Srikumar Ramalingam

Research Scientist, Google

Joined

October 2017

Names

Srikumar Ramalingam

Emails

****@gmail.com (Confirmed)

****@cs.utah.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Research Scientist

Google (google.com)

2019 – Present

Associate Professor

Computer Science, , University of Utah (cs.utah.edu)

2017 – 2019

Researcher

Mitsubishi Electric Research Labs (merl.com)

2008 – 2016

Advisors, Relations & Conflicts

Postdoc Advisor

Philip. H.S. Torr

2007 – 2008

PhD Advisor

Peter Sturm

2003 – 2006

Expertise

Deep Learning

Present

Probabilistic Graphical models

Present

Text-to-Image generation

Present

Multi-view geoemetry and 3D reconstruction

Present

Publications

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
Dylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh, Srikumar Ramalingam, Gui Citovsky, Sanjiv Kumar
- NeurIPS 2025 poster
- Readers: Everyone
GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
Matthew Fahrbach, Srikumar Ramalingam, Morteza Zadimoghaddam, Sara Ahmadian, Gui Citovsky, Giulia DeSalvo
- NeurIPS 2025 poster
- Readers: Everyone
On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions
Maximilian Böther, Abraham Sebastian, Pranjal Awasthi, Ana Klimovic, Srikumar Ramalingam
- MLSys 2025
- Readers: Everyone
Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training
Hanna Mazzawi, Pranjal Awasthi, Javier Gonzalvo, Srikumar Ramalingam
- Compression Workshop @ NeurIPS 2024
- Readers: Everyone
SurfR: Surface Reconstruction with Multi-scale Attention
Siddhant Ranade, Gonçalo Dias Pais, Ross Tyler Whitaker, Pedro Miraldo, Jacinto C Nascimento, Srikumar Ramalingam
- 3DV 2025 Poster
- Readers: Everyone
LS3D: Single-view gestalt 3D surface reconstruction from Manhattan line segments
Yiming Qian, Srikumar Ramalingam, James H Elder
- 10 Nov 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
When does mixup promote local linearity in learned representations?
Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit, Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar
- 06 Oct 2022 (modified: 05 May 2023)
- INTERPOLATE at NeurIPS 2022
- Readers: Everyone
Leveraging Importance Weights in Subset Selection
Gui Citovsky, Giulia DeSalvo, Sanjiv Kumar, Srikumar Ramalingam, Afshin Rostamizadeh, Yunjuan Wang
- Published: 01 Feb 2023, Last Modified: 01 Mar 2023
- ICLR 2023 poster
- Readers: Everyone
Learning Strict Identity Mappings in Deep Residual Networks
Xin Yu, Zhiding Yu, Srikumar Ramalingam
- 30 Mar 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Less data is more: Selecting informative and diverse subsets with balancing constraints
Srikumar Ramalingam, Daniel Glasner, Kaushal Patel, Raviteja Vemulapalli, Sadeep Jayasumana, Sanjiv Kumar
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone

View all 45 publications

Co-Authors

View all 83 co-authors