Philipp Krähenbühl

117 papers A* 35A 1Misc 3Journal 63Unranked 14

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Compressed Map Priors for 3D Perception. CoRR Brady Zhou, Philipp Krähenbühl
2026	J	`jnl`	Entropy-Preserving Reinforcement Learning. CoRR Aleksei Petrenko, Ben Lipkin, Kevin Chen, Erik Wijmans, Marco F. Cusumano-Towner, Raja Giryes, Philipp Krähenbühl
2025	A*	`conf`	Cut Your Losses in Large-Vocabulary Language Models. ICLR Erik Wijmans, Brody Huval, Alexander Hertzberg, Vladlen Koltun, Philipp Krähenbühl
2025	A*	`conf`	Distilling Structural Representations into Protein Sequence Models. ICLR Jeffrey Ouyang-Zhang, Chengyue Gong, Yue Zhao, Philipp Krähenbühl, Adam R. Klivans, Daniel Jesus Diaz
2025	A*	`conf`	Does Spatial Cognition Emerge in Frontier Models? ICLR Santhosh Kumar Ramakrishnan, Erik Wijmans, Philipp Krähenbühl, Vladlen Koltun
2025	A*	`conf`	Image and Video Tokenization with Binary Spherical Quantization. ICLR Yue Zhao, Yuanjun Xiong, Philipp Krähenbühl
2025	J	`jnl`	Interactive Post-Training for Vision-Language-Action Models. CoRR Shuhan Tan, Kairan Dou, Yue Zhao, Philipp Krähenbühl
2025	A*	`conf`	Language-Image Models with 3D Understanding. ICLR Jang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krähenbühl, Yan Wang, Marco Pavone
2025	J	`jnl`	Latent Chain-of-Thought World Modeling for End-to-End Driving. CoRR Shuhan Tan, Kashyap Chitta, Yuxiao Chen, Ran Tian, Yurong You, Yan Wang, Wenjie Luo, Yulong Cao, Philipp Krähenbühl, Marco Pavone, Boris Ivanovic
2025	J	`jnl`	Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation. CoRR Xiuyu Yang, Shuhan Tan, Philipp Krähenbühl
2025	J	`jnl`	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding. CoRR Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi, Triantafyllos Afouras, Tushar Nagarajan, Muhammad Maaz, Yale Song, Tengyu Ma, Shuming Hu, Suyog Dutt Jain, Miguel Martin, Huiyu Wang, Hanoona Abdul Rasheed, Peize Sun, Po-Yao Huang, Daniel Bolya, Nikhila Ravi, Shashank Jain, Tammy Stark, Shane Moon, Babak Damavandi, Vivian Lee, Andrew Westbury, Salman H. Khan, Philipp Krähenbühl, Piotr Dollár, Lorenzo Torresani, Kristen Grauman, Christoph Feichtenhofer
2025	J	`jnl`	QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation. CoRR Yue Zhao, Fuzhao Xue, Scott Reed, Linxi Fan, Yuke Zhu, Jan Kautz, Zhiding Yu, Philipp Krähenbühl, De-An Huang
2025	J	`jnl`	Reinforcement Learning for Long-Horizon Interactive LLM Agents. CoRR Kevin Chen, Marco F. Cusumano-Towner, Brody Huval, Aleksei Petrenko, Jackson Hamburger, Vladlen Koltun, Philipp Krähenbühl
2025	A*	`conf`	Robust Autonomy Emerges from Self-Play. ICML Marco Francis Cusumano-Towner, David Hafner, Alexander Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor W. Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun
2025	J	`jnl`	Robust Autonomy Emerges from Self-Play. CoRR Marco F. Cusumano-Towner, David Hafner, Alexander Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor W. Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun
2025	J	`jnl`	Spherical Leech Quantization for Visual Tokenization and Generation. CoRR Yue Zhao, Hanwen Jiang, Zhenlin Xu, Chutong Yang, Ehsan Adeli, Philipp Krähenbühl
