Research Admissions Aug 2024

Recent Updates

  • All applicants called for interview must fill out the Applicant Information Form. The deadline for submitting this mandatory form is extended to May 7, 23:59 PM.
  • Here is a sample question paper for the computer-aided aptitude test.

The admission process for the Aug 2024 cycle to the Department of Computational and Data Sciences (CDS) comprises two consecutive phases. Phase I will be a computer-aided online aptitude test on the HackerEarth platform, which serves as the first part of the evaluation and Phase II will be an oral interview for all candidates who qualified in the aptitude test conducted in Phase I. Note that both the computer-aided aptitude test and the oral interview will be held in-person in the CDS department.

Candidates shortlisted for the computer-aided online aptitude test (Phase I of the interview) will receive a call letter or email from the IISc Admissions office (please login to the IISc admissions portal and check for the call letter). The aptitude test will be conducted on the same day and session as per the allotted slot in your call letter. The test will be held in-person in the CDS department, and you will be provided with a computer to take the test (you need not bring a laptop/computer). You will receive a separate email from the CDS department for your test and instructions such as the test link, rules, guidelines, practice test, etc. This online computer-aided aptitude test will have multiple-choice and programming questions as per the syllabus below.

The Phase II (in-person) oral interview is only for students who attempt and qualify in the computer-aided online aptitude test conducted in Phase I. The oral interviews for the qualified candidates will be held in the same session immediately after the results for Phase I are announced. The syllabus for the interview (similar to the aptitude test, with lab-specific readings) is also given in detail below.

About one or two weeks before the date of computer-aided aptitude test (and subsequent interview if qualified in the aptitude test), the shortlisted candidates will be sent an email from the CDS department to fill out an online student information Google form. This must be completed and submitted in order to participate in the interview. As part of this, candidates should choose up to three labs in the department for which they will be considered. These labs are described below. If successfully admitted, students will be placed in one of these labs for conducting their research. Orientation sessions and lab introductions to help candidates make the right choice based on their interest will be conducted online through webinars for which shortlisted candidates will be invited.

Pre-interview familiarization of CDS and lab introductions will be conducted through webinars and dates will be displayed on the CDS Research Admissions Website.

Computer-aided Aptitude Test

The Phase I computer-aided objective and programming test will be conducted using the “HackerEarth” online platform on the same day and session as per the allotted slot in your call letter. This test will be held in the CDS department, and the candidates will be provided with a computer to take the online exam. Candidates will be emailed with a link to the online test a few days before the test date. The test will be enabled at the start of your session before the in-person oral interviews begin. It must be completed in a single sitting. You will need to create a free HackerEarth account to take the test. You MUST use the same email address as the one used for your IISc Admissions Application. Please do this ahead of time. That email will also have another link to let you take a practice test to get familiar with the HackerEarth platform. Please note that these practice questions would not be from the test syllabus. Candidates may take the practice test as many times as they want. Candidates should get familiar with the programming IDE, compilation, and testing interface of HackerEarth to ensure that the programming questions are correctly attempted. The computer-aided online aptitude test will have 8 questions. There will be 6 multiple choice questions and 2 programming questions. The topics for the objective test are:

  • Combinatorics, Linear Algebra/Matrices, Probability and Statistics, Differential Equations, Plotting, Data Structures and Algorithms.

Here is a sample question paper for the computer-aided aptitude test. The programming languages that you can use are C, C++ and Java. The HackerEarth interface will allow you to type the program, compile it and run test cases, all within the browser. We will provide a basic code template for reading and writing the inputs and outputs for each problem. The candidates should focus on the actual code logic and brush up on concepts such as if/then/else conditions, for/while loops and arrays/data structures.

Students are encouraged to first solve the problems that they are comfortable with and then move on to more difficult problems.

A familiarization program for the online aptitude test and HackerEarth platform will be conducted. The exact date and time for this online test familiarization program will be intimated by email to the candidates shortlisted for the online aptitude test.

In-Person Oral Interview

Students who qualify in the online aptitude test (Phase I of the interview) will only attend the subsequent oral interview (Phase II of the interview) in the same allotted session as per the call letter. In the oral interview, you will be questioned on the following basic topics, and on advanced topics that are based on your lab preferences:

Basic Topics: Linear Algebra; Probability & Statistics; Programming, Data Structures, Algorithms; Numerical Methods; Ordinary Differential Equations; Discrete Mathematics.  Final year undergraduate level preparation is required.

