I am a Research Scientist at GenAI Research (Meta) where I lead the generative efforts on…

• Using Org-mode and Subversion for Managing and Publishing Content in Computer Science Courses

  IEEE Conference on Technology for Education (T4E) 2012

  Content creation and management is an inevitable part of teaching a course. This paper describes a novel way of handling this problem using Org-mode, a recently created text based information management tool being used within the Emacs user community. We list certain desirable features, specially for the purposes of computer science courses, such as support for collaborative development and literate programming. We show how Org-mode compares favourably over other approaches like wikis and other…

  Content creation and management is an inevitable part of teaching a course. This paper describes a novel way of handling this problem using Org-mode, a recently created text based information management tool being used within the Emacs user community. We list certain desirable features, specially for the purposes of computer science courses, such as support for collaborative development and literate programming. We show how Org-mode compares favourably over other approaches like wikis and other content and course management systems. We describe why the combination of Org-mode and version control is suitable for creating and publishing content quickly, with minimum overhead in a collaborative manner.

  Other authors

  See publication

• Hybrid Implementation of Error Diffusion Dithering

  IEEE International Conference on High Performance Computing (HiPC) December 18, 2011

  Many image filtering operations provide ample parallelism, but progressive non-linear processing of images is among the hardest to parallelize due to long, sequential, and non-linear data dependency. A typical example of such an operation is error diffusion dithering, exemplified by the Floyd-Steinberg algorithm. In this paper, we present its parallelization on multicore CPUs using a block-based approach and on the GPU using a pixel based approach. We also present a hybrid approach in which the…

  Many image filtering operations provide ample parallelism, but progressive non-linear processing of images is among the hardest to parallelize due to long, sequential, and non-linear data dependency. A typical example of such an operation is error diffusion dithering, exemplified by the Floyd-Steinberg algorithm. In this paper, we present its parallelization on multicore CPUs using a block-based approach and on the GPU using a pixel based approach. We also present a hybrid approach in which the CPU and the GPU operate in parallel during the computation. High Performance Computing has traditionally been associated with high end CPUs and GPUs. Our focus is on everyday computers such as laptops and desktops, where significant compute power is available on the GPU as on the CPU. Our implementation can dither an 8K × 8K image on an off-the-shelf laptop with an Nvidia 8600M GPU in about 400 milliseconds when the sequential implementation on its CPU took about 4 seconds

  Other authors

  See publication

• MIT Tech Review's 35 innovators under 35

  MIT Tech Review

  Jul 2022

  Recognized for my contributions to self-supervised learning research by MIT Tech Review in 2022. I was featured in their 35 under 35 list which is compiled across all technological disciplines worldwide.

  Read more - https://www.technologyreview.com/innovator/ishan-misra/

• Best Student Paper: Data-Driven Exemplar Model Selection

  IEEE WACV

  Mar 2014

• Gold Medal for highest CGPA

  International Institute of Information Technology

  Oct 2012

• Carnegie Mellon University

  Graduate Student

  Aug 2012 - Present

• INRIA

  Intern/Stagiaire

  May 2012 - Aug 2012

• Yale University

  Summer Intern

  May 2011 - Jul 2011