Philipp Krähenbühl

Computer Science · Physical Sciences

45h-index21.5kcitations102works0.92yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(37), Advanced Image and Video Retrieval Techniques(29), Human Pose and Action Recognition(23), Domain Adaptation and Few-Shot Learning(19), Multimodal Machine Learning Applications(17)

Publications102 total

Compressed Map Priors for 3D Perception
arXiv (Cornell University)·2025Open Access
Compressed Map Priors for 3D Perception
ArXiv.org·2025Open Access
Spherical Leech Quantization for Visual Tokenization and Generation
arXiv (Cornell University)·2025Open Access
Latent Chain-of-Thought World Modeling for End-to-End Driving
arXiv (Cornell University)·2025Open Access
Triangle Multiplication Is All You Need For Biomolecular Structure Representations
arXiv (Cornell University)·2025Open Access
Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
arXiv (Cornell University)·2025Open Access
Interactive Post-Training for Vision-Language-Action Models
arXiv (Cornell University)·2025Open Access
QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
arXiv (Cornell University)·2025Open Access
Robust Autonomy Emerges from Self-Play
arXiv (Cornell University)·2025Open Access
Reinforcement Learning for Long-Horizon Interactive LLM Agents
arXiv (Cornell University)·2025Open Access
Cut Your Losses in Large-Vocabulary Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Distilling Structural Representations into Protein Sequence Models
2024· 6 citedOpen Access
Promptable Closed-loop Traffic Simulation
arXiv (Cornell University)·2024Open Access
Language-Conditioned Detection Transformer
2024· 2 cited
Distilling Vision-Language Models on Millions of Videos
2024· 5 cited
Image and Video Tokenization with Binary Spherical Quantization
arXiv (Cornell University)·2024Open Access
Language-Image Models with 3D Understanding
arXiv (Cornell University)·2024Open Access
Distilling Vision-Language Models on Millions of Videos
arXiv (Cornell University)·2024· 2 citedOpen Access
Language-conditioned Detection Transformer
arXiv (Cornell University)·2023Open Access
Predicting a Protein's Stability under a Million Mutations
arXiv (Cornell University)·2023· 15 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Vladlen Koltun(12), Xingyi Zhou(12), Chao-Yuan Wu(9), Alexei A. Efros(7), Trevor Darrell(5), Tianwei Yin(4), Andreas Hornung(3), Jun-Yan Zhu(3), Eli Shechtman(3), R. Manmatha(3), Alexander J. Smola(3), Dequan Wang(3), Jeff Donahue(3), Christoph Feichtenhofer(3), Kaiming He(3), Ross Girshick(3), Tinghui Zhou(3), Qixing Huang(3), Jiacheng Zhuo(2), Rohit Girdhar(2)