Kashyap Chitta


I am a PhD student at the University of Tübingen, Germany, where I am part of the Autonomous Vision Group led by Prof. Andreas Geiger.

News: This year, our team came first place in the map track of the CARLA challenge, and second in the generative track (with a best paper award) for the dataset distillation challenge! We also won the inaugural nuPlan challenge in 2023. I was selected for the doctoral consortium at ICCV 2023, as a 2023 RSS pioneer, and an outstanding reviewer for CVPR, ICCV, ECCV, and NeurIPS.

Research: I am excited about data-driven solutions to complex decision-making tasks. Currently, my research focuses on self-driving vehicles and embodied AI. Representative papers are highlighted below.

Bio: Kashyap did a bachelor's degree in electronics at the RV College of Engineering, India. He then moved to the US in 2017 to obtain his Master's degree in computer vision from Carnegie Mellon University, where he was advised by Prof. Martial Hebert. During this time, he was also an intern at NVIDIA working with Dr. Jose M. Alvarez. He is currently a PhD student in the Autonomous Vision Group at the University of Tübingen, Germany, supervised by Prof. Andreas Geiger.

CV Mail Scholar Twitter Linkedin GitHub YouTube

Profile picture

Publications


Project image
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
Daniel Dauner, Marcel Hallgarten, Tianyu Li, Xinshuo Weng, Zhiyu Huang, Zetong Yang, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, Kashyap Chitta
Advances in Neural Information Processing Systems (NeurIPS), 2024
Abs / Paper / Code /
@inproceedings{Dauner2024NEURIPS, 
	author = {Daniel Dauner and Marcel Hallgarten and Tianyu Li and Xinshuo Weng and Zhiyu Huang and Zetong Yang and Hongyang Li and Igor Gilitschenski and Boris Ivanovic and Marco Pavone and Andreas Geiger and Kashyap Chitta}, 
	title = {NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking}, 
	booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, 
	year = {2024}, 
}
Project image
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
Shenyuan Gao, Jiazhi Yang, Li Chen, Kashyap Chitta, Yihang Qiu, Andreas Geiger, Jun Zhang, Hongyang Li
Advances in Neural Information Processing Systems (NeurIPS), 2024
Abs / Paper / Code /
@inproceedings{Gao2024NEURIPS, 
	author = {Shenyuan Gao and Jiazhi Yang and Li Chen and Kashyap Chitta and Yihang Qiu and Andreas Geiger and Jun Zhang and Hongyang Li}, 
	title = {Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability}, 
	booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, 
	year = {2024}, 
}
Project image
End-to-end Autonomous Driving: Challenges and Frontiers
Li Chen, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, Hongyang Li
Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024
Abs / Paper / Code /
@article{Chen2024PAMI, 
	author = {Li Chen and Penghao Wu and Kashyap Chitta and Bernhard Jaeger and Andreas Geiger and Hongyang Li}, 
	title = {End-to-end Autonomous Driving: Challenges and Frontiers}, 
	booktitle = {Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)}, 
	year = {2024}, 
}
Project image
DriveLM: Driving with Graph Visual Question Answering (Oral)
Chonghao Sima*, Katrin Renz*, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang Li
European Conference on Computer Vision (ECCV), 2024
Abs / Paper / Code /
@inproceedings{Sima2024ECCV, 
	author = {Chonghao Sima and Katrin Renz and Kashyap Chitta and Li Chen and Hanxue Zhang and Chengen Xie and Jens Beißwenger and Ping Luo and Andreas Geiger and Hongyang Li}, 
	title = {DriveLM: Driving with Graph Visual Question Answering}, 
	booktitle = {European Conference on Computer Vision (ECCV)}, 
	year = {2024}, 
}
Project image
SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic
Kashyap Chitta*, Daniel Dauner*, Andreas Geiger
European Conference on Computer Vision (ECCV), 2024
Abs / Paper / Supplementary / Code /
@inproceedings{Chitta2024ECCV, 
	author = {Kashyap Chitta and Daniel Dauner and Andreas Geiger}, 
	title = {SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic}, 
	booktitle = {European Conference on Computer Vision (ECCV)}, 
	year = {2024}, 
}
Project image
Generalized Predictive Model for Autonomous Driving
Jiazhi Yang*, Shenyuan Gao*, Yihang Qiu*, Li Chen, Tianyu Li, Bo Dai, Kashyap Chitta, Penghao Wu, Jia Zeng, Ping Luo, Jun Zhang, Andreas Geiger, Yu Qiao, Hongyang Li
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Abs / Paper / Code /
@inproceedings{Yang2024CVPR, 
