Sign up to save your podcasts
Or
Share [short] MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
[short] MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Proposed MoE-tuning strategy for Large Vision-Language Models (LVLMs) creates a sparse model with constant computational cost, addressing performance degradation and reducing hallucinations.
https://arxiv.org/abs//2401.15947
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
View all episodes
By Igor Melnyk
5
33 ratings
Proposed MoE-tuning strategy for Large Vision-Language Models (LVLMs) creates a sparse model with constant computational cost, addressing performance degradation and reducing hallucinations.
https://arxiv.org/abs//2401.15947
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
More shows like Arxiv Papers
View all
Exchanges
962 Listeners
Odd Lots
1,986 Listeners
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
436 Listeners
The Daily
112,842 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
10,104 Listeners
Hard Fork
5,539 Listeners
UnHerd with Freddie Sayers
216 Listeners
Unsupervised Learning with Jacob Effron
51 Listeners
Latent Space: The AI Engineer Podcast
99 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
475 Listeners