Meta AI

Episodes:

• | AI at Meta 2026-02-27 02:52:14
• Introducing SAM Audio: The First Unified Multimodal Model for Audio Separation | AI at Meta 2025-12-17 01:26:54
• SAM 3: Building a unified model architecture for detection and tracking 2025-12-09 02:57:07
• Personalized Rehab with AI 2025-11-27 00:07:47
• How AI is helping animal conservation | AI at Meta 2025-11-25 02:27:10
• Introducing the Segment Anything Playground | AI at Meta 2025-11-22 04:58:41
• SAM 3D: Behind the two-model design | AI at Meta 2025-11-21 04:53:06
• SAM 3: Under the hood of the data engine | AI at Meta 2025-11-21 00:27:29
• Introducing SAM 3D: a New Standard for 3D Object & Human Reconstruction from a Single Image 2025-11-20 00:41:42
• Introducing Meta Segment Anything Model 3 (SAM 3): Unified Detection, Segmentation & Tracking 2025-11-20 00:31:19
• Introducing SAM 3 + SAM 3D AI at Meta 2025-11-20 00:24:03
• Introducing Meta Omnilingual Automatic Speech Recognition | Transcription for 1,600+ languages 2025-11-11 02:14:44
• Introducing DINOv3: Self-supervised learning for vision at unprecedented scale 2025-08-15 00:34:16
• Open Molecules 2025 and Meta’s Universal Model for Atoms: Design at the Atomic Scale | AI at Meta 2025-05-16 02:43:30
• Unlocking How the Human Brain Develops Language | AI at Meta 2025-05-16 02:40:13
• Adjoint Sampling: A Breakthrough in Highly Scalable, Reward-Driven Generative Modeling | AI at Meta 2025-05-16 02:34:52
• New Research: Molecular Property Prediction, Language Processing, and Neuroscience | AI at Meta 2025-05-16 02:32:01
• Built with Llama: Solo Tech | AI at Meta 2025-05-13 02:27:26
• Meta PARTNR: Unlocking Human-Robot Collaboration 2025-02-07 22:00:21
• Advancing robotics and touch perception | AI Research from Meta FAIR 2024-11-01 00:08:47
• Knowledge Distillation with Llama 3.1 405B | Llama for Developers 2024-10-19 01:14:57
• Behind the scenes with Blumhouse x Meta Movie Gen 2024-10-17 23:00:19
• Open Approach to Trust & Safety: Llama Guard 3, Prompt Guard & More | Llama for Developers 2024-08-09 23:15:01
• Meet Llama 3.1 2024-07-25 00:00:48
• Understanding the Meta Llama 3 Tokenizer | Llama for Developers 2024-06-29 00:01:19
• More ways to run Llama 3 | Build with Meta Llama 2024-05-24 00:00:34
• Run Llama 3 on Linux | Build with Meta Llama 2024-05-24 00:00:26
• Run Llama 3 on Windows | Build with Meta Llama 2024-05-24 00:00:01
• Run Llama 3 on Mac | Build with Meta Llama 2024-05-24 00:00:00
• 10 Years of Advancing the State-of-the-Art through Open Science at FAIR | AI at Meta 2023-12-06 00:00:17
• Reimagining Meta's Infrastructure for the AI Age | Meta AI 2023-05-19 23:00:12
• AI Infra @Scale | Meta AI - 翻译完成 (摘要已翻译) 2023-05-19 14:44:20
• MSVP - Meta's First In-House Silicon for Video Processing | Meta AI 2023-05-19 01:35:00
• MTIA - Meta's First-Generation AI Inference Accelerator | Meta AI 2023-05-19 01:20:00
• Accelerating Research with Meta's Research SuperCluster | Meta AI 2023-05-19 00:30:05
• Origin Stories | Meta AI 2023-04-08 01:37:24
• Inside the Lab: Building for the metaverse with AI (2022) | Meta AI 2022-12-13 06:43:22
• CICERO from the research team’s POV | Meta AI 2022-12-07 01:00:20
• CICERO as a Diplomacy partner | Meta AI 2022-12-06 01:00:07
• Speaking of CICERO with Mike Lewis | Meta AI 2022-11-30 01:00:01
• Diplomacy Gameplay with CICERO | Meta AI 2022-11-29 01:00:27
• CICERO & Strategic Reasoning with Noam Brown and Anton Bakhtin | Meta AI 2022-11-24 03:53:32
• Milestones to CICERO | Meta AI 2022-11-23 01:00:36
• CICERO: The first AI to play Diplomacy at a human level | Meta AI 2022-11-22 23:15:49
• Is human led mathematics over? Panel with Joelle Pineau, Timothy Gowers & Yann LeCun | Meta AI - 翻译完成 (摘要已翻译) 2022-11-03 21:41:10
• The first AI-powered speech translation system for a primarily oral language | Meta AI 2022-10-19 23:00:18
• Make-A-Scene: Mike Schroepfer talks with Oran Gafni about text and sketch prompts 2022-08-02 23:23:51
