3 papers
cs.CV2025
LLMs can see and hear without any training
Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen +2
We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ab…
cs.CL2025
IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding
Sankalp KJ, Ashutosh Kumar, Laxmaan Balaji +4
Known by more than 1.5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to…
cs.CV2024
SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
Changan Chen, Kumar Ashutosh, Rohit Girdhar +2
We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Whereas existing methods rely on curated data with known audio-…