Pinar Yanardag
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Vision×2AI×1
Frequent co-authors
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.
From Zero to Hero: Training-Free Custom Concept Spawning in World Models
The paper introduces SPAWN, a training-free method that allows users to inject specified visual concepts into existing autoregressive world models, enabling controllable scene composition beyond the initial reference frame.
Highlighted terms show continued research focus across papers
Papers
cs.CVRecentJun 1, 2026
From Zero to Hero: Training-Free Custom Concept Spawning in World Models
The paper introduces SPAWN, a training-free method that allows users to inject specified visual concepts into existing autoregressive world models, enabling controllable scene composition beyond the i…
View →
cs.CVcs.AIRecentMay 28, 2026