Svetlana Lazebnik

University of Illinois Urbana-Champaign — United States

Computer Science · Physical Sciences

54h-index28.2kcitations152works6.42yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(81), Multimodal Machine Learning Applications(51), Image Retrieval and Classification Techniques(40), Domain Adaptation and Few-Shot Learning(31), Advanced Neural Network Applications(16)

Publications152 total

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
arXiv (Cornell University)·2025Open Access
A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards
2025· 6 cited
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
2025· 7 cited
A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards
arXiv (Cornell University)·2025Open Access
UnZipLoRA: Separating Content and Style from a Single Image
arXiv (Cornell University)·2024Open Access
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
Lecture notes in computer science·2024· 29 cited
Combining Multiple Cues for Visual Madlibs Question Answering
UNC Libraries·2024Open Access
Shadows Don't Lie and Lines Can't Bend! Generative Models Don't know Projective Geometry…for Now
2024· 16 cited
In Memoriam: Xiaoou Tang
International Journal of Computer Vision·2024Open Access
Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
arXiv (Cornell University)·2023Open Access
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
arXiv (Cornell University)·2023· 1 citedOpen Access
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
ArXiv.org·2023· 5 citedOpen Access
JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
arXiv (Cornell University)·2023Open Access
One-Shot Stylization for Full-Body Human Images
arXiv (Cornell University)·2023Open Access
Robust Online Video Instance Segmentation with Track Queries
arXiv (Cornell University)·2022· 1 citedOpen Access
MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GAN
arXiv (Cornell University)·2022Open Access
Transfer of Representations to Video Label Propagation: Implementation Factors Matter
arXiv (Cornell University)·2022· 2 citedOpen Access
Interpretation of Emergent Communication in Heterogeneous Collaborative\n Embodied Agents
arXiv (Cornell University)·2021Open Access
GridToPix: Training Embodied Agents with Minimal Supervision
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 12 cited
Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 58 cited
page 1 of 8Next →

Frequent Co-authors

C. Schmid(9), Jean Ponce(9), Yunchao Gong(8), Liwei Wang(8), Jianguo Zhang(5), Arun Mallya(5), Joseph Tighe(4), Alexander G. Schwing(4), Bryan A. Plummer(3), Juan Carlos Caicedo(3), Julia Hockenmaier(3), Jan‐Michael Frahm(3), Changchang Wu(3), Cordelia Schmid(3), Marcin Marszałek(3), Albert Gordo(2), Florent Perronnin(2), Chris M. Cervantes(2), Maxim Raginsky(2), Rahul Raguram(2)