Skip to content

Yun-Ta Tsai

Senior Staff Software Engineer at Tesla

‪Yun-Ta Tsai‬ – ‪Google Scholar‬


Speciality: Full Stack Engineering, ML, Janitor of All.

2023 Sr. Staff Engineer, @Tesla_AI

2020 Staff Engineer, @Tesla_AI

2019 Staff SWE, @GoogleAI

2017 Senior SWE, @GoogleAI

2015 SWE, @GoogleAI

2014 SWE, Google X Senior Research Scientist, @nvidia

2011 Research Scientist, @nvidia

2010 Senior Researcher, @nokia

2009 Researcher, @nokia

Yun-Ta Tsai

@YunTaTsai1

Designing an inference chip for robots is actually very difficult. In data centers each chip is bathed in jacuzzi and babysat by nannies. If they died it would be hot swapped by one of their clones. The fault rate of GPUs in datacenter is actually quite high. Industrial average annual fault rate of H100 is 9%. Ideal conditions could reduce it down to 2% but never below a single digit. The fault recovery of GPU nodes actually could take a while, from minutes to hours. It is not instantaneous. In robots, the chips are out in the cold and they need rapid self recovery. The fault tolerance is in a different league. It is not uncommon many robotic companies struggle to get the chip running more than a few hours without rebooting. For chip companies, this is great since they would tell robotic companies to buy more chips for hot swapping. For robotic companies, this is bad since it is obviously not a scaleable solution but they are stuck with endless back-and-forth JIRA tickets with vendors.

·

4.3M Views

Neural light transportT Yun-Ta, X Zhang, JT Barron, S FANELLO, SUN Tiancheng, T XueUS Patent 12,094,05452024
Photo relighting using deep neural networks and confidence learningSUN Tiancheng, T Yun-TaUS Patent 11,776,09582023
Neural light transport for relighting and view synthesisX Zhang, S Fanello, YT Tsai, T Sun, T Xue, R Pandey, S Orts-Escolano, …ACM Transactions on Graphics (TOG) 40 (1), 1-171342021
Cross-camera convolutional color constancyM Afifi, JT Barron, C LeGendre, YT Tsai, F BleibelProceedings of the IEEE/CVF International Conference on Computer Vision …772021
Light stage super-resolution: continuous high-frequency relightingT Sun, Z Xu, X Zhang, S Fanello, C Rhemann, P Debevec, YT Tsai, …ACM Transactions on Graphics (TOG) 39 (6), 1-12572020
Portrait shadow manipulationX Zhang, JT Barron, YT Tsai, R Pandey, X Zhang, R Ng, DE JacobsACM Transactions on Graphics (TOG) 39 (4), 78: 1-78: 141132020
Sky optimization: Semantically aware image processing of skies in low-light photographyO Liba, L Cai, YT Tsai, E Eban, Y Movshovitz-Attias, Y Pritch, H Chen, …Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …202020
Handheld mobile photography in very low light.O Liba, K Murthy, YT Tsai, T Brooks, T Xue, N Karnad, Q He, JT Barron, …ACM Trans. Graph. 38 (6), 164:1-164:161472019
Single image portrait relighting.T Sun, JT Barron, YT Tsai, Z Xu, X Yu, G Fyffe, C Rhemann, J Busch, …ACM Trans. Graph. 38 (4), 79:1-79:123152019
Fast fourier color constancyJT Barron, YT TsaiProceedings of the IEEE conference on computer vision and pattern …2572017
Efficient approximate-nearest-neighbor (ANN) search for high-quality collaborative filteringDS PAJAK, T Yun-Ta, M SteinbergerUS Patent 9,454,806142016
Fast ANN for High‐Quality Collaborative FilteringYT Tsai, M Steinberger, D Pająk, K PulliComputer graphics forum 35 (1), 138-15162016
Face beautification system and method of use thereofE Albuz, C Tracey, N Garg, YT TSAI, D PajakUS Patent App. 14/031,55162014
Flexisp: A flexible camera image processing frameworkF Heide, M Steinberger, YT Tsai, M Rouf, D Pająk, D Reddy, O Gallo, J Liu, …ACM Transactions on Graphics (ToG) 33 (6), 1-134102014
Image pyramid processor and method of multi-resolution image processingQ Zhu, N Garg, T Yun-Ta, K Pulli, A MeixnerUS Patent App. 13/764,41662014
Fast ANN for high-quality collaborative filteringYT Tsai, M Steinberger, D Pająk, K PulliProceedings of High Performance Graphics, 61-70112014
An energy efficient time-sharing pyramid pipeline for multi-resolution computer visionQ Zhu, N Garg, YT Tsai, K Pulli2013 IFIP/IEEE 21st International Conference on Very Large Scale Integration …62013
Mobile visual computing in C++ on AndroidYT Tsai, O Gallo, D Pajak, K PulliACM SIGGRAPH 2013 Mobile, 1-112013
Urban canvas: Unfreezing street-view imagery with semantically compressed LIDAR pointcloudsT Korah, YT Tsai2011 10th IEEE International Symposium on Mixed and Augmented Reality, 271-27242011
Indirect augmented realityJ Wither, YT Tsai, R AzumaComputers & Graphics 35 (4), 810-8221952011
Electric Agents: combining television and mobile phones for an educational gameR Ballagas, G Revelle, K Buza, H Horii, K Mori, H Raffle, M Spasojevic, …Proceedings of the 10th International Conference on Interaction Design and …52011
Mobile augmented reality at the hollywood walk of fameT Korah, J Wither, YT Tsai, R Azuma2011 IEEE Virtual Reality Conference, 183-186192011
The westwood experience: connecting story to locations via mixed realityJ Wither, R Allen, V Samanta, J Hemanus, YT Tsai, R Azuma, W Carter, …2010 IEEE International Symposium on Mixed and Augmented Reality-Arts, Media …582010
CDIKP: A highly-compact local feature descriptorYT Tsai, Q Wang, S You2008 19th International Conference on Pattern Recognition, 1-4182008
Practical Realtime Fracture Simulation for GamesYT Tsai, JS Chang, CY Lin12005
Cross-Camera Convolutional Color Constancy Supplemental MaterialM Afifi, JT Barron, C LeGendre, YT Tsai, F Bleibel