	author = {Jiazhi Yang and Shenyuan Gao and Yihang Qiu and Li Chen and Tianyu Li and Bo Dai and Kashyap Chitta and Penghao Wu and Jia Zeng and Ping Luo and Jun Zhang and Andreas Geiger and Yu Qiao and Hongyang Li}, 
	title = {Generalized Predictive Model for Autonomous Driving}, 
	booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2024}, 
}
Project image
Parting with Misconceptions about Learning-based Vehicle Motion Planning (Winner, 2023 nuPlan Challenge)
Daniel Dauner, Marcel Hallgarten, Andreas Geiger, Kashyap Chitta
Conference on Robot Learning (CoRL), 2023
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Dauner2023CORL, 
	author = {Daniel Dauner and Marcel Hallgarten and Andreas Geiger and Kashyap Chitta}, 
	title = {Parting with Misconceptions about Learning-based Vehicle Motion Planning}, 
	booktitle = {Conference on Robot Learning (CoRL)}, 
	year = {2023}, 
}
Project image
Hidden Biases of End-to-End Driving Models (Winner, 2022 CARLA Challenge Map Track)
Bernhard Jaeger, Kashyap Chitta, Andreas Geiger
International Conference on Computer Vision (ICCV), 2023
Abs / Paper / Video / Poster / Code /
@inproceedings{Jaeger2023ICCV, 
	author = {Bernhard Jaeger and Kashyap Chitta and Andreas Geiger}, 
	title = {Hidden Biases of End-to-End Driving Models}, 
	booktitle = {International Conference on Computer Vision (ICCV)}, 
	year = {2023}, 
}
Project image
TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving (Runner Up, 2021 CARLA Challenge)
Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger
Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
Abs / Paper / Supplementary / Video / Poster / Code /
@article{Chitta2023PAMI, 
	author = {Kashyap Chitta and Aditya Prakash and Bernhard Jaeger and Zehao Yu and Katrin Renz and Andreas Geiger}, 
	title = {TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving}, 
	booktitle = {Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)}, 
	year = {2023}, 
}
Project image
PlanT: Explainable Planning Transformers via Object-Level Representations
Katrin Renz, Kashyap Chitta, Otniel-Bogdan Mercea, Sophia Koepke, Zeynep Akata, Andreas Geiger
Conference on Robot Learning (CoRL), 2022
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Renz2022CORL, 
	author = {Katrin Renz and Kashyap Chitta and Otniel-Bogdan Mercea and Sophia Koepke and Zeynep Akata and Andreas Geiger}, 
	title = {PlanT: Explainable Planning Transformers via Object-Level Representations}, 
	booktitle = {Conference on Robot Learning (CoRL)}, 
	year = {2022}, 
}
Project image
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients (Oral)
Niklas Hanselmann, Katrin Renz, Kashyap Chitta, Apratim Bhattacharyya, Andreas Geiger
European Conference on Computer Vision (ECCV), 2022
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Hanselmann2022ECCV, 
	author = {Niklas Hanselmann and Katrin Renz and Kashyap Chitta and Apratim Bhattacharyya and Andreas Geiger}, 
	title = {KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients}, 
	booktitle = {European Conference on Computer Vision (ECCV)}, 
	year = {2022}, 
}
Project image
Training Data Subset Search with Ensemble Active Learning
Kashyap Chitta, Jose Alvarez, Elmar Haussmann, Clement Farabet
Transactions on Intelligent Transportation Systems (T-ITS), 2021
Abs / Paper /
@article{Chitta2021ITS, 
	author = {Kashyap Chitta and Jose Alvarez and Elmar Haussmann and Clement Farabet}, 
	title = {Training Data Subset Search with Ensemble Active Learning}, 
	booktitle = {Transactions on Intelligent Transportation Systems (T-ITS)}, 
	year = {2021}, 
}
Project image
Projected GANs Converge Faster
Axel Sauer, Kashyap Chitta, Jens Muller, Andreas Geiger
Advances in Neural Information Processing Systems (NeurIPS), 2021
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Sauer2021NEURIPS, 
	author = {Axel Sauer and Kashyap Chitta and Jens Muller and Andreas Geiger}, 
	title = {Projected GANs Converge Faster}, 
	booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, 
	year = {2021}, 
}
Project image
Benchmarking Unsupervised Object Representations for Video Sequences
Marissa Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander Ecker
Journal of Machine Learning Research (JMLR), 2021
Abs / Paper / Video / Code /
@article{Weis2021JMLR, 
	author = {Marissa Weis and Kashyap Chitta and Yash Sharma and Wieland Brendel and Matthias Bethge and Andreas Geiger and Alexander Ecker}, 
	title = {Benchmarking Unsupervised Object Representations for Video Sequences}, 
	booktitle = {Journal of Machine Learning Research (JMLR)}, 
	year = {2021}, 
}
Project image
NEAT: Neural Attention Fields for End-to-End Autonomous Driving (Runner Up, 2020 CARLA Challenge)
