Antonio Torralba

Computer Science · Physical Sciences

123h-index97.2kcitations542works7.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(142), Multimodal Machine Learning Applications(104), Generative Adversarial Networks and Image Synthesis(79), Image Retrieval and Classification Techniques(70), Advanced Vision and Imaging(57)

Publications541 total

VideoSketcher: Video Models Prior Enable Versatile Sequential Sketch Generation
arXiv (Cornell University)·2026Open Access
VideoSketcher: Video Models Prior Enable Versatile Sequential Sketch Generation
ArXiv.org·2026Open Access
Fairness Aware Reward Optimization
ArXiv.org·2026Open Access
Fairness Aware Reward Optimization
arXiv (Cornell University)·2026Open Access
Ambient Dataloops: Generative Models for Dataset Refinement
ArXiv.org·2026Open Access
Ambient Dataloops: Generative Models for Dataset Refinement
arXiv (Cornell University)·2026Open Access
Motion Attribution for Video Generation
arXiv (Cornell University)·2026Open Access
Motion Attribution for Video Generation
ArXiv.org·2026Open Access
VirtualEnv: A Platform for Embodied AI Research
ArXiv.org·2026Open Access
VirtualEnv: A Platform for Embodied AI Research
arXiv (Cornell University)·2026Open Access
Dataset Distillation for Pre-Trained Self-Supervised Vision Models
arXiv (Cornell University)·2025Open Access
Generalized Dynamics Generation towards Scannable Physical World Model
arXiv (Cornell University)·2025Open Access
DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
arXiv (Cornell University)·2025Open Access
MultiModal Action Conditioned Video Generation
arXiv (Cornell University)·2025Open Access
Separating Knowledge and Perception with Procedural Data
arXiv (Cornell University)·2025Open Access
Single-pass Adaptive Image Tokenization for Minimum Program Search
arXiv (Cornell University)·2025Open Access
Eval3D: Interpretable and Fine-Grained Evaluation for 3D Generation
2025· 1 cited
Ambient Diffusion Omni: Training Good Models with Bad Data
arXiv (Cornell University)·2025Open Access
SketchAgent: Language-Driven Sequential Sketch Generation
2025· 4 cited
Compositional Physical Reasoning of Objects and Events From Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 3 cited
page 1 of 28Next →

Frequent Co-authors

Aude Oliva(17), Bolei Zhou(9), Aditya Khosla(8), Àgata Lapedriza(6), William T. Freeman(6), Hang Zhao(5), Carl Vondrick(5), Jianxiong Xiao(4), Sanja Fidler(4), Jenny Yuen(4), Hamed Pirsiavash(4), Kevin Murphy(3), Rob Fergus(3), Bryan Russell(2), Krista A. Ehinger(2), Xavier Puig(2), Adela Barriuso(2), Alexei A. Efros(2), Yair Weiss(2), Yukun Zhu(2)