Arka Mukherjee

arka.mukherjee078@gmail.com

Bengaluru, India

Hi, I’m Arka Mukherjee, a KIIT CS senior passionate about research in multimodal LLMs, evaluation science, reasoning, and AI agents, with a focus on human-computer and agent-computer interaction. Currently, I am a Research Intern at AMD working on LLM inference with Dr. S Pavankumar Dubagunta, and do research at IIT Bhubaneswar with Dr. Shreya Ghosh. I was also an IUSSTF-Viterbi Summer Research Intern at the University of Southern California with Dr. Maja Mataric, where I worked on efficient long-video understanding.

Beyond research, I engage with the tech community as a tech journalist, where I share insights on GPUs and emerging trends in AI.

news

Oct 19, 2026	Selected for the Google DeepMind APAC Research Symposium 2026.
Sep 01, 2026	I am joining the AMD AGI team as a Research Intern working on LLM inference.
Aug 26, 2026	Selected as a Singapore AI Safety Hub FAST fellow for frontier AI safety training.
Aug 22, 2026	GeoAgent was accepted to EMNLP 2026!
May 24, 2026	I am joining the USC Interaction Lab through the IUSSTF-Viterbi program.

selected publications

EMNLP
GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation

Arka Mukherjee, Soham Roy, Kartikeya, and 1 more author

In Findings of the Association for Computational Linguistics: EMNLP 2026, Oct 2026

Abs arXiv Bib HTML PDF Website

We evaluate vision-language model geolocalization through embodied navigation, studying how models coordinate visual reasoning, spatial grounding, and navigation decisions.
@inproceedings{mukherjee2026geoagent, title = {GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation}, author = {Mukherjee, Arka and Roy, Soham and {Kartikeya} and Ghosh, Shreya}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026}, year = {2026}, month = oct, }
ICCV
Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation

Arka Mukherjee and Shreya Ghosh

In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Oct 2025

Oral Abs Bib HTML PDF

Oral Presentation

We present the first systematic evaluation framework for assessing cultural competence in Vision-Language Models (VLMs) through multimodal story generation, analyzing five contemporary VLMs with novel evaluation metrics.
@inproceedings{mukherjee2025cultural, title = {Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation}, author = {Mukherjee, Arka and Ghosh, Shreya}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}, year = {2025}, month = oct, }
AACL
mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language Models

Arka Mukherjee and Shreya Ghosh

Findings of IJCNLP-AACL 2025, Nov 2025

Abs arXiv Bib HTML PDF Website

We introduce mmJEE-Eval, a bilingual multimodal benchmark comprising 1,460 STEM problems evaluating 17 VLMs. Models detect 53% of errors but correct only 3.5%, exposing metacognitive gaps between open and closed models.
@article{mukherjee2025mmjee, title = {mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language Models}, author = {Mukherjee, Arka and Ghosh, Shreya}, journal = {Findings of IJCNLP-AACL 2025}, year = {2025}, month = nov, }