"As AI continues to permeate various sectors, from healthcare to autonomous vehicles, the need for models that can deliver high performance without excessive resource consumption becomes increasingly important." Read the official blog from Bilge Basakcioglu Soran, PhD and Yunyang Xiong from Meta as they dive deeply into AI efficiency. They will introduce two innovative approaches addressing AI challenges: EfficientSAM and SqueezeSAM. Find it here: https://lnkd.in/gbauHVtu
@Scale
Software Development
Menlo Park , CA 2,577 followers
@Scale is a series of technical conferences for engineers working with systems that are designed for scale.
About us
@Scale is a series of technical conferences for engineers who build or maintain systems that are designed for scale. Building applications and services that scale to millions or even billions of people presents a complex set of engineering challenges, many of them unprecedented. The @Scale community is focused on bringing people together to openly discuss these challenges and collaborate on the development of new solutions across a series of topics
- Website
-
https://atscaleconference.com/
External link for @Scale
- Industry
- Software Development
- Company size
- 2-10 employees
- Headquarters
- Menlo Park , CA
- Type
- Nonprofit
Locations
-
Primary
Menlo Park , CA 94025, US
Updates
-
🌐 Come learn about how Meta has improved the collection of the largest video segmentation dataset to date! Segment Anything Model 2 (SAM 2) is now here and it’s 6x faster than the original. Chay Ryali from Meta gave insights at Video @Scale 2024 that will serve as a significant milestone for video segmentation and related perception tasks. 🎥 Watch his session today: https://lnkd.in/gcxXAKi3
-
🔎 Let's take a deeper look into foundational models for video generation, editing, personalization and audio generation. Check out Ishan Misra's blog on the official @Scale website: https://lnkd.in/gme9Ehhe
-
💪 EfficientSAM may be small, but it’s mighty. “Efficient Segment Anything” by Bilge Soran and Yunyang Xiong from Meta is now available for on-demand viewing! Check it out here: https://lnkd.in/gHHDQcUF To view this session, and many others from the 2-day conference designed for engineers who develop or manage large-scale video systems serving millions of people, visit our Youtube channel today: https://lnkd.in/gsTQcQnq
-
🚀 Excited about the future of mobile video playback? Wen Li from Meta presented “On-Device Video Playback Upsampling” at Video @Scale 2024 and explored how advanced video upsampling technologies transform how videos are streamed to mobile devices. Interested in learning more? Read his blog on the @Scale website for more information! 🧾: https://lnkd.in/gjbMRfd9
-
💡 Discover the power of advanced video input pre-filtering in modern production workflow! Originally used to reduce noise in low-quality video, these techniques have evolved to enhance even pristine content. Tune into “Rethinking the Video Transcoding Pipeline: How Pre-Filtering Holds the Key to Efficiency and Quality” by Ramzi Khsib from Amazon Web Services (AWS), and explore how AWS Elemental's new pre-filtering solution improves video quality by reducing file sizes without compromising visual fidelity, while tackling common issues like softness and deblocking. Learn how this technology enables efficient, high-quality video delivery for everything from streaming to broadcast, and gain practical insights for optimizing your own workflows. 🔎 Watch the full session here: https://lnkd.in/gZ8ySavP
-
🚀 Segment Anything Model 2 (SAM 2) is now here and it’s 6x faster than the original! Come learn about the foundation model solving promotable visual segmentation in images and videos and the data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Tune in as Chay Ryali from Meta gives insights that will serve as a significant milestone for video segmentation and related perception tasks. 💡 Watch the full session from Video @Scale here: https://lnkd.in/g8WiGSpQ
-
🤝 Image, video, and audio generation are a fundamental building block for Generative AI research and applications in the real world. In this talk, Ishan Misra from Meta discussed a set of foundational models for video generation, editing, personalization and audio generation. 👀 Watch the full session from Video @Scale here: https://lnkd.in/gmk736Hn
-
🎥 Thank you to all who joined us for Video @Scale 2024! If you missed our sessions, or want to revisit something you saw, our videos are now available on-demand on our YouTube channel: https://lnkd.in/gH2mWupX A huge thank you to our speakers, planning, and production crew. ✨ We can't wait to reveal what we have in store for 2025; stay tuned!