Advanced Topics: You will be questioned on the topics related to labs selected in the student information Google form. The topics for each lab and the prior training expected are listed below. Candidates choosing a lab must be prepared on at least one of the lab-related interview topics.

Note: Most labs give preference to applicants for the Ph.D. program over the M.Tech. (Research) program. Some labs may not even take any students for the M.Tech. (Research) program. Students with a B.E./B.Tech. degree are also eligible to apply for the Ph.D. program.

Candidates for the Ph.D. program should prepare well on their fundamentals, come with a focus and knowledge of the research areas they would like to target in their Ph.D., and have clarity on the preferred lab(s) and the kind of work done in them. Review the research topics and the papers from the labs you are interested in.

List of labs that are admitting students

The following labs (ATCG, BioMedIA, BCL, CSPL, FLAME, MATRIX, MIG, NATL, QUEST, SCL, STARS) accept students from all background qualifications.

1. Algorithmic Techniques for Computational Genomics (ATCG)

Faculty: Chirag Jain


Lab Description: We work at the intersection of computer science and biology. Our goal is to accelerate discovery in life sciences by developing novel algorithms, data structures and open-source software tools. Most of our projects involve addressing computational problems associated with the analysis of large-scale DNA and RNA sequencing data in the context of various biomedical applications. Refer to our lab website to learn more about ongoing projects.

Our lab is engaged in active collaborations with industry (e.g., Intel Labs, Strand Life Sciences) and academic groups (e.g., Genome Institute of Singapore, University of Texas Dallas, IIT Delhi, Center for Brain Research).

Interview topics: Algorithms design and analysis, data structures, graph algorithms

Prior training: Students should have an engineering or an applied mathematics background. Strong programming and algorithm development skills are required.

2. Biomedical Image Analysis (BioMedIA) Lab

Faculty: Vaanathi Sundaresan


Lab Description: Our aim is to develop innovative AI-based methods for computational analysis of multidisciplinary biomedical images for clinical applications. We specifically focus on building scalable and translatable tools for big data applications in neuroimaging. We are also interested in tackling key challenges of medical image analysis including label scarcity and data diversity, model generalisability and interpretability.

Our current research areas include computer vision and machine learning-based methods for identification of MR imaging biomarkers for various neurological diseases and their population-level impact, semi-supervised techniques for analysis of various imaging modalities, data harmonisation/domain adaptation, image reconstruction and quality improvement.

Interview topics: Signal Processing, Image Processing, Linear Algebra, Probability and Machine Learning basics.

Prior Training: We are looking for students with an engineering background, preferably Computer Science or Electrical Engineering, interested in the following topics: deep learning and computer vision applications, domain adaptation and weakly supervised learning, uncertainty estimation and explainable AI methods in medical imaging, specifically neuroimaging.

3. Biomolecular Computation Laboratory (BCL)

Faculty: Debnath Pal


Lab description: The aim of the lab is to understand biological data for insights into biological structure, function and processes at multiple scales. The scope of work spans the areas of genomics, proteomics, metabolomics, structural biology, health and disease, methods and algorithms. There is an opportunity to do research problems in real-life projects in cancer, diabetes, neurodegeneration etc., where intensive bio-computational analysis is required.

For the Aug 2024 admissions, we are looking for two PhD students to work in the broad areas of health and disease which may involve translational components.

Interview topics: Students are expected to have good programming knowledge and a sound understanding in at least one of the basic subjects at the undergraduate level: Math, Physics or Chemistry. Exposure to data science, bioinformatics and computational biology is desirable but not essential.

Prior training: Students with sound knowledge in any background and enthusiasm for learning biology.

4. Computational & Statistical Physics Lab (CSPL)

Faculty: Murugesan Venkatapathi


Lab description: Research at CSPL can be broadly grouped into a) theoretical and computational models in condensed matter physics, b) numerical and scientific computing, and c) randomized algorithms and statistical computing.

CSPL is looking for two PhD students to work in the broad areas ‘a’ and ‘c’. In the former, we would like to extend some of our recent understanding of counterintuitive optical properties of extremely small metal nanoparticles to their electrical properties as well. In ‘c’, we are interested in developing new algorithms for randomized numerical linear algebra and high-dimensional integration.

Interview topics: Linear/Matrix algebra, numerical methods, statistics, and topics in physics as appropriate for the research area.

Prior training: A degree in Engineering or Physics or Mathematics.

