Alexei A. Efros

Berkeley College — United States

Computer Science · Physical Sciences

99h-index89.2kcitations306works6.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(103), Advanced Vision and Imaging(99), Generative Adversarial Networks and Image Synthesis(89), Domain Adaptation and Few-Shot Learning(38), Human Pose and Action Recognition(33)

Publications306 total

It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
arXiv (Cornell University)·2025Open Access
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
ArXiv.org·2025Open Access
Fast Data Attribution for Text-to-Image Models
arXiv (Cornell University)·2025Open Access
The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio
arXiv (Cornell University)·2025Open Access
Continuous 3D Perception Model with Persistent State
2025· 10 cited
GPS as a Control Signal for Image Generation
2025· 1 cited
Vision Transformers Don't Need Trained Registers
arXiv (Cornell University)·2025· 1 citedOpen Access
Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
arXiv (Cornell University)·2025Open Access
Continuous 3D Perception Model with Persistent State
arXiv (Cornell University)·2025Open Access
GPS as a Control Signal for Image Generation
arXiv (Cornell University)·2025Open Access
Diffusion Models as Data Mining Tools
Lecture notes in computer science·2024· 1 cited
Prioritized Generative Replay
arXiv (Cornell University)·2024Open Access
IT$^3$: Idempotent Test-Time Training
arXiv (Cornell University)·2024Open Access
Evaluating Multiview Object Consistency in Humans and Image Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Diffusion Models as Data Mining Tools
arXiv (Cornell University)·2024Open Access
COLMAP-Free 3D Gaussian Splatting
2024· 85 cited
Sequential Modeling Enables Scalable Learning for Large Vision Models
2024· 70 cited
Interpreting the Weight Space of Customized Diffusion Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
arXiv (Cornell University)·2024Open Access
Rethinking Score Distillation as a Bridge Between Image Distributions
arXiv (Cornell University)·2024Open Access
page 1 of 16Next →

Frequent Co-authors

Phillip Isola(9), Richard Zhang(9), Jun-Yan Zhu(7), Martial Hebert(6), Trevor Darrell(6), Eli Shechtman(5), Oliver Wang(5), Tinghui Zhou(5), Josef Šivic(5), Derek Hoiem(5), Deepak Pathak(5), Jitendra Malik(5), Taesung Park(4), Abhinav Gupta(4), Bryan Russell(4), James Hays(4), William T. Freeman(3), Philipp Krähenbühl(3), Andrew Zisserman(3), Shubham Tulsiani(3)