2. V-JEPA 2 Meta AI introduces V-JEPA 2, a scalable joint-embedding predictive architecture for self-supervised video learning, targeting the goal of building a generalist world model capable of understanding, predicting, and planning in the physical world.
MULTIMODAL AI
-
Neural Operators for Medical Imaging Advance at CVPR
By
–
Check out our poster on neural operators for medical imaging today @CVPR
-
Inkr: Real-time STT Transcription Tool with Chinese Support
By
–
发现一个主打实时转录 STT 的工具，支持中文 Inkr – 每周有免费额度，需求量不大够用 之前听过不少叉友说有类似的需求，推荐一下 亮点
• 支持多种音频格式上传，转写速度极快
• 超过 100 种语言自动转录，适合多语言场景
• 自动区分说话人，便于整理访谈和会议记录
• 支持 AI -
Bilive: Automated Live Stream Recording and AI-Powered Video Processing
By
–
发现一个 B 站专属全自动，识别，切片，上传的工具 bilive – 自动化程度高，兼容强 – 人人都是录播员 亮点
• 支持 7 x 24 小时无人值守录制 B 站直播
• 自动渲染弹幕、识别字幕并合成到视频
• 根据弹幕密度自动切片，生成精彩片段并自动上传
• 集成多模态大模型，自动生成切片标题和视频封面 -
Interviewing Sophia World’s First Humanoid Robot
By
–
Interviewing Sophia, World's First Humanoid Robot! https://
search.app/g4wjB #sophiarobot #sophia #robot #ai #Tech #Technology #ArtificialIntelligence #robotics @lexfridman @KirkDBorne @Ronald_vanLoon @erikbryn @antgrasso @sallyeaves @Nicochan33 @HaroldSinnott @mvollmer1 -
Local AI Podcast Generator: Text to Multilingual Audio
By
–
Local AI Podcast Generator Transform text into multilingual podcasts with this AI system! Built using LangChain + Ollama, it combines text summarization and speech generation for seamless podcast creation. Check out the tutorial here https://
youtu.be/h5D4rDNe8xk -
AI Fuses Multiple Video Feeds for Real-Time Traffic Omniscience
By
–
Une IA fusionne plusieurs flux vidéo pour devenir un véritable dieu omniscient de la circulation.
— VISION IA (@vision_ia) 14 juin 2025
Voici ce qui se passe quand les caméras commencent à « se parler » : elles cartographient en temps réel la trajectoire de chaque véhicule et piéton, de manière fluide, d’une… pic.twitter.com/NIKF6yiX4qUne IA fusionne plusieurs flux vidéo pour devenir un véritable dieu omniscient de la circulation. Voici ce qui se passe quand les caméras commencent à « se parler » : elles cartographient en temps réel la trajectoire de chaque véhicule et piéton, de manière fluide, d’une
-
Microsoft Copilot Vision gains user traction and positive reception
By
–
Definitely digging Microsoft Copilot Vision right now.
-
AI Music Video Generation: Rapping Completed Successfully
By
–
3. Music video – rapping done, clean output! pic.twitter.com/9NYQZCuxQQ
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 14 juin 20253. Music video – rapping done, clean output!
-
Speak AI Transforms Selfies into Realistic Full-Body Videos
By
–
This changes everything.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 14 juin 2025
AI can now turn a single selfie into a full-body video that walks, talks, and performs like a real human.
It’s called Speak — the latest breakthrough from @higgsfield_ai.
Upload one photo. Get a hyper-realistic AI actor in motion.
Here are 10 stunning… pic.twitter.com/TSuL3zREcVThis changes everything. AI can now turn a single selfie into a full-body video that walks, talks, and performs like a real human. It’s called Speak — the latest breakthrough from @higgsfield_ai
. Upload one photo. Get a hyper-realistic AI actor in motion. Here are 10 stunning