu explains how AI avatars are replacing the camera for business video, and how the company handles quality, trust and safety, and capital.
1:17:31ENImage AI Is Still at the GPT-2 Stage: Suhail Doshi on Building a Unified Vision Model主持 Nathan LabenzPlayground AI's founder explains why image generation has barely begun to deliver real utility, and why his team is betting 2024 on editing and a single model that can create, edit and understand pixels.
43:44ENRoblox's 20-Year Bet: Building the Holodeck with Native AI Models主持 Sarah Guo, Elad GilRoblox CEO Dave Baszucki explains how 13 billion monthly hours of 3D interaction data could power smarter NPCs, virtual doppelgängers and a cloud-native future for games.
1:02:15ENSuno’s CEO Says the Future of Music Is a Conversation, Not a Prompt主持 Jacob EffronSuno CEO Mikey Shulman explains how AI music is moving from text prompts to co-creation, why music evals are subjective, and what he would build next.









