Scholar
Vasu Sharma
Google Scholar ID: PLUB4dIAAAAJ
Facebook AI Research (FAIR)
Citations & Impact
Citations
8,169
H-index
15
i10-index
19
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- - DINOv2: Learning Robust Visual Features without Supervision, TMLR 2024
- - MAViL: Masked Audio-Video Learners, NeurIPS 2023
- - Chameleon: Mixed-Modal Early-Fusion Foundation Models, arXiv 2024
- - Alexa Arena: Embodied-AI Platform, NeurIPS 2023
- - FLAP: Fast Language-Audio Pre-training, ASRU 2024
Research Experience
- - Applied Research Scientist Lead, Meta AI (FAIR), Aug 2022 – Present, Menlo Park, CA: Tech-lead for Llama 3/4, Chameleon, and MoE initiatives; designed MaVIL, a SOTA masked audio-video learner; developed text-quality scoring that halved training corpus size with no loss.
- - Applied Scientist, Amazon Alexa AI, Aug 2021 – Aug 2022, Sunnyvale, CA: Co-founded Alexa Arena embodied-AI benchmark; built real-time multimodal transformers.
- - Quantitative Research Analyst, Citadel GQS, Aug 2019 – Aug 2021, Chicago, IL: Automated cross-asset alpha construction with large-scale ML pipelines.
Education
- - M.S. Language Technologies, Carnegie Mellon University, GPA 4.19/4.33 (dept rank #1)
- - B.Tech. CSE, IIT Kanpur, CPI 9.9/10; All-India JEE Rank 165
- - AISSCE, St. Columba’s School, 97%
Background
- Research Interests: Multimodal foundation models, generative AI agents. Overview: Currently leading applied research at Meta AI (FAIR) with a focus on 100B-parameter LLMs and self-supervised vision & audio-video systems.
Miscellany
- Personal Interests: Open to research collaborations and speaking engagements.