• NLLB: Schrep talks with Necip Fazil Ayan about inclusion through the power of AI 2022-08-02 23:22:14
• Make-A-Scene: Greater creative control for AI image generation. 2022-07-14 22:44:58
• 200 languages within a single AI model: A breakthrough in high-quality machine translation 2022-07-06 21:02:10
• Acoustic synthesis for AR/VR experiences 2022-06-24 22:25:02
• Studying the brain to build AI that processes language as people do 2022-04-29 02:50:20
• AI for clean energy: Mike Schroepfer talks to Larry Zitnick about Open Catalyst 2022-04-18 22:00:11
• Using AI to deliver more inclusive biographical content on Wikipedia 2022-03-31 20:34:52
• Project CAIRaoke: Breakthrough conversational AI that makes talking to assistants more enjoyable 2022-02-24 02:09:14
• Teaching AI to translate 100s of spoken and written languages in real time 2022-02-24 02:02:23
• Builder Bot demo 2022-02-24 01:39:58
• Introducing the AI Research SuperCluster — Meta’s cutting-edge supercomputer for AI research 2022-01-24 21:10:21
• Harmful content can evolve rapidly and it’s crucial for AI systems to evolve alongside it. 2021-12-11 02:30:21
• Building diverse MiniHack environments with just a few lines of code 2021-12-04 01:46:12
• Habitat 2.0: Training home assistants to rearrange their habitat 2021-11-23 02:08:52
• Zero-shot transfer to Formula 1 racetracks 2021-11-23 02:08:11
• Ego4D: Teaching AI to perceive the world through your eyes 2021-10-14 20:00:13
• AI now enables robots to adapt rapidly to changing real world conditions 2021-07-09 20:55:53
• PyTorchVideo: A deep learning library for video understanding 2021-05-19 02:34:33
• Expire-Span: Teaching AI How to Forget at Scale 2021-05-14 23:30:33
• Advancing the state of the art in computer vision with self-supervised Vision Transformers 2021-05-01 00:29:43
• How can we make sure that AI systems operate fairly for everyone? 2021-03-31 21:48:48
• How can we teach AI skills using visual demos? Model-based Inverse Reinforcement Learning 2021-01-27 23:25:37
• Mike Schroepfer @Schrep chats "AI 101 with Joelle Pineau" co-lead of the Facebook AI Research lab. 2021-01-26 07:02:45
• How does AI learn to finish your sentences? Learn about Smart Compose 2021-01-22 05:24:21
• How AI is getting better at detecting hate speech 2020-11-20 03:00:07
• The first AI model that translates 100 languages without relying on English data 2020-10-19 23:33:20
• FastMRI breakthrough shows AI-accelerated MRIs interchangeable with traditional MRIs 2020-09-02 06:34:14
• New milestones in embodied AI 2020-08-28 01:07:15
• Building 3D deep learning models with PyTorch3D 2020-06-15 05:57:10
• Powered by AI: Engineering new shopping experiences 2020-05-21 00:51:04
• The evolution of deep learning and PyTorch 2020-03-12 00:00:17
• Facebook AI Research 2020-03-05 05:57:37
• Facebook AI Research | Excellence 2020-03-04 00:42:07
• Facebook AI Research | Freedom 2020-03-04 00:42:04
• Facebook AI Research | Openness 2020-03-04 00:42:00
• Facebook AI Research | Scale 2020-03-04 00:41:57
• Building richer, real-world data sets to push conversational research forward 2020-01-24 00:56:03
• Yann LeCun on the future of deep learning hardware 2020-01-17 06:58:56
• Making conversation models more empathic 2019-11-27 04:33:50
• LIGHT, a multi-player crowdsourced text adventure game for dialogue research 2019-11-27 03:54:13
• Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker 2019-11-27 02:58:39
• Detectron2: A PyTorch-based modular object detection library 2019-11-27 02:58:34
• Powered by AI: How we’ve advanced Smart Camera for new Portal video-calling devices 2019-11-27 02:58:30
• Powered by AI: Oculus Insight 2019-11-27 02:58:25
• Creating real-time depth maps for occlusions in AR 2019-11-27 02:58:16
• Open-sourcing AI Habitat, an advanced simulation platform for embodied AI research 2019-11-27 02:58:12