7 papers
Exact Posterior Score Estimation for Solving Linear Inverse Problems
Abbas Mammadov, Ozgur Kara, Kaan Oktay +5
Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to…
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral +4
Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the wi…
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Tuna Han Salih Meral, Kaan Oktay, Hidir Yesiltepe +2
Latent flow matching for image generation usually transports Gaussian noise to variational autoencoder latents along linear paths. Both endpoints, however, concentrate in thin sphe…
Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
Hidir Yesiltepe, Tuna Han Salih Meral, Adil Kaan Akan +2
Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding…
Learning Object-Centric Representations Based on Slots in Real World Scenarios
Adil Kaan Akan
A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat…
Compositional Video Synthesis by Temporal Object-Centric Learning
Adil Kaan Akan, Yucel Yemez
We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from ima…