Kshitij Ambilduke

नमस्कार !

I am Kshitij Ambilduke, a second-year master’s student at the MVA program, ENS Paris-Saclay. My research interests broadly surround Natural Language Processing (NLP) and I am particularly excited about extensions of NLP towards other modalities like speech and vision. I am currently interning at NAVER LABS Europe under the supervision of Marcely Zanon Boito, Vassilina Nikoulina and Caroline Brun, working on the evaluation of Speech LLMs.

Before my master's, I worked on extending LLMs to speech as a Research Assistant under the guidance of Prof. André F. T. Martins and Prof. Bruno Martins at the SARDINE lab in Lisbon. More recently, I investigated the gains of using complementary multimodal data over unimodal counterparts in a video-game corpus under the supervision of Dr. Djamé Seddah at the ALMAnaCH team, INRIA-Paris.

I completed my bachelor’s in Electronics and Communication from Visvesvaraya National Institute of Technology (VNIT), India. I did my bachelor's thesis with Dr. Anamika Singh where I worked on image captioning. During my pre-final year summer, I worked on interpretable Visual Question Answering under the supervision of Prof. André F. T. Martins and Prof. Bruno Martins.

I was also fortunate to be a part of IvLabs, the AI and Robotics lab of VNIT, where I developed most of my research interests thanks to the oversight of Prof. Shital Chiddarwar

News

Apr. 2026
Starting an internship at NAVER LABS Europe on evaluation of Speech LLMs.
Sep. 2025
Starting my second year of master's at the MVA program, ENS Paris-Saclay.
Aug. 2025
From Tower to Spire: Adding the Speech Modality to a Text-Only LLM Accepted at the Findings of EMNLP 2025.
Mar. 2025
From Tower to Spire: Adding the Speech Modality to a Text-Only LLM available on arXiv.
Sep. 2024
Starting my first year of master’s at the Computer Science department (AI Track), Université Paris-Saclay.
May 2024
Awarded with the France Excellence Charpak Master Scholarship 2024 for pursuing my master's at Université Paris-Saclay.

Show older news (5)Show less

Jul. 2023
Attended LxLMS: Lisbon Machine Learning School 2023.
Feb. 2023
My paper titled "Attending to Transforms: A Survey on Transformer-based Image Captioning" was accepted at PCEMS 2023.
Oct. 2021
My paper titled "Enhancing Context Through Contrast" was accepted at the NeurIPS 2022 Pre-registration workshop.
Sep. 2021
Ranked amongst the top 100 teams in the Amazon ML Challenge 2021.
Aug. 2021
Elected as the Chairperson for IEEE VNIT Student Branch.

Publications

EMNLP 2025 · Findings

From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM

Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani, Tsz Kin Lam, Bruno Martins, André F.T. Martins, Marcely Zanon Boito

Findings of EMNLP 2025

@inproceedings{ambilduke-etal-2025-tower,
    title = "From Tower to Spire: Adding the Speech Modality to a Translation-Specialist {LLM}",
    author = "Ambilduke, Kshitij  and
      Peters, Ben  and
      Sannigrahi, Sonal  and
      Keshwani, Anil  and
      Lam, Tsz Kin  and
      Martins, Bruno  and
      Martins, Andre  and
      Zanon Boito, Marcely",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.1071/",
    doi = "10.18653/v1/2025.findings-emnlp.1071",
    pages = "19658--19673",
    ISBN = "979-8-89176-335-7"
}

PCEMS 2023

Attending to Transforms: A Survey on Transformer-based Image Captioning

Kshitij Ambilduke, Thanmay Jayakumar, Luqman Farooqui, Himanshu Padole, Anamika Singh

Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS 2023)

Paper

@inproceedings{ambilduke2023attending,
    title = {Attending to Transforms: A Survey on Transformer-based Image Captioning},
    author = {Ambilduke, Kshitij and Jayakumar, Thanmay and Farooqui, Luqman and Padole, Himanshu and Singh, Anamika},
    booktitle = {2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)},
    pages = {1--6},
    year = {2023},
    publisher = {IEEE},
    doi = {10.1109/PCEMS58491.2023.10136098}
}

NeurIPS 2021 · Workshop

Enhancing Context through Contrast

Kshitij Ambilduke, Aneesh Shetye, Diksha Bagade, Rishika Bhagwatkar, Khurshed Fitter, Prasad Vagdargi, Shital Chiddarwar

NeurIPS 2021 Workshop on Pre-registration in Machine Learning

@inproceedings{ambilduke2021enhancing,
    title = {Enhancing Context Through Contrast},
    author = {Ambilduke, Kshitij and Shetye, Aneesh and Bagade, Diksha and Bhagwatkar, Rishika and Fitter, Khurshed and Vagdargi, Prasad and Chiddarwar, Shital},
    booktitle = {NeurIPS 2021 Workshop on Pre-registration in Machine Learning},
    year = {2021},
    url = {https://preregister.science/papers_21neurips/18_paper.pdf}
}