5. FLAME:Lab (FLow Analysis and Multi-physics simulations at Extreme-scale) Lab

Faculty: Konduri Aditya

Website: and

Lab description: The research group focuses on the simulation and analysis of multi-scale multi-physics fluid flow problems that leverage high performance computing (HPC) platforms. Specifically, the work would involve development of HPC centric numerical methods and algorithms for solving partial differential equations (PDE) that are relevant to computational fluid dynamics (CFD), application of machine learning methods to analyze and model data generated from simulations, and investigation of turbulent flow problems that arise in combustion systems (gas turbine and scramjet engines), high-speed aerodynamics and environmental flows. 

Our current projects include reduced-order modelling (ROM) for reacting flows, scalable asynchronous PDE solvers, hydrogen combustion, and detection & forecasting of extreme events.  For the Aug 2024 admissions, we are looking for three PhD/MTech (Research) students.

Interview topics: Numerical methods, linear algebra, probability, scientific programming, differential equations, fluid mechanics (optional), programming models (optional)

Prior training:  Students should have a Bachelors’ or Masters’ degree in any one of the following areas: Mechanical Engineering, Aerospace Engineering, Chemical Engineering, Computational Engineering, Computational Physics, Applied Mathematics, Scientific computing or similar areas. Ph.D. candidates are preferred.

6. MATRIX:Lab  (Materials-physics & Algorithmic Techniques Research In eXtreme-computing)

Faculty:  Phani Motamarri


Lab description: Our lab delves into interdisciplinary research, drawing ideas from quantum mechanics, computational linear algebra, materials science, solid mechanics, finite-element methods, machine learning, and large-scale scientific computing (HPC). In particular, we focus on developing advanced mathematical techniques, hardware-aware computational algorithms (CPUs+GPUs, Quantum computers), multiscale methodologies, and machine-learning frameworks aimed at pushing the boundaries of the current predictive capabilities of materials design. This opens up avenues for tackling a wide array of scientifically and technologically significant problems previously beyond reach. Application areas include design of energy storage materials, catalytic materials, quantum modeling of complex defects in functional and structural materials, multi-scale modeling in combustion, nano-fluidics and quantum emitter applications. Additionally, students will contribute to novel computational methodologies and HPC algorithmic innovations, which will integrate into the open-source code DFT-FE, the workhorse behind the 2023 ACM Gordon Bell Prize.  The research you will conduct truly reflects our country’s indigenous ability to build methods and open-source exascale codes, ensuring our nation remains competitive in this exascale era. Further, our lab is making initial forays into developing quantum computing-based algorithms for scientific computations.

In Aug 2024 admissions, MATRIX lab is looking for bright and highly motivated research students to join our lab. We are seeking candidates interested in conducting highly interdisciplinary research across various disciplines, as outlined above. This is an exciting opportunity for students from traditional science and engineering backgrounds to engage in multidisciplinary research at the forefront of computational science and data science, thereby acquiring versatile skills.

Interview topics: Numerical methods, Linear Algebra, Calculus, Scientific programming, Differential equations, Topics based on student’s UG/PG background

Prior training: Bachelors’ or a Masters’ degree in any one of the following areas: Engineering Physics/Physics, Computer Science, Electrical/Electronics Engineering, Mechanical/Aero Engineering, Materials Engineering, Chemical Engineering, Computational Engineering, Physics, Applied Mathematics or similar areas. Strong programming skills are a must.

7. Medical Imaging Group (MIG)

Faculty: Phaneendra K. Yalavarthy


Lab description: MIG’s research work has consistently demonstrated a deep understanding of complex medical imaging systems and the development of innovative solutions to improve their performance. The group has made significant contributions in these areas, including development of novel algorithms for image reconstruction, the application of artificial intelligence techniques to medical imaging, and development of new imaging methods. The research work at MIG includes (a) developing technologies that extract quantitatively accurate information from imaging modalities, and (b) development of Artificial Intelligence (AI)- enabled digital assistants to provide rapid diagnosis/prognosis.  Our research group consistently publishes in leading journals of Medical Imaging, including IEEE Transactions on Medical Imaging, IEEE Transactions on Neural Networks, Medical Physics, NMR in Biomedicine, IEEE Transactions on Ultrasonics, Journal of Biomedical Optics, and Biomedical Optics Express. The group also has active collaborations with GE HealthCare, Shell Technology Centre, and leading hospitals in Bangalore, including Aster-CMI Hospital.

Interview topics: Linear Algebra and/or Signal Processing with Programming Background.