Kashyap Chitta*, Aditya Prakash*, Andreas Geiger
International Conference on Computer Vision (ICCV), 2021
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Chitta2021ICCV, 
	author = {Kashyap Chitta and Aditya Prakash and Andreas Geiger}, 
	title = {NEAT: Neural Attention Fields for End-to-End Autonomous Driving}, 
	booktitle = {International Conference on Computer Vision (ICCV)}, 
	year = {2021}, 
}
Project image
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Aditya Prakash*, Kashyap Chitta*, Andreas Geiger
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Abs / Paper / Supplementary / Video / Poster / Code /
@inproceedings{Prakash2021CVPR, 
	author = {Aditya Prakash and Kashyap Chitta and Andreas Geiger}, 
	title = {Multi-Modal Fusion Transformer for End-to-End Autonomous Driving}, 
	booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2021}, 
}
Project image
Label Efficient Visual Abstractions for Autonomous Driving
Aseem Behl*, Kashyap Chitta*, Aditya Prakash, Eshed Ohn-Bar, Andreas Geiger
International Conference on Intelligent Robots and Systems (IROS), 2020
Abs / Paper / Video /
@inproceedings{Behl2020IROS, 
	author = {Aseem Behl and Kashyap Chitta and Aditya Prakash and Eshed Ohn-Bar and Andreas Geiger}, 
	title = {Label Efficient Visual Abstractions for Autonomous Driving}, 
	booktitle = {International Conference on Intelligent Robots and Systems (IROS)}, 
	year = {2020}, 
}
Project image
Scalable Active Learning for Object Detection
Elmar Haussmann, Michele Fenzi, Kashyap Chitta, Jan Ivanecky, Hanson Xu, Donna Roy, Akshita Mittel, Nicolas Koumchatzky, Clement Farabet, Jose Alvarez
Intelligent Vehicles Symposium (IV), 2020
Abs / Paper /
@inproceedings{Haussmann2020IV, 
	author = {Elmar Haussmann and Michele Fenzi and Kashyap Chitta and Jan Ivanecky and Hanson Xu and Donna Roy and Akshita Mittel and Nicolas Koumchatzky and Clement Farabet and Jose Alvarez}, 
	title = {Scalable Active Learning for Object Detection}, 
	booktitle = {Intelligent Vehicles Symposium (IV)}, 
	year = {2020}, 
}
Project image
Learning Situational Driving
Eshed Ohn-Bar, Aditya Prakash, Aseem Behl, Kashyap Chitta, Andreas Geiger
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Abs / Paper / Supplementary / Video /
@inproceedings{Ohn-bar2020CVPR, 
	author = {Eshed Ohn-Bar and Aditya Prakash and Aseem Behl and Kashyap Chitta and Andreas Geiger}, 
	title = {Learning Situational Driving}, 
	booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2020}, 
}
Project image
Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving
Aditya Prakash, Aseem Behl, Eshed Ohn-Bar, Kashyap Chitta, Andreas Geiger
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Abs / Paper / Supplementary / Video / Code /
@inproceedings{Prakash2020CVPR, 
	author = {Aditya Prakash and Aseem Behl and Eshed Ohn-Bar and Kashyap Chitta and Andreas Geiger}, 
	title = {Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving}, 
	booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2020}, 
}
Project image
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions
Kashyap Chitta, Jose Alvarez, Martial Hebert
Winter Conference on Applications of Computer Vision (WACV), 2020
Abs / Paper / Poster / Code /
@inproceedings{Chitta2020WACV, 
	author = {Kashyap Chitta and Jose Alvarez and Martial Hebert}, 
	title = {Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions}, 
	booktitle = {Winter Conference on Applications of Computer Vision (WACV)}, 
	year = {2020}, 
}

Talks


Project image
Non-Reactive Autonomous Vehicle Simulation and Benchmarking
CVPR Workshop on Autonomous Driving, Seattle, 2024
Slides / Recording
Project image
Synthesizing Simulation Environments with Generative Models
CVPR Workshop on Data-Driven Autonomous Driving Simulation, Seattle, 2024
Slides / Recording
Project image
Reading, Writing, and Reviewing for Robotics and Computer Vision Research
Sogang University Applied Data Engineering Seminar (Virtual), 2023
Slides / Recording
Project image
End-to-End Driving with Attention
ICRA Workshop on Scalable Autonomous Driving, London, 2023
Slides / Recording
Project image
Imitation via Abstraction and Planning
ETH Computer Vision Lab, Zürich, 2023
Slides / Recording
Project image
Imitation with Transformer-Based Sensor Fusion for Autonomous Driving
University of Toronto AI in Robotics Seminar (Virtual), 2022
Slides / Recording

This website is based on the lightweight and easy-to-use template from Michael Niemeyer. Check out his github repository for instructions on how to use it!