2025	J	`jnl`	Triangle Multiplication Is All You Need For Biomolecular Structure Representations. CoRR Jeffrey Ouyang-Zhang, Pranav Murugan, Daniel Jesus Diaz, Gianluca Scarpellini, Richard Strong Bowen, Nate Gruver, Adam R. Klivans, Philipp Krähenbühl, Aleksandra Faust, Maruan Al-Shedivat
2024	J	`jnl`	Cut Your Losses in Large-Vocabulary Language Models. CoRR Erik Wijmans, Brody Huval, Alexander Hertzberg, Vladlen Koltun, Philipp Krähenbühl
2024	A*	`conf`	Distilling Vision-Language Models on Millions of Videos. CVPR Yue Zhao, Long Zhao, Xingyi Zhou, Jialin Wu, Chun-Te Chu, Hui Miao, Florian Schroff, Hartwig Adam, Ting Liu, Boqing Gong, Philipp Krähenbühl, Liangzhe Yuan
2024	J	`jnl`	Distilling Vision-Language Models on Millions of Videos. CoRR Yue Zhao, Long Zhao, Xingyi Zhou, Jialin Wu, Chun-Te Chu, Hui Miao, Florian Schroff, Hartwig Adam, Ting Liu, Boqing Gong, Philipp Krähenbühl, Liangzhe Yuan
2024	J	`jnl`	Does Spatial Cognition Emerge in Frontier Models? CoRR Santhosh Kumar Ramakrishnan, Erik Wijmans, Philipp Krähenbühl, Vladlen Koltun
2024	J	`jnl`	Image and Video Tokenization with Binary Spherical Quantization. CoRR Yue Zhao, Yuanjun Xiong, Philipp Krähenbühl
2024	A*	`conf`	Language-Conditioned Detection Transformer. CVPR Jang Hyun Cho, Philipp Krähenbühl
2024	J	`jnl`	Language-Image Models with 3D Understanding. CoRR Jang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krähenbühl, Yan Wang, Marco Pavone
2024	Misc	`conf`	Promptable Closed-loop Traffic Simulation. CoRL Shuhan Tan, Boris Ivanovic, Yuxiao Chen, Boyi Li, Xinshuo Weng, Yulong Cao, Philipp Krähenbühl, Marco Pavone
2024	J	`jnl`	Promptable Closed-loop Traffic Simulation. CoRR Shuhan Tan, Boris Ivanovic, Yuxiao Chen, Boyi Li, Xinshuo Weng, Yulong Cao, Philipp Krähenbühl, Marco Pavone
2023	Misc	`conf`	Language Conditioned Traffic Generation. CoRL Shuhan Tan, Boris Ivanovic, Xinshuo Weng, Marco Pavone, Philipp Krähenbühl
2023	J	`jnl`	Language Conditioned Traffic Generation. CoRR Shuhan Tan, Boris Ivanovic, Xinshuo Weng, Marco Pavone, Philipp Krähenbühl
2023	J	`jnl`	Language-conditioned Detection Transformer. CoRR Jang Hyun Cho, Philipp Krähenbühl
2023	A*	`conf`	Learning Video Representations from Large Language Models. CVPR Yue Zhao, Ishan Misra, Philipp Krähenbühl, Rohit Girdhar
2023	J	`jnl`	Long-tail Detection with Effective Class-Margins. CoRR Jang Hyun Cho, Philipp Krähenbühl
2023	A*	`conf`	PartDistillation: Learning Parts from Instance Segmentation. CVPR Jang Hyun Cho, Philipp Krähenbühl, Vignesh Ramanathan
2023	A*	`conf`	Predicting a Protein's Stability under a Million Mutations. NeurIPS Jeffrey Ouyang-Zhang, Daniel Jesus Diaz, Adam R. Klivans, Philipp Krähenbühl
2023	J	`jnl`	Training a Large Video Model on a Single Machine in a Day. CoRR Yue Zhao, Philipp Krähenbühl
2022	A*	`conf`	Cross-view Transformers for real-time Map-view Semantic Segmentation. CVPR Brady Zhou, Philipp Krähenbühl
2022	J	`jnl`	Cross-view Transformers for real-time Map-view Semantic Segmentation. CoRR Brady Zhou, Philipp Krähenbühl
2022	—	`conf`	Detecting Twenty-Thousand Classes Using Image-Level Supervision. ECCV (9) Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
2022	J	`jnl`	Detecting Twenty-thousand Classes using Image-level Supervision. CoRR Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