Prior Training: B.E./B.Tech. in EE/ECE/IN/CS/IT/BME (or) M.Sc. (Mathematics/Physics). Enthusiastic to work with clinicians and industry for impactful and translatable research (one ex:

8. Numerical Algorithms and Tensor Learning Laboratory (NAT Lab)

Faculty: Ratikanta Behera


Lab Description: We are developing adaptive recurrent neural networks to solve time-varying tensor equations. The aim is to design innovative, scalable, and efficient tensor-based algorithms supported by theoretical principles to solve significant existing and emerging multidimensional problems. Specifically, interested in developing fast tensor algorithms for solutions to multilinear systems, nonlinear optimization problems, low-rank approximation, generalized inverses of tensors, and solutions to partial differential equations in high dimensions problems. We also focus on developing HPC-centric adaptive wavelet algorithms for solving Partial Differential Equations (PDEs), Fractional Differential Equations (FDEs), integral equations, and signal & image processing.

Interview Topics: Linear/Matrix algebra, Numerical Methods, Differential Equations with Basic Programming.

Student Background: Mathematics is preferable. However, we welcome applicants with Physics, Computer Science, Earth Science, Information Technology, Electrical, Electronics and/or Communications, or any other closely related areas who are enthusiastic about learning and developing skills in these areas.

For the 2024 Admissions cycle, the NAT Lab is looking for 2-3 enthusiastic students interested in the following topic.

  1. Tensor Decompositions and Approximations
  2. Generalized inverses for Matrix/Tensor
  3. Neural Networks and its Applications
  4. Image/Video Processing
  5. Wavelet Methods for (Ordinary/Partial/Fractional) Differential Equations
  6. Wavelets in Scientific Computing

9. Quantifying Uncertainty in Engineering, Science and Technology (QUEST) Lab

Faculty: Deepak Subramani


Lab description:  This admission cycle, we are looking for students to develop and use AI/ML for weather prediction (development of Generative AI technologies), and guidance of autonomous underwater vehicles in uncertain worlds (development of Planning AI technologies).

Interview topics: Machine Learning, Training of Deep Neural Networks, Basics of Image Processing or Signal Processing, Data Analysis, Hypothesis Testing

Prior training: All backgrounds are welcome. Interest in AI/ML, ability to work long hours independently, likeable/friendly nature, and ability to work with other team members are necessary.

Important: Please see previous papers from the lab, watch our YouTube videos and ensure that you like the work we do.

10. Scientific Computation Lab (SCL)

Faculty: Soumyendu Raha


Lab description: The Scientific Computation Lab works on mathematical and computational aspects of Data Science and on Computational Mathematics.  Current research interests are in Computational aspects of Stochastic Differential Equations, application of constrained dynamical systems, construction of stochastic networks and complexes of simplices for learning from data from measurement of dynamical systems and prediction of responses. Application interests include but are not limited to very long-range surveillance of near space objects, power drop in VLSI physical designs, non-linear particle filters on graph networks and on complexes of simplices for learning and prediction of time series systems.   

Interview topics: Matrix Analysis, programming in a compiled (preferable) and/or interpreted language, computer implementation (basic data structure and foundational algorithms) of graph and/or linear algebra algorithms, probability theory. Familiarity with dynamical systems/ordinary differential equations (ODE) is a plus.

Prior training: Any advanced engineering mathematics book such as Kreyszig etc. for matrix analysis, probability and ODEs; any book on introductory programming in C/python with data structures used in first semesters of engineering courses.  Interview should reflect sound and in-depth prior training in these simple but foundational areas.

11. Scientific Machine Learning and Operations (STARS)

Faculty: Sashikumaar Ganesan


Lab description: STARS (Scientific Machine Learning and Operations) is an advanced research group specializing in scientific computing, machine learning, and high-performance computing. The lab focuses on two main areas:

  • Scientific Machine Learning (SciML): Innovating in machine learning algorithms for complex problems, employing Physics-informed neural networks (PINNs) for numerical improvements, and AI for parameter estimation in scientific simulations.
  • Machine Learning Operations (MLOps): Developing scalable ML algorithms and distributed training via cloud computing, enhancing ML model and data version control, and implementing robust CI/CD pipelines for effective real-world ML integration.

STARS stands out for merging scientific exploration with technological advancement, pushing boundaries in both academia and industry applications.  

