Highlights and News

LAMP, our language-assisted motion planning framework for controllable video generation, was accepted to CVPR 2026.

We received an NVIDIA Academic Grant to support our research in generative and multimodal visual intelligence.

Our work on spherical vision transformers for audio-visual saliency prediction in 360-degree videos was accepted for publication in IEEE TPAMI.

We released GaussianVideo, an efficient video representation based on hierarchical Gaussian splatting.

Awarded funding from TUBITAK 2247-A National Outstanding Researchers Program on generative AI approaches to visual data generation.

Our work on diffusion-based object removal from images accepted to NeurIPS 2024 as a poster presentation.

Our work on a GAN-based unified framework for domain adaptation, image synthesis and manipulation accepted to SIGGRAPH Asia 2024.

Our work on sequential compositional generalization in multimodal models accepted to NAACL 2024 as an oral presentation.

Our work on evaluating zero-shot linguistic and temporal understanding capabilities of video-language models accepted to ICLR 2024.

Our work on 360-degree video saliency prediction accepted to BMVC 2023.

Our paper on video editing is accepted to ICCV 2023: VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs. Read more about our paper at our project website.

Our work on StyleGAN and CLIP-based text-guided image manipulation has been accepted for publication in ACM Transactions on Graphics. We will be presenting our work at SIGGRAPH Asia 2023 at Sydney.

I received a gift fund from Adobe Research to work on text-guided image synthesis and editing. I will be collaborating with Duygu Ceylan of Adobe Research and Erkut Erdem in this exciting project. Thanks Adobe!

We are organizing the first Workshop on Multimodal, Multilingual NLG (MM-NLG) at INLG/SIGDial 2023 in September 2023.

BIG-bench paper has been accepted for publication in Transactions on Machine Learning Research.

Our work on omnidirectional image quality assessment got accepted to ICASSP 2023.

We ranked 2nd in the euphemism detection shared task organized by the Figurative Language Processing workshop at EMNLP 2022.