Kartik Narayan
@KartikNarayan10
Followers
103
Following
353
Media
4
Statuses
74
AIML Research Intern @ | PhD CS @ Johns Hopkins University
Baltimore, MD
Joined May 2019
Interesting work! We took it a step further, aligned with GPT-4o’s abstraction capabilities instead and made it training-free. Training Free Stylized Abstraction:
ShareGPT-4o-Image. Aligning Multimodal Models with GPT-4o-Level Image Generation
0
0
2
#ICCV2025 🌺FaceXFormer has been accepted by ICCV !.
FaceXFormer: A Unified Transformer for Facial Analysis .w/ @vibashan @KartikNarayan10 @jhuclsp @HopkinsEngineer.@JHUECE. Paper: Code: Website:
0
2
12
RT @vishalm_patel: 🎨 New work: Training-Free Stylized Abstraction.Generate stylized avatars (LEGO, South Park, dolls) from a single image !….
0
6
0
RT @koushik_srivats: 📣 If you’re at #CVPR2025 in Nashville, come check out our Highlight 🌟paper:. 🧠 STEREO: A Two-Stage Framework for Adver….
0
1
0
RT @vishalm_patel: 💥 New paper: Think Before You Diffuse. Meet DiffPhy — LLM-guided, physics-aware video diffusion 🎥🧠🌍.SOTA on real-world m….
0
23
0
RT @vishalm_patel: Honored to be speaking alongside other respected experts at the Biometrics Institute US Biometrics Seminar. We’ll be div….
0
6
0
🥳🥳Two papers accepted in FG 2025 !!!. Improved Representation Learning for Unconstrained Face Recognition.w/ @NithinGK10 @vishalm_patel . Investigating Social Biases in Multimodal LLMs.w/ Malsha Perera, @vishalm_patel.
1
2
11
RT @HopkinsEngineer: Even the most advanced MLLMs struggle spotting deepfakes or counting crowds when put the test with @vishalm_patel's F….
engineering.jhu.edu
New tool tests AI models on everything from identifying faces to detecting biases in facial data
0
6
0
Our recent work FaceXBench: Evaluating Multimodal LLMs on Face Understanding !!!. We believe FaceXBench will be a.crucial resource for developing MLLMs equipped to perform sophisticated face understanding.
We present FaceXBench, a benchmark of 5,000 multimodal multiple-choice questions from 25 public datasets, spanning 14 tasks across 6 categories, for face understanding. @vibashan @HopkinsEngineer @KartikNarayan10 @JHUECE @JHUCompSci @jhuclsp . GIthub:
0
2
5
RT @shaoyuanlo: 📢 Excited to share that our paper published in @IEEEComputerSoc T-PAMI 2022 was recently featured in @ieeecesoc News on Con….
0
5
0
Project Page: Hugging Face: The improved face segmentation performance can help in numerous downstream applications such as face swapping, face completion, facial makeup, and face modeling.
huggingface.co
0
1
1
#AAAI2025.Introducing SegFace: Face Segmentation of Long-Tail Classes, which achieves SOTA face segmentation performance. w/ @vibashan @vishalm_patel . Paper: GitHub: @JHUCompSci @JHUECE @HopkinsEngineer @jhuclsp
1
6
11
RT @vishalm_patel: Check out our new work PETALface, where we harness the power of parameter-efficient fine-tuning to address the challengi….
0
3
0
RT @vishalm_patel: 📢 Excited to share that the JHU VIU Lab will present three papers at #NeurIPS2024 this week! 🎉 Join us at our poster ses….
0
8
0
phew 😮💨!!!.#CVPR2025.
… and that’s a wrap for the #CVPR2025 paper submission deadline. Good luck!. Live view of your publicity media chair @CSProfKGD 🥱
0
0
3
RT @vishalm_patel: Call for Papers: IEEE TBIOM Special Issue on “Generative AI and Large Vision-Language Models for Biometrics".Please subm….
0
3
0
RT @vishalm_patel: Check out our WACV'25 paper where we conduct an in-depth examination of sample replication in video diffusion models.….
0
6
0
October Update! 🎉. 1 paper accepted to #WACV2025 with @NithinGK10 @vishalm_patel . 1 paper accepted to IEEE T-BIOM with @thakralkartik78 @surbhimittal97 @MayankVatsa3 @RichaSingh26. Stay tuned for the paper and code! #WACV #TBIOM #IEEE @wacv_official.
1
1
9
RT @vishalm_patel: The JHU VIU Lab will be presenting the following papers at ECCV this week in Milan! Stop by our posters and say hello! @….
0
3
0