Get started
Author

Viraj Prabhu

Observed name: Prabhu, Viraj
OpenAlex ID: A5110751285
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
2024 · Xue, Le, Shu, Manli, et al. · arXiv (Cornell University) · 205
PDF
Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
2021 · Viraj Prabhu, Arjun Chandrasekaran, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 153
PDF
SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation
2021 · Viraj Prabhu, Shivam Khare, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 126
PDF
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
2023 · Micah Goldblum, Hossein Souri, et al. · neural information processing systems · 78
PDF
Do explanations make VQA models more predictable to a human?
2018 · Arjun Chandrasekaran, Viraj Prabhu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 69
PDF
CoAct-1: Computer-using Multi-Agent System with Coding Actions
2025 · Song, Linxin, Dai, Yutong, et al. · arXiv (Cornell University) · 60
PDF
It Takes Two to Tango: Towards Theory of AI's Mind
2017 · Chandrasekaran, Arjun, Yadav, Deshraj, et al. · arXiv (Cornell University) · 60
PDF
Few-shot learning for dermatological disease diagnosis
2022 · Viraj Prabhu, Anitha Kannan, et al. · Elsevier eBooks · 46
Evaluating Visual Conversational Agents via Cooperative Human-AI Games
2017 · Prithvijit Chattopadhyay, Deshraj Yadav, et al. · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · 44
PDF
Do Explanations make VQA Models more Predictable to a Human?
2018 · Chandrasekaran, Arjun, Prabhu, Viraj, et al. · arXiv (Cornell University) · 41
PDF
Evaluating Visual Conversational Agents via Cooperative Human-AI Games
2017 · Chattopadhyay, Prithvijit, Yadav, Deshraj, et al. · arXiv (Cornell University) · 35
PDF
The Promise of Premise: Harnessing Question Premises in Visual Question Answering
2017 · Aroma Mahendru, Viraj Prabhu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 35
PDF
AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation
2021 · Prabhu, Viraj, Khare, Shivam, et al. · arXiv (Cornell University) · 27
PDF
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
2023 · Viraj Prabhu, Sriram Yenamandra, et al. · neural information processing systems · 26
PDF
BLIP-3: A Family of Open Large Multimodal Models
2025 · Le Xue, Manli Shu, et al. · IEEE International Conference on Computer Vision Workshops · 25
WALT: Web Agents that Learn Tools
2025 · Prabhu, Viraj, Dai, Yutong, et al. · arXiv (Cornell University) · 23
PDF
UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
2021 · Arvindkumar Krishnakumar, Viraj Prabhu, et al. · British Machine Vision Conference (BMVC) · 16
PDF
Prototypical Clustering Networks for Dermatological Disease Diagnosis
2018 · Prabhu, Viraj, Kannan, Anitha, et al. · arXiv (Cornell University) · 15
PDF
FACTS: First Amplify Correlations and Then Slice to Discover Bias
2023 · Sriram Yenamandra, Pratik Ramesh, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 14
PDF
S4T: Source-free domain adaptation for semantic segmentation via self-supervised selective self-training.
2021 · Viraj Prabhu, Shivam Khare, et al. · arXiv (Cornell University) · 13
Open Set Medical Diagnosis
2019 · Prabhu, Viraj, Kannan, Anitha, et al. · arXiv (Cornell University) · 13
PDF
Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency
2022 · Viraj Prabhu, Sriram Yenamandra, et al. · neural information processing systems · 12
PDF
Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
2023 · Prabhu, Viraj, Acuna, David, et al. · arXiv (Cornell University) · 10
PDF
Mitigating Bias in Visual Transformers via Targeted Alignment
2021 · Sruthi Sudhakar, Viraj Prabhu, et al. · British Machine Vision Conference (BMVC) · 7
PDF
Trust but Verify: Programmatic VLM Evaluation in the Wild
2025 · Viraj Prabhu, Senthil Purushwalkam, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 6
Works count: 34
Citation count: 1,196
H-index: 16
I10-index: 24
Year
Topic
Type