7 citations · 17 across the 13 of their papers we have counts for
15 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…
Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
Adil Kaan Akan, Yucel Yemez
We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our metho…
ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation
Görkay Aydemir, Adil Kaan Akan, Fatma Güney
Forecasting future trajectories of agents in complex traffic scenes requires reliable and efficient predictions for all agents in the scene. However, existing methods for trajector…
Stochastic Future Prediction in Real World Driving Scenarios
Adil Kaan Akan
Uncertainty plays a key role in future prediction. The future is uncertain. That means there might be many possible futures. A future prediction method should cover the whole possi…
Trajectory Forecasting on Temporal Graphs
Görkay Aydemir, Adil Kaan Akan, Fatma Güney
Predicting future locations of agents in the scene is an important problem in self-driving. In recent years, there has been a significant progress in representing the scene and the…
Stochastic Video Prediction with Structure and Motion
Adil Kaan Akan, Sadra Safadoust, Fatma Güney
While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot p…
StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
Adil Kaan Akan, Fatma Güney
In self-driving, predicting future in terms of location and motion of all the agents around the vehicle is a crucial requirement for planning. Recently, a new joint formulation of…
SLAMP: Stochastic Latent Appearance and Motion Prediction
Adil Kaan Akan, Erkut Erdem, Aykut Erdem +1
Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is det…
Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation
Adil Kaan Akan, Emre Akbas, Fatos T. Yarman Vural
In this study, we introduce a measure for machine perception, inspired by the concept of Just Noticeable Difference (JND) of human perception. Based on this measure, we suggest an…
Just Noticeable Difference for Machines to Generate Adversarial Images
Adil Kaan Akan, Mehmet Ali Genc, Fatos T. Yarman Vural
One way of designing a robust machine learning algorithm is to generate authentic adversarial images which can trick the algorithms as much as possible. In this study, we propose a…