Note: Partha Ghosh has transitioned from the institute (alumni).
I am a post-doctoral researcher in the EI department. I focus on Video generative models and investigate opportunities of causal representations in this context. Apart from that, I am investigating Autoformalizaton, a technique that leverages the vast natural language understanding of LLMs to represent mathematical problems precisely using formal languages where reasoning can be cast as a search problem. I think a program that can come up with a new formal system or at least extend an existing formal system as needed during the runtime can overcome the lack of representation power and therefore applicability of existing formal systems.
Prior to this, I was an IMPRS-IS scholar and was supervised by Michael Black. I focused on Generative modelling. More specifically, the conditional versions of them. Conditional generative models are a means to learn one-to-many mappings. Although such models, especially GANs, do a good job at density estimation of high dimensional data (images), they are far from perfect. These imperfections induce errors that manifest as spurious correlations (among many others) in the generated data. Although this may not be noticeable readily, it can render such models completely unusable for many applications. I worked on addressing this issue.
PARTHA GHOSH Email : pghosh@tuebingen.mpg.de , parthaghosh.iitbbs@gmail.com Phone No : +49 15128950793 |
|
RESEARCH INTERESTS |
|
|
|
EDUCATIONAL QUALIFICATIONS |
|
Post-Doctoral Researcher |
Empirical Inference, Max Planck Institute for Intelligent Systems. 2022–Current. |
Doctoral student |
Perceiving Systems, Max Plnack Institute for Intelligent Systems. 2017–2022. |
MSc. Robotics, Systems and Control |
Eidgenössische Technische Hochschule Zürich (ETHZ) 2014 – 2016, 5.39/6.0 |
Bachelor of Technology (Electrical Engineering) |
Indian Institute of Technology Bhubaneswar (IITBBS) 2009 – 2013, CGPA 8.91/10.00 |
West Bengal Council of Higher Secondary Education |
Hindu School, Kolkata 2009, 80.6% Aggregate |
West Bengal Board of Secondary Education |
Changdoba High School, Bankura 2007, 93.5% Aggregate |
PATENTS AND PUBLICATIONS |
Ghosh, P., Zietlow, D., Black, M. J., Davis, L. S., & Hu, X. “InvGAN: Invertable GANs. arXiv preprint arXiv:2112.04598.” 2021.
Ghosh P., Gupta P. S.ingh, Uziel R. and Ranjan A. and Black M. and Bolkart T. “GIF: Generative Interpretable Faces”, Published in International Conference on 3D Vision (3DV), 2020.
Ghosh P., Sajjadi M.S., Vergari A., Black M. and Schölkopf B., “From variational to deterministic autoencoders”, Published in International Conference on Learning Representations (ICLR), 2020. Ghosh P., Losalka A, Black M, “Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders”, published in thirty third AAAI conference on artificial Intelligence 2019.
Ghosh P, Song J, Aksan E, Hilliges O, “Learning Human Motion Models for Long-term Predictions”, best paper award at 2017 international conference on 3DVision (3DV).
Bongale P., Sundaresan V., Ghosh P. and Parekhji P., "A novel technique for interdependent trim code optimization", 2016 IEEE 34th VLSI Test Symposium (VTS), Las Vegas, NV, 2016, pp. 1-6. doi: 10.1109/VTS.2016.7477261
“Novel Hardware Implementation of Simplex Minimization Algorithm to Enable On-chip Multi-variable Trims for Circuit Calibration”, Partha Ghosh, Pankaj Bongale, Parekhji Rubin, USA; approved by Texas Instruments for non-provisional patent application, 2014. |
“An intelligent car door dent preventing system”, Partha Ghosh, Pravir Singh Gupta, S. N. Panigrahi, India; Patent application number 874/KOL/2013; Patent pending, 2013. |
“A vehicle mounted surveillance system for tracking and monitoring the vehicle position and its surroundings”, Partha Ghosh, Pravir Singh Gupta, S.N. Panigrahi, India; Patent application 496/KOL/2013; Patent pending, 2013. |
RESEARCH PROJECTS |
||
Thesis on “Improvement of Scalability of Bundle Adjustment for Large Visual Inertial maps”, Autonomous Systems Lab, ETH Zurich, October 2015 – May 2016. |
||
“Visual Inertial odometry with Stereo and Monocular vision”, Advanced Interactive Technologies Lab, ETH Zürich, February 2015 - August 2015. |
||
Thesis on “Movement of Unmanned Vehicle in General Terrain” under supervision of Dr. S.N.Panigrahi, School of Mechanical Sciences(SMS) & Prof. Ganapati Panda, School of Electrical Sciences(SES), IIT BBS, ’12-’13 |
||
“Active Automotive Mufflers” under the guidance of Dr. S.N. Panigrahi, SMS, IIT Bhubaneswar 2010-2011 |
||
“Study of Magnetic Levitation”, under the guidance of Dr. A.K. Ghosh, SES, IIT Bhubaneswar 2011-2012 |
||
|
||
WORK EXPERIENCE |
||
Oct. 2016-Nov. 2017 |
AIT lab ETH Zurich, Zurich |
Research Engineer |
Sept. 2014-Sept. 2016 |
ADRL lab ETH Zurich, Zurich |
Research Assistant |
July 2013-July 2014 |
Texas Instruments Inc., Bangalore |
Design Engineer |
July 2012-Dec 2012 |
Indian Institute of technology Bhubaneswar |
TA, Programing and Data-structure |
May-2012-July 2012 |
Texas Instruments Inc., Bangalore |
Summer Internship |
|
||
SCHOLASTIC ACHIEVEMENTS |
||
Best paper award 3DV 2017 Winner of Social Impact Start stipend, Impact Hub Zurich, October 2015-2016 Recipient of Government of India Merit cum Means Scholarship, 2009-2013 |
||
Ranked among top 1% students in Joint Entrance Examination conducted by IITs in the year 2009 |
||
Ranked among top 1% students in All India Engineering Entrance Examination (AIEEE), CBSE in 2009 |
||
Scholarship through ‘National Scholarship Examination of the Secondary Stage for the Talented Children in Rural Areas of Directorate of School Education’, Government of West Bengal 2005-2009 |
EXTRA CURRICULAR ACTIVITIES |
Represented IIT Bhubaneswar in chess at the 46th Inter IIT Sports Meet held in IIT Delhi |
Runners-up in Codec - C-programming competition & Second-Runners up in Mathematics Olympiad in Wissenaire’11, the national level techno-management fest of IIT Bhubaneswar |
HOBBIES AND INTERESTS |
Playing Billiard, Badminton, Table tennis, Skating, Skiing, Chess |
Pencil sketching, Water Painting |