{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:37:18Z","timestamp":1778344638901,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888601","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Chitrarth: Bridging Vision and Language for a Billion People"],"prefix":"10.1109","author":[{"given":"Shaharukh","family":"Khan","sequence":"first","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayush","family":"Tarun","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Ravi","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Faraz","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Praveen Kumar","family":"Pokala","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anagha","family":"Bhangare","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raja","family":"Kolla","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chandra","family":"Khatri","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubham","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Krutrim AI,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref3","article-title":"Deepseek-vl: towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref4","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024"},{"key":"ref5","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024"},{"key":"ref6","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024"},{"key":"ref7","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref9","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref10","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024"},{"key":"ref11","article-title":"Airavata: Introducing hindi instruction-tuned llm","author":"Gala","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3639856.3639890"},{"key":"ref13","article-title":"Krutrim LLM: Multilingual foundational model for over a billion people","author":"Team","year":"2024","journal-title":"Under Review"},{"key":"ref14","article-title":"Sutra: Scalable multilingual language model architecture","author":"Bendale","year":"2024"},{"key":"ref15","article-title":"The refinedweb dataset for falcon llm: outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref17","article-title":"Building and better understanding vision-language models: insights and future directions","author":"Lauren\u00e7on","year":"2024"},{"key":"ref18","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref20","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Perceiver: General perception with iterative attention","volume-title":"ICLR","author":"Jaegle"},{"key":"ref22","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref24","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref25","article-title":"Pali: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref26","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref28","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref29","article-title":"Palo: A polyglot large multimodal model for 5b people","author":"Maaz","year":"2024"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.595"},{"key":"ref34","article-title":"MM-VET: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref40","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.54"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888601.pdf?arnumber=10888601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:02Z","timestamp":1774416122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888601","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}