Who can opt? STARS lab is seeking highly motivated PhD students to work on SciML, particularly in the area of Physics-informed neural networks (PINNs). For more details, check the latest publication at (

Interview topics: Numerical methods, linear algebra, scientific programming, differential equations, fluid mechanic.

Prior training: Candidates should have a degree in Engineering or Mathematics, and must be proficient in C/C++/Python programming. Applicants should also be willing to learn Finite Element Methods.

The following labs (CSL, DREAM, DSL, MARS, NLP, VAL, VCL) only accept students from CS/EE background qualification.

1. Cloud Systems Lab (CSL)

Faculty: J. Lakshmi

Website: and

Lab Description: Cloud Systems Lab (CSL) engages in large-scale distributed systems research, specifically in the emerging and evolving paradigms of service architectures, isolation, resource provisioning and management, virtualization, guarantees (QoS) for application performance, dependability, fault tolerance, etc. Incumbent students are required to have good background knowledge of Operating system topics like resource management, scheduling, process and memory management, disks, and file systems, I/O devices, interrupt management, networking, synchronization, deadlocks, agreement protocols, etc., and passion for systems research.

Current research work entails architecting and evaluating serverless platforms for QoS, realizing lightweight virtualization environment for real-time DAG based workflows, Service resilience using data-oriented recovery paradigms, Intelligent solutions for real-time dynamic optimal placement problems.

We are interested in, but not limited to, exploring disaggregated resources for distributed computing, stateful serverless paradigm, and software defined data centers.

Interview topics: Operating Systems, Distributed Systems, Computer Organization

Prior training: Students must have a Bachelors’ or Masters’ degree in Computer Science, Information Technology, Electrical, Electronics and/or Communications. Preference will be given to those having experience with any OS or Linux source code.

2. DREAM:Lab (Distributed systems Research on Emerging Applications & Machines)

Faculty: Yogesh Simmhan


Lab Description: Research in the DREAM:Lab focuses on distributed systems, Big Data platforms, scalable software platforms for ML, and distributed graph algorithms. We explore, design and develop software platforms, data management architectures and distributed algorithms, for efficient and reliable use of distributed computing systems like cloud computing, edge accelerators and quantum computing, with applications to emerging domains like fintech, drones/UAVs, hyperledger/blockchain and smart city/IoT. We emphasize hands-on systems research on real distributed and cloud computing systems, software platforms and large-scale empirical evaluations. We also actively collaborate with IBM Research, NPCI/UPI, University of Massachusetts-Amherst, Cardiff University, University of Melbourne, etc.

For the 2024 Admissions cycle, the DREAM:Lab is looking for 4-5 enthusiastic students interested in:

  • Scalable platforms for federated deep learning using GPU-accelerated edge and cloud computing
  • ML-driven scheduling algorithms and software platforms for serverless multi-cloud computing
  • Data management, routing strategies and edge+cloud analytics for drone fleet operations
  • Platforms and algorithms for hybrid quantum computing and cloud computing
  • Distributed and temporal algorithms for large graphs and GNNs in fintech and IoT
  • Scalable consensus algorithms and platforms for distributed hyperledgers and blockchain

Students must have strong aptitude and demonstrated skills in systems software, algorithms and programming.

Interview topics: Operating Systems (or) Graph Algorithms (or) Distributed Systems.

Recommended Reading:

  1. Operating System Concepts by Silberschatz, Gavin and Gagne
  2. Distributed Systems: Concepts and Design by Coulouris, et al.
  3. TiFL: A Tier-based Federated Learning System, Zheng Chai, et al, HPDC, 2020
  4. Pregel: A System for Large-Scale Graph Processing, Malewicz, et al., SIGMOD, 2010,

Prior training: Students must have a Bachelors/Masters degree in Computer Science, IT, Electrical, Electronics or Communications. Strong programming, algorithms and systems skills required. Ph.D. candidates preferred.

3. Database Systems Lab (DSL)

Faculty: Jayant R. Haritsa


Lab description: We work on the design, implementation and testing of the internals of database engines, and collaborate with major industrial research labs. Our lab’s software is used in many universities and companies worldwide.

Interview topics:  Data Models, Query Languages, Schema Design, Transaction Processing, Index Structures, Memory Management

Prior training:  Bachelor’s or Master’s in Computer Science/Information Technology, and creative aptitude for algorithms and computer systems.

4. Middleware And Runtime Systems (MARS) Lab

Faculty: Sathish Vadhiyar


Lab Description: High performance computing (HPC), Parallel computing – middleware, system software, algorithms and applications on large-scale parallel computers and GPUs.

