Animesh Kumar

animesh_linkedin.jpg

ank028[At]ucsd.edu

Hi! My name is Animesh Kumar. I am a second-year MS student in Computer Science at UC San Diego, working with Prof. Jingbo Shang and Prof. Arun Kumar. Previously, I worked as a Software Engineer at Oracle India in the Database Cloud organization, solving scalable database infrastructure and incident management challenges. I completed my undergraduate degree at NITK, India, in 2021, where my undergraduate thesis, under the guidance of Prof. Jeny Rajan, focused on improving Capsule Network architectures.

My research interests generally lie in multi-modal generative AI and ML systems. Currently, I am interested in:

  • Developing modular and scalable LLMs (e.g., Mixture-of-Experts).
  • Optimizing inference and training times of LLMs.
  • Understanding merging capabilities of neural networks.

In my free time, I enjoy hiking, lifting weights, cooking, and playing video games.

Publications

  1. EMNLP 2024
    Data Contamination Can Cross Language Barriers
    Feng Yao, Yufan Zhuang, Zihao Sun, Sunan Xu, Animesh Kumar, and 1 more author
    EMNLP, 2024
    PDF Code
  2. ACL 2024
    Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
    Xiaochen Kev Gao, Feng Yao, Kewen Zhao, Beilei He, Animesh Kumar, and 2 more authors
    ACL, (Oral), 2024
    PDF Code
  3. ICAC3N 2021
    Analysis of written interactions in open-source communities using RCNN
    Aashay Maheshwarkar, Animesh Kumar, and Manas Gupta
    In 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021
    PDF
  4. C2I4 2021
    Securing Database Backups Using Blockchain and Peer-to-Peer Network
    Aashay Maheshwarkar, Animesh Kumar, and Manas Gupta
    In 2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4), 2021
    PDF