2022	A*	`conf`	Global Tracking Transformers. CVPR Xingyi Zhou, Tianwei Yin, Vladlen Koltun, Philipp Krähenbühl
2022	J	`jnl`	Global Tracking Transformers. CoRR Xingyi Zhou, Tianwei Yin, Vladlen Koltun, Philipp Krähenbühl
2022	J	`jnl`	Learning Video Representations from Large Language Models. CoRR Yue Zhao, Ishan Misra, Philipp Krähenbühl, Rohit Girdhar
2022	A*	`conf`	Learning from All Vehicles. CVPR Dian Chen, Philipp Krähenbühl
2022	J	`jnl`	Learning from All Vehicles. CoRR Dian Chen, Philipp Krähenbühl
2022	—	`conf`	Long-tail Detection with Effective Class-Margins. ECCV (8) Jang Hyun Cho, Philipp Krähenbühl
2022	J	`jnl`	NMS Strikes Back. CoRR Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl
2022	—	`conf`	Real-Time Online Video Detection with Temporal Smoothing Transformers. ECCV (34) Yue Zhao, Philipp Krähenbühl
2022	J	`jnl`	Real-time Online Video Detection with Temporal Smoothing Transformers. CoRR Yue Zhao, Philipp Krähenbühl
2022	A*	`conf`	Simple Multi-dataset Detection. CVPR Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
2021	A*	`conf`	Center-Based 3D Object Detection and Tracking. CVPR Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
2021	A*	`conf`	Learning to drive from a world on rails. ICCV Dian Chen, Vladlen Koltun, Philipp Krähenbühl
2021	J	`jnl`	Learning to drive from a world on rails. CoRR Dian Chen, Vladlen Koltun, Philipp Krähenbühl
2021	A*	`conf`	Memory Optimization for Deep Networks. ICLR Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krähenbühl
2021	A*	`conf`	Multimodal Virtual Point 3D Detection. NeurIPS Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
2021	J	`jnl`	Multimodal Virtual Point 3D Detection. CoRR Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
2021	J	`jnl`	Probabilistic two-stage detection. CoRR Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
2021	J	`jnl`	Simple multi-dataset detection. CoRR Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
2021	A*	`conf`	Towards Long-Form Video Understanding. CVPR Chao-Yuan Wu, Philipp Krähenbühl
2021	J	`jnl`	Towards Long-Form Video Understanding. CoRR Chao-Yuan Wu, Philipp Krähenbühl
2020	A*	`conf`	A Multigrid Method for Efficiently Training Video Models. CVPR Chao-Yuan Wu, Ross B. Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl
2020	J	`jnl`	Center-based 3D Object Detection and Tracking. CoRR Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
2020	—	`conf`	Domain Adaptation Through Task Distillation. ECCV (26) Brady Zhou, Nimit Kalra, Philipp Krähenbühl
2020	J	`jnl`	Domain Adaptation Through Task Distillation. CoRR Brady Zhou, Nimit Kalra, Philipp Krähenbühl
2020	J	`jnl`	Lossless Image Compression through Super-Resolution. CoRR Sheng Cao, Chao-Yuan Wu, Philipp Krähenbühl
2020	J	`jnl`	Memory Optimization for Deep Networks. CoRR Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krähenbühl
2020	—	`conf`	Tracking Objects as Points. ECCV (4) Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
2020	J	`jnl`	Tracking Objects as Points. CoRR Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
2019	J	`jnl`	A Multigrid Method for Efficiently Training Video Models. CoRR Chao-Yuan Wu, Ross B. Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl
2019	A*	`conf`	Bottom-Up Object Detection by Grouping Extreme and Center Points. CVPR Xingyi Zhou, Jiacheng Zhuo, Philipp Krähenbühl
2019	J	`jnl`	Bottom-up Object Detection by Grouping Extreme and Center Points. CoRR Xingyi Zhou, Jiacheng Zhuo, Philipp Krähenbühl
2019	J	`jnl`	Does computer vision matter for action? CoRR Brady Zhou, Philipp Krähenbühl, Vladlen Koltun
2019	J	`jnl`	Does computer vision matter for action? Sci. Robotics Brady Zhou, Philipp Krähenbühl, Vladlen Koltun
2019	—	`conf`	Don't let your Discriminator be fooled. ICLR (Poster) Brady Zhou, Philipp Krähenbühl
2019	A*	`conf`	Joint Monocular 3D Vehicle Detection and Tracking. ICCV Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu
2019	Misc	`conf`	Learning by Cheating. CoRL Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl
2019	J	`jnl`	Learning by Cheating. CoRR Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl
2019	A*	`conf`	Long-Term Feature Banks for Detailed Video Understanding. CVPR Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross B. Girshick
2019	A	`conf`	Monocular Plan View Networks for Autonomous Driving. IROS Dequan Wang, Coline Devin, Qi-Zhi Cai, Philipp Krähenbühl, Trevor Darrell
2019	J	`jnl`	Monocular Plan View Networks for Autonomous Driving. CoRR Dequan Wang, Coline Devin, Qi-Zhi Cai, Philipp Krähenbühl, Trevor Darrell
2019	J	`jnl`	Objects as Points. CoRR Xingyi Zhou, Dequan Wang, Philipp Krähenbühl
2018	J	`jnl`	Assessing Generalization in Deep Reinforcement Learning. CoRR Charles Packer, Katelyn Gao, Jernej Kos, Philipp Krähenbühl, Vladlen Koltun, Dawn Song
2018	A*	`conf`	Compressed Video Action Recognition. CVPR Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl
2018	—	`conf`	Domain Transfer Through Deep Activation Matching. ECCV (16) Haoshuo Huang, Qixing Huang, Philipp Krähenbühl
2018	A*	`conf`	Free Supervision From Video Games. CVPR Philipp Krähenbühl
2018	J	`jnl`	Joint Monocular 3D Vehicle Detection and Tracking. CoRR Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu
2018	J	`jnl`	Long-Term Feature Banks for Detailed Video Understanding. CoRR Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross B. Girshick
2018	—	`conf`	Video Compression Through Image Interpolation. ECCV (8) Chao-Yuan Wu, Nayan Singhal, Philipp Krähenbühl
2018	J	`jnl`	Video Compression through Image Interpolation. CoRR Chao-Yuan Wu, Nayan Singhal, Philipp Krähenbühl
2017	J	`jnl`	A Century of Portraits: A Visual Historical Record of American High School Yearbooks. IEEE Trans. Computational Imaging Shiry Ginosar, Kate Rakelly, Sarah Sachs, Brian Yin, Crystal Lee, Philipp Krähenbühl, Alexei A. Efros
2017	—	`conf`	Adversarial Feature Learning. ICLR (Poster) Jeff Donahue, Philipp Krähenbühl, Trevor Darrell
2017	J	`jnl`	Compressed Video Action Recognition. CoRR Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl
2017	A*	`conf`	Sampling Matters in Deep Embedding Learning. ICCV R. Manmatha, Chao-Yuan Wu, Alexander J. Smola, Philipp Krähenbühl
2017	J	`jnl`	Sampling Matters in Deep Embedding Learning. CoRR Chao-Yuan Wu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl
2016	J	`jnl`	Adversarial Feature Learning. CoRR Jeff Donahue, Philipp Krähenbühl, Trevor Darrell
