Viraj Prabhu

I am a research scientist on the multimodal AI team at Salesforce Research. I received my PhD in Computer Science from Georgia Tech in December 2023, where I was advised by Judy Hoffman and worked on making computer vision models generalize to new environments. I earned my Master's in CS (awarded the MS Research award) in May 2019, also at Georgia Tech, where I was advised by Devi Parikh and worked on developing visual conversational agents.

In grad school, I've had the opportunity to intern at NVIDIA (with Sanja Fidler), Salesforce (with Nikhil Naik), and Curai (with Anitha Kannan). Before that, I've had stints as a research assistant at Virginia Tech (with Dhruv Batra), a software engineer at Adobe, and a mentor for Google Summer of Code. I received my Bachelor's degree in Computer Science from BITS Pilani in 2015.

In my free time, I enjoy reading, running, soccer, and playing the guitar.

Email / CV / Scholar / LinkedIn / Github

CoAct-1: Computer-using Agents with Coding as Actions

Linxin Song, Yutong Dai, Viraj Prabhu, Jieyu Zhang, Taiwei Shi, Li Li, Junnan Li, Silvio Savarese, Zeyuan Chen, Jieyu Zhao, Ran Xu, Caiming Xiong

[Project] [Paper] [Code]

Trust but Verify: Programmatic VLM Evaluation in the Wild

Viraj Prabhu, Senthil Purushwalkam, An Yan, Caiming Xiong, Ran Xu

ICCV 2025

[Paper] [Data] [Explorer]

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Salesforce AI Research (Viraj Prabhu: core contributor)

ICCV 2025 Findings Workshop

[Paper] [Project]

We're Not Using Videos Effectively: An Updated Video Domain Adaptation Baseline

Simar Kareer, Vivek Vijaykumar, Harsh Maheshwari, Judy Hoffman, Prithvijit Chattopadhyay, Viraj Prabhu

TMLR 2024

[Paper] [Code]

Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets

Yuan-Hong Liao, David Acuna, Rafid Mahmood, James Lucas, Viraj Prabhu, Sanja Fidler

ICLR 2024

[Paper]

AUGCAL: Sim-to-Real Adaptation by Improving Uncertainty Calibration on Augmented Synthetic Images

Prithvijit Chattopadhyay, Bharat Goyal, Bogi Ecsedi, Viraj Prabhu, Judy Hoffman

ICLR 2024

[Paper] [arXiv]

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

Viraj Prabhu, Sriram Yenamandra, Prithvijit Chattopadhyay, Judy Hoffman

NeurIPS 2023

[Paper] [Code] [Project] [News]

Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting

Viraj Prabhu, David Acuna, Yuan-Hong Liao, Rafid Mahmood, Marc T. Law, Judy Hoffman, Sanja Fidler, James Lucas

TMLR 2023

[Paper] [arXiv]

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Vision Tasks

Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Adrien Bardes, Mark Ibrahim, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein

NeurIPS Datasets & Benchmarks 2023

[Paper] [Code]

FACTS: First Amplify Correlations and Then Slice to Discover Bias

Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu, Judy Hoffman

ICCV 2023

[Paper] [arXiv]

ICON²: Reliably Benchmarking Inequity in Detection by Identifying and Controlling for Confounders

Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman

CVPR Workshop 2023

[Paper]

Can domain adaptation make object recognition work for everyone?

Viraj Prabhu, Ramprasaath R. Selvaraju, Judy Hoffman, Nikhil Naik

CVPR Workshop 2022

[Paper] [Code]

Mitigating Bias in Visual Transformers via Targeted Alignment

Sruthi Sudhakar, Viraj Prabhu, Arvind Krishnakumar, Judy Hoffman

BMVC 2021

[Paper] [arXiv]

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

Viraj Prabhu*, Sriram Yenamandra*, Aaditya Singh, Judy Hoffman (* = equal contribution)

NeurIPS 2022

[Paper] [arXiv] [News]

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Segmentation

Viraj Prabhu*, Shivam Khare*, Deeksha Kartik, Judy Hoffman (* = equal contribution)

ECCV Workshop 2022

[Paper] [Talk]

UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models

Arvind Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman

BMVC 2021

[Paper] [arXiv] [Code]

Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

ICCV 2021

[Paper] [Code] [Video] [Webpage]

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Viraj Prabhu, Arjun Chandrasekaran, Kate Saenko, Judy Hoffman

ICCV 2021

[Paper] [Code] [Project] [Video]

Open Set Medical Diagnosis

Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso, Namit Katariya, Manish Chablani, David Sontag, Xavier Amatriain

NeurIPS Workshop 2019

Few-shot Learning for Dermatological Disease Diagnosis

Viraj Prabhu, Anitha Kannan, Murali Ravuri, Manish Chablani, David Sontag, Xavier Amatriain

MLHC 2019 (spotlight)

[Paper] [arXiv]

Do Explanations make VQA Models more Predictable to a Human?

Arjun Chandrasekaran*, Viraj Prabhu*, Deshraj Yadav*, Prithvijit Chattopadhyay*, Devi Parikh (* = equal contribution)

EMNLP 2018

[Paper] [arXiv]

The Promise of Premise: Harnessing Question Premises in Visual Question Answering

Aroma Mahendru*, Viraj Prabhu*, Akrit Mohapatra*, Dhruv Batra, Stefan Lee (* = equal contribution)

EMNLP 2017

[Project] [arXiv] [Code]

Evaluating Visual Conversational Agents via Cooperative Human-AI Games

Prithvijit Chattopadhyay*, Deshraj Yadav*, Viraj Prabhu, Arjun Chandrasekaran, Abhishek Das, Stefan Lee, Dhruv Batra, Devi Parikh (* = equal contribution)

HCOMP 2017

[Paper] [Code]

Viraj Prabhu

Research

CoAct-1: Computer-using Agents with Coding as Actions

Trust but Verify: Programmatic VLM Evaluation in the Wild

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

We're Not Using Videos Effectively: An Updated Video Domain Adaptation Baseline

Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets

AUGCAL: Sim-to-Real Adaptation by Improving Uncertainty Calibration on Augmented Synthetic Images

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Vision Tasks

FACTS: First Amplify Correlations and Then Slice to Discover Bias

ICON²: Reliably Benchmarking Inequity in Detection by Identifying and Controlling for Confounders

Can domain adaptation make object recognition work for everyone?

Mitigating Bias in Visual Transformers via Targeted Alignment

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Segmentation

UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models

Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Open Set Medical Diagnosis

Few-shot Learning for Dermatological Disease Diagnosis

Do Explanations make VQA Models more Predictable to a Human?

The Promise of Premise: Harnessing Question Premises in Visual Question Answering

Evaluating Visual Conversational Agents via Cooperative Human-AI Games

Miscellaneous

Service & Recognition

Talks & Media

Projects & Software