Kashyap Chitta
@kashyap7x.bsky.social
kashyap7x.github.io
Postdoc at NVIDIA. Previously at the University of Tübingen and CMU. Robot Learning, Autonomous Driving.
Postdoc at NVIDIA. Previously at the University of Tübingen and CMU. Robot Learning, Autonomous Driving.
Launching the Physical AI AV Dataset! 🚀
huggingface.co/datasets/nvi...
One of the largest, most diverse & commercially usable open-source datasets for AVs.
- 1727 hours of driving data
- Camera, LiDAR, & radar
- 25 countries, 2500+ cities
This is just the beginning, more features to come!
huggingface.co/datasets/nvi...
One of the largest, most diverse & commercially usable open-source datasets for AVs.
- 1727 hours of driving data
- Camera, LiDAR, & radar
- 25 countries, 2500+ cities
This is just the beginning, more features to come!
October 28, 2025 at 5:59 PM
Launching the Physical AI AV Dataset! 🚀
huggingface.co/datasets/nvi...
One of the largest, most diverse & commercially usable open-source datasets for AVs.
- 1727 hours of driving data
- Camera, LiDAR, & radar
- 25 countries, 2500+ cities
This is just the beginning, more features to come!
huggingface.co/datasets/nvi...
One of the largest, most diverse & commercially usable open-source datasets for AVs.
- 1727 hours of driving data
- Camera, LiDAR, & radar
- 25 countries, 2500+ cities
This is just the beginning, more features to come!
Driving world models become much easier to control and more effective for practical applications when their training data combines human driving demonstrations with synthetic 'non-expert' data from a simulator.
Introducing ReSim: resim-world-model.github.io
Introducing ReSim: resim-world-model.github.io
June 13, 2025 at 11:52 AM
Driving world models become much easier to control and more effective for practical applications when their training data combines human driving demonstrations with synthetic 'non-expert' data from a simulator.
Introducing ReSim: resim-world-model.github.io
Introducing ReSim: resim-world-model.github.io
Announcing the 2025 NAVSIM Challenge! What's new? We're testing not only on real recordings—but also imaginary futures generated from the real ones! 🤯
Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇
Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇
April 13, 2025 at 11:08 AM
Announcing the 2025 NAVSIM Challenge! What's new? We're testing not only on real recordings—but also imaginary futures generated from the real ones! 🤯
Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇
Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇
The paper has great ICLR scores, [8, 8, 8, 8]: openreview.net/forum?id=pIS.... Also, I really like the teaser video! Hope to see more work soon on whether these data scaling trends hold when using language-conditioned generalist policies, like openvla.github.io
November 26, 2024 at 5:44 PM
The paper has great ICLR scores, [8, 8, 8, 8]: openreview.net/forum?id=pIS.... Also, I really like the teaser video! Hope to see more work soon on whether these data scaling trends hold when using language-conditioned generalist policies, like openvla.github.io
rl.tools - "Looks like every impactful continuous control paper only used tiny MLPs, let's hardcode this in pure C++ so we can get 300k training steps in 0.5 seconds". Crazy speeds! Is this the github.com/karpathy/llm.c of RL?
November 22, 2024 at 12:54 AM
rl.tools - "Looks like every impactful continuous control paper only used tiny MLPs, let's hardcode this in pure C++ so we can get 300k training steps in 0.5 seconds". Crazy speeds! Is this the github.com/karpathy/llm.c of RL?