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

Adil Kaan Akan

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Vision×3AI×2ML×1Stats ML×1

Frequent co-authors

Kaan Oktay3×
Hidir Yesiltepe2×
Jiazhen Hu2×
Tuna Han Salih Meral2×
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.

Exact Posterior Score Estimation for Solving Linear Inverse Problems

The paper presents a new method called Exact Posterior Score (EPS) for solving linear inverse problems using diffusion and flow-based models.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CVstat.MLEmpiricalRecentJun 15, 2026

Exact Posterior Score Estimation for Solving Linear Inverse Problems

Abbas Mammadov, Ozgur Kara, Kaan Oktay, Iskander Azangulov +4 more

The paper presents a new method called Exact Posterior Score (EPS) for solving linear inverse problems using diffusion and flow-based models.

View →
cs.CVcs.AIRecent
May 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 →