Chameleon: Mixed-Modal Early-Fusion Foundation Models

Researcher at Apple working on speech, audio, and multimodal machine learning; previously a senior research scientist at SRI International and also worked at Google.

Researcher at Moonshot AI working on multimodal large language models; previously a key member of Alibaba's Qwen team and author of work including Kimi-VL, DeepSeek-VL, and Qwen technical reports.

Researcher at Alibaba Group exploring the math and science of large language models; incoming assistant professor at Nanyang Technological University.

Research scientist at Meta AI focused on vision-language models, large language models, and agents; public work includes the multimodal foundation model Chameleon.

Armand Joulin is a researcher and the cofounder and chief scientist of Mistral AI. Public arXiv records also list him as an author of LLaMA: Open and Efficient Foundation Language Models.

Research scientist at Meta working on computer vision and multimodal foundation models with an emphasis on robustness, trustworthiness, and alignment.

Mike Lewis is a natural language processing researcher whose public work includes multimodal language modeling and large-scale pretraining.

Alaaeldin El-Nouby is a machine learning researcher whose public work includes multimodal and vision-language models.

Christopher Pal is a professor and AI researcher whose public work spans deep learning, multimodal learning, and large language models.

Research scientist at Meta AI focused on multimodal and embodied AI, with interests in computer vision, deep learning, and decision making.

Khaled Saeed is a Research Scientist at Meta working on efficient multimodal reasoning and AI systems.

Faisal Azhar is a PhD candidate in computer science at Stanford University. His work focuses on multimodal systems that unify text, image, and speech, together with efficient training and inference for large-scale machine learning.

Senior AI research scientist at Meta and affiliate researcher at MIT working on computer vision and machine learning.

Computer scientist known for work in computer vision, machine learning, and human-centered AI.

Research scientist at FAIR working on multimodal systems.

Professor in computer science and engineering at the University of Washington, scientist at the Allen Institute for Artificial Intelligence, and co-director of the UW NLP group.

Research scientist at Meta working on multimodal reasoning, vision-language models, multimodal generation, and compression. His homepage highlights a background spanning machine learning, computer vision, and NLP.

Vice president of GenAI at Microsoft AI and a long-time machine learning researcher known for work on the foundations of reinforcement learning and bandits.

Research scientist at Meta working on embodied AI, robotics, and reinforcement learning.

Research scientist at Meta whose public work covers embodied AI, language agents, and multimodal systems; his arXiv author results include the Chameleon multimodal model paper.

Canonical link

Asterios Katsamanis

Hao Yang

Mingze Li

Chenguang Zhu

Armand Joulin

Nicholas Crane

Mike Lewis

Alaaeldin El-Nouby

Christopher Pal

Srujana Merugu

Khaled Saeed

Faisal Azhar

Alberto Mario Cadeddu

Fei-Fei Li

Geneviève Dorkenwald

Luke M. Zettlemoyer

Madhu Krishna

Sébastien Bubeck

Tianhe Yu

Udit Sodhi