TheSequence - Edge 441: SSMs Beyond Language
Was this email forwarded to you? Sign up here
In this issue:
💡 ML Concept of the Day: SSMs Beyond LanguageThroughout this series, we have explored the fundamentals latest research in state space models(SSMs) as one of the main alternatives to transformer architectures. SSMs provide a more efficient scaling mechanism than transformers which makes it ideal for models with large context windows. Given the state of the market, the core focus on SSMs have been in LLMs but, surprisingly, some of the core applications of SSMs are surfacing in other modalities. Take audio, for instance, SSMs have emerged as one 3of the most efficient techniques in this modality given its efficiency processing continuous irregular continuous data. Models like AudioMamba , RawMamba and some of the work done by Cartesia are great examples of SSMs applied to audio... Subscribe to TheSequence to unlock the rest.Become a paying subscriber of TheSequence to get access to this post and other subscriber-only content. A subscription gets you:
|
Older messages
The Sequence Chat: Why Transformers are the Best Thing that Ever Happened to NVIDIA
Monday, October 21, 2024
A discussion about some controvertial and original ideas in AI. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
NVIDIA Releases Nemotron 70B
Sunday, October 20, 2024
The new model has been making the headlines due to its impressive performance. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
AI Dropped the Mic at the Nobel Party
Sunday, October 20, 2024
Two Nobel Prizes were awarded to AI scientists ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Edge 439: SSMs with Attention, Understanding Zamba
Sunday, October 20, 2024
Combining the best of SSMs and transformers in a single architecture. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Edge 440: Interested in AI Evaluation? Meet Microsoft's EUREKA
Sunday, October 20, 2024
The framework provides an evaluation pipeline as well as a collection of benchmarks for evaluating language and vision capabilities. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
You Might Also Like
Christmas On Repeat 🎅
Monday, December 23, 2024
Christmas nostalgia is a hell of a drug. Here's a version for your browser. Hunting for the end of the long tail • December 22, 2024 Hey all, Ernie here with a refresh of a piece from our very
SRE Weekly Issue #456
Monday, December 23, 2024
View on sreweekly.com A message from our sponsor, FireHydrant: On-call during the holidays? Spend more time taking in some R&R and less getting paged. Let alerts make their rounds fairly with our
The Power of an Annual Review & Grammarly acquires Coda
Sunday, December 22, 2024
I am looking for my next role, Zen Browser got a fresh new look, Flipboard introduces Surf, Campsite shuts down, and a lot more in this week's issue of Creativerly. Creativerly The Power of an
Daily Coding Problem: Problem #1645 [Hard]
Sunday, December 22, 2024
Daily Coding Problem Good morning! Here's your coding interview problem for today. This problem was asked by Facebook. Implement regular expression matching with the following special characters: .
PD#606 How concurrecy works: A visual guide
Sunday, December 22, 2024
A programmer had a problem. "I'll solve it with threads!". has Now problems. two he ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
RD#486 (React) Things I Regret Not Knowing Earlier
Sunday, December 22, 2024
Keep coding, stay curious, and remember—you've got this
🎶 GIFs Are Neat, but I Want Clips With Sound — Your Own Linux Desktop in the Cloud
Sunday, December 22, 2024
Also: 9 Games That Were Truly Ahead of Their Time, and More! How-To Geek Logo December 22, 2024 Did You Know Dextrose is another name for glucose, so if you see it listed prominently on the ingredients
o3—the new state-of-the-art reasoning model - Sync #498
Sunday, December 22, 2024
Plus: Nvidia's new tiny AI supercomputer; Veo 2 and Imagen 3; Google and Microsoft release reasoning models; Waymo to begin testing in Tokyo; Apptronik partners with DeepMind; and more! ͏ ͏ ͏ ͏ ͏ ͏
Sunday Digest | Featuring 'The World’s 20 Largest Economies, by GDP (PPP)' 📊
Sunday, December 22, 2024
Every visualization published this week, in one place. Dec 22, 2024 | View Online | Subscribe | VC+ | Download Our App Hello, welcome to your Sunday Digest. This week, we visualized public debt by
Android Weekly #654 🤖
Sunday, December 22, 2024
View in web browser 654 December 22nd, 2024 Articles & Tutorials Sponsored Solving ANRs with OpenTelemetry While OpenTelemetry is the new observability standard, it lacks official support for many