2016	A*	`conf`	Context Encoders: Feature Learning by Inpainting. CVPR Deepak Pathak, Philipp Krähenbühl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
2016	J	`jnl`	Context Encoders: Feature Learning by Inpainting. CoRR Deepak Pathak, Philipp Krähenbühl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
2016	A*	`conf`	Data-dependent Initializations of Convolutional Neural Networks. ICLR (Poster) Philipp Krähenbühl, Carl Doersch, Jeff Donahue, Trevor Darrell
2016	—	`conf`	Generative Visual Manipulation on the Natural Image Manifold. ECCV (5) Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros
2016	J	`jnl`	Generative Visual Manipulation on the Natural Image Manifold. CoRR Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros
2016	A*	`conf`	Learning Dense Correspondence via 3D-Guided Cycle Consistency. CVPR Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qi-Xing Huang, Alexei A. Efros
2016	J	`jnl`	Learning Dense Correspondence via 3D-guided Cycle Consistency. CoRR Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qixing Huang, Alexei A. Efros
2015	A*	`conf`	Constrained Convolutional Neural Networks for Weakly Supervised Segmentation. ICCV Deepak Pathak, Philipp Krähenbühl, Trevor Darrell
2015	J	`jnl`	Constrained Convolutional Neural Networks for Weakly Supervised Segmentation. CoRR Deepak Pathak, Philipp Krähenbühl, Trevor Darrell
2015	J	`jnl`	Constrained Structured Regression with Convolutional Neural Networks. CoRR Deepak Pathak, Philipp Krähenbühl, Stella X. Yu, Trevor Darrell
2015	A*	`conf`	Learning Data-Driven Reflectance Priors for Intrinsic Image Decomposition. ICCV Tinghui Zhou, Philipp Krähenbühl, Alexei A. Efros
2015	J	`jnl`	Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition. CoRR Tinghui Zhou, Philipp Krähenbühl, Alexei A. Efros
2015	A*	`conf`	Learning a Discriminative Model for the Perception of Realism in Composite Images. ICCV Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros
2015	J	`jnl`	Learning a Discriminative Model for the Perception of Realism in Composite Images. CoRR Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros
2015	A*	`conf`	Learning to propose objects. CVPR Philipp Krähenbühl, Vladlen Koltun
2014	—	`—`	Dense random fields. Philipp Krähenbühl
2014	—	`conf`	Geodesic Object Proposals. ECCV (5) Philipp Krähenbühl, Vladlen Koltun
2013	—	`conf`	Parameter Learning and Convergent Inference for Dense Random Fields. ICML (3) Philipp Krähenbühl, Vladlen Koltun
2012	J	`jnl`	Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials CoRR Philipp Krähenbühl, Vladlen Koltun
2012	—	`conf`	Efficient Nonlocal Regularization for Optical Flow. ECCV (1) Philipp Krähenbühl, Vladlen Koltun
2012	A*	`conf`	Saliency filters: Contrast based filtering for salient region detection. CVPR Federico Perazzi, Philipp Krähenbühl, Yael Pritch, Alexander Hornung
2011	—	`conf`	Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials. NIPS Philipp Krähenbühl, Vladlen Koltun
2010	J	`jnl`	Gesture controllers. ACM Trans. Graph. Sergey Levine, Philipp Krähenbühl, Sebastian Thrun, Vladlen Koltun
2009	J	`jnl`	A system for retargeting of streaming video. ACM Trans. Graph. Philipp Krähenbühl, Manuel Lang, Alexander Hornung, Markus H. Gross