Kartik Narayan

I am a 2nd 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 research focuses on computer vision and its applications in face analysis, understanding, and recognition, with a particular emphasis on multimodal LLMs and generation.

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. During my time at IIT Jodhpur, I also collaborated with Dr. Suman Kundu and Dr. Suchetana Chakraborty. Additionally, I interned at the University of Texas, San Antonio, where I worked with Dr. Heena Rathore and Dr. Faycal Znidi.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Twitter  /  Github

profile photo

Research

My research primarily focuses 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. My specific research interests include multimodal LLMs and video generation. My current work focuses on MLLM agents, reasoning, and video generation. I have authored multiple first-author papers in top conferences like CVPR, ICCV, AAAI.


News

  • [June, 2025] One Paper is accepted at ICCV 2025.
  • [May, 2025] I will join 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.

FaceXFormer: A Unified Transformer for Facial Analysis
Kartik Narayan, Vibashan VS, Rama Chellappa, Vishal M. Patel

ICCV 2025
arXiv / project / code (263 ⭐)
SegFace: Face Segmentation of Long-Tail Classes
Kartik Narayan, Vibashan VS, Vishal M. Patel

AAAI 2025
arXiv / project / code (69 ⭐)
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
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
Using Epidemic Modelling, Machine Learning and Control Feedback Strategy for Policy Management of COVID-19
Kartik Narayan, Heena Rathore, Faycal Znidi

IEEE Access 2022
paper / code
Leveraging ambient sensing for the estimation of curiosity-driven human crowd
Anirban Das, Kartik Narayan, Suchetana Chakraborty

IEEE Systems Conference (SysCon) 2022
paper

Template credits. Last updated June 2025.