Some of the recent research topics in the MARS lab are the following.

  • Harnessing the power of both CPUs and GPUs in a hybrid manner in modern-day parallel systems.
  • Novel models of parallelism for Machine Learning (ML)/Deep Learning (DL) applications.
  • High performance parallel I/O solutions for scientific and ML/DL applications.
  • Communication-minimization strategies for Exascale applications including development of asynchronous methods, one-sided communications and approximate computing.
  • Identifying scalability bottlenecks in parallel applications and developing acceleration and scalability improvement techniques.
  • Fault tolerance frameworks for parallel scientific and ML/DL applications.

Interview topics:

  1. Operating Systems including pthreads, filesystems.
  2. Computer architecture including multi-core CPUs and modern GPUs, differences between shared memory and distributed memory parallel architectures, different network topologies (e.g., ring, mesh etc.)
  3. MPI parallel programming interface – Google for “MPI Complete reference” and read Introduction, Point-to-Point and Collective Communications chapters.

Prior training: Students must have a Bachelors’ or Masters’ degree in Computer Science, Information Technology, Electrical, Electronics and/or Communications. Strong programming, algorithms and systems skills are required. Ph.D. candidates are preferred.

5. Natural Language Processing (NLP) Lab

Faculty: Danish Pruthi


Lab Description: This new lab broadly works in the areas of Natural Language Processing (NLP) and Machine Learning (ML). These areas already impact our lives—from answering questions we ask, curating content we read online, auto-completing words we are likely to type, to translating text from languages we don’t understand. The lab aims to ensure that such technologies are inclusive, safe and are adopted responsibly. Specifically, we work on projects related to inclusive model evaluation, model control (e.g., editing, de-biasing trained models) and validating data sources (in response to biased or harmful behavior). Additionally, we hope to contribute towards important NLP applications (e.g., content moderation, assisted writing), and engage in understanding their broader societal and ethical implications. From the outset, the lab is envisioned to be diverse, transparent, friendly and highly collaborative.

Interview topics: Language Modeling, Probability and basics of Machine Learning and Deep Learning.

Prior training: Students must have a Bachelors’ or Masters’ degree in Computer Science, Information Technology, Electrical, Electronics and/or Communications or other closely related disciplines.

6. Vision and AI Lab (VAL – formerly Video Analytics Lab)

Faculty: R. Venkatesh Babu


Lab Description: At VAL, we aim to perform world-class research in the broad fields of Computer Vision and Machine Learning, to push the performance limits on different applications, and ensure their reliability in practical settings. Our research and expertise spans across several areas in Deep Learning for Computer Vision as listed below:

i) Representation Learning iii) Domain Adaptation iv) Adversarial Attacks and Defenses v) Self-supervised and unsupervised learning vi) Out-of-Distribution (OOD) Robustness of Deep Models/ Domain Generalization vii) Object Detection viii) Learning on long-tail data ix) Generative models x) 3D Vision xi) Multi-modal learning.

Interview topics: Linear Algebra, Probability, Basics of Machine Learning and Image Processing (optional)

Prior training: Students must have a Bachelor’s or Master’s degree in either Computer Science, Information Technology, Electrical, Electronics and/or Communications or in any other closely related areas.

7. Visual Computing Lab (VCL)

Faculty: Anirban Chakraborty


Lab Description: At VCL, we are interested in developing novel computer vision and machine learning algorithms to solve visual analytics problems arising from real-world applications. The majority of our ongoing research projects can be categorized into one of the following three areas – 1. Data-efficient & privacy-preserving deep learning (zero-shot/few-shot knowledge distillation, continual learning, source-free/unsupervised domain adaptation, data-free adversarial defense, federated learning etc.), 2. Learning across modalities/domains (e.g., text-driven 3D scene editing, text-based image retrieval, sketch-guided localization, visual question answering, domain adaptation etc.) and 3. Perceiving humans and their actions (e.g., person-reidentification, anomaly detection, human gait and pose analysis etc.).

Interview topics: Linear Algebra, Probability and Machine Learning basics. Students are also strongly encouraged to read at least one recent paper from our group (see that aligns well with their research interests.

Prior training: Students must have a Bachelor’s or Master’s degree in Computer Science, Information Technology, Electrical, Electronics and/or Communications or in any other closely related areas. Applicants with strong mathematical aptitude and good programming skills will be given preference.