|
Kartik Narayan
I am a 3rd year Ph.D. student in the Computer Science
department
at Johns Hopkins University, where I am a member of VIU lab, advised by Dr.Vishal Patel. My current interests
lies in multimodal LLMs, agents,
reasoning and video generation. My prior research focused on computer vision and its applications in
face analysis, understanding,
and recognition, with a particular emphasis on multimodal LLMs.
Currently in my Ph.D., I have been fortunate to intern at:
- Apple (Navid Shiee, Peter Grasch, Chao Jia, Yinfei Yang, Zhe
Gan): Empowering Multimodal LLMs in Multimodal Agentic WebSearch.
Prior to my doctoral studies, I worked as an undergraduate researcher under
Prof. Richa Singh and
Prof. Mayank Vatsa at the
Image Analysis and Biometrics (IAB) Lab,
IIT Jodhpur, where I worked on deepfake video generation.
Email  / 
CV  / 
Google Scholar
 / 
LinkedIn  / 
Twitter  / 
Github
|
|
|
Research
My current research interests are multimodal LLMs, agents, reasoning and video generation. My
prior
research focused on computer vision and its applications in face analysis,
understanding, and recognition, with the goal of developing robust open-world algorithms that can be
deployed for real-world impact.
|
|
News
- [June, 2025] One Paper is accepted at ICCV 2025.
-
[May, 2025] Research Intern at
Apple for Summer 2025.
- [April, 2025] Two Papers are accepted at FG 2025.
- [December, 2024] One Paper is accepted at AAAI 2025.
- [October, 2024] One Paper is accepted at WACV 2025.
- [October, 2024] One Paper is accepted at IEEE TBIOM.
- [January, 2024] One Paper is accepted at FG 2024.
- [August, 2023] Joined as a PhD student at VIU Lab, Johns Hopkins University.
- [May, 2023] Received CVPR Student Travel Award.
- [Feb, 2023] One Paper is Accepted at CVPR 2023.
- [September, 2022] One Paper is Accepted at IEEE Access.
- [August, 2022] One Paper is Accepted at IJCB 2022.
- [April, 2022] One Paper is Accepted at CVPRW TCV 2022.
- [January, 2022] One Paper is Accepted at IEEE SysCon 2022.
|
|
Publications
See my Google
Scholar profile for the complete and most recent publications.
Representative papers are highlighted.
|
|
|
DeepMMSearch-R1: Empowering Multimodal LLMS in Mulitmodal Web Search
Kartik Narayan,
Yang Xu,
Tian Cao,
Kavya Nerella,
Vishal M. Patel,
Navid Shiee,
Peter Grasch,
Chao Jia,
Yinfei Yang,
Zhe Gan
Under Review
arXiv
|
|
|
|
FaceXFormer: A Unified Transformer for Facial Analysis
Kartik Narayan,
Vibashan VS,
Rama Chellappa,
Vishal M. Patel
ICCV 2025
arXiv /
project /
code (291 ⭐)
|
|
|
|
SegFace: Face Segmentation of Long-Tail Classes
Kartik Narayan,
Vibashan VS,
Vishal M. Patel
AAAI 2025
arXiv /
project /
code (84 ⭐)
|
|
|
|
FaceXBench: Evaluating Multimodal LLMs on Face Understanding
Kartik Narayan, Vibashan VS, Vishal M. Patel
Under Review
arXiv /
project /
code
|
|
|
PETALface: Parameter Efficient Transfer Learning for Low-resolution Face
Recognition
Kartik Narayan, Nithin Gopalkrishnan Nair, Jennifer Xu, Rama Chellappa, Vishal M.
Patel
WACV 2025 (Oral)
arXiv /
project /
code
|
|
|
|
FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
Kartik Narayan, Vishal M. Patel
Under Review
paper
|
|
|
|
Training-Free Stylized Abstraction
Aiman Rahman*, Kartik Narayan*, Vishal M. Patel
Under Review
arXiv /
project /
code
|
|
|
|
RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration
Sudarshan Rajagoplan, Kartik Narayan, Vishal M. Patel
Under Review
arXiv /
project /
code
|
|
|
|
INFER: Implicit Neural Features for Exposing Realism
Dhananjaya Jayasundara, Kartik Narayan, Vishal M. Patel
Under Review
paper
|
|
|
|
TransFIRA: Transfer Learning for Face Image Recognizability Assessment
Allen Tu, Kartik Narayan, Joshua Gleason, Jennifer Xu, Matthew Meyn, Tom Goldstein,
Vishal M. Patel
Under Review
arXiv
|
|
|
|
Investigating Social Biases in Multimodal LLMs
Malsha Perera*, Kartik Narayan*, Vishal M. Patel
IEEE International Conference on Automatic Face and Gesture
Recognition (FG) 2025
paper
|
|
|
|
Improved Representation Learning for Unconstrained Face Recognition
Nithin Gopalkrishnan Nair*, Kartik Narayan*, Maitreya Suin, Ram Prabhakar, Jennifer
Xu, Soraya Stevens, Joshua Gleason, Nathan Shnidman, Rama Chellappa, Vishal M. Patel
IEEE International Conference on Automatic Face and Gesture
Recognition (FG) 2025
paper
|
|
|
|
Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofing
Kartik Narayan, Vishal M. Patel
IEEE International Conference on Automatic Face and Gesture
Recognition (FG) 2024
paper /
project /
code
|
|
|
|
DF-Platter: Multi-subject Heterogeneous Deepfake Dataset
Kartik Narayan,
Harsh Agarwal,
Kartik Thakral,
Surbhi Mittal,
Mayank Vatsa,
Richa Singh
CVPR 2023
paper
/
poster
|
|
|
|
DeePhyNet: Towards Detecting Phylogeny in Deepfakes
Kartik Thakral, Harsh Agarwal, Kartik Narayan, Surbhi Mittal, Mayank Vatsa, Richa
Singh
IEEE Transactions on Biometrics, Behavior, and Identity Science
(T-BIOM)
paper
|
|
|
|
DeePhy: On Deepfake Phylogeny
Kartik Narayan, Harsh Agarwal, Kartik Thakral, Surbhi Mittal, Mayank Vatsa, Richa
Singh
International Joint Conference on Biometrics (IJCB) 2022
(Oral)
paper
|
|
|
|
DeSI: Deepfake Source Identifier for Social Media
Kartik Narayan, Harsh Agarwal, Surbhi Mittal, Kartik Thakral, Suman Kundu, Mayank
Vatsa, Richa Singh
CVPR Workshops 2022
paper
|
|
|