Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hidir Yesiltepe

Hidir Yesiltepe

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×2AI×2

Frequent co-authors

Jiazhen Hu2×
Tuna Han Salih Meral2×
Adil Kaan Akan2×
Kaan Oktay2×
Hoda Eldardiry2×
Pinar Yanardag2×

Research Timeline

2026
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput for autoregressive video diffusion.

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput for autoregressive video diffusion.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentMay 28, 2026

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, Adil Kaan Akan +3 more

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

View →
cs.CVcs.AIRecentMay 28, 2026

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, Adil Kaan Akan +3 more

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

View →