Ranjay Krishna

Ranjay Krishna is an Assistant Professor at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where he co-directs the RAIVN lab and leads the computer vision team at the Allen Institute for AI (Ai2). His research intersects computer vision, natural language processing, robotics, and human-computer interaction.

• PhD in Computer Science from Stanford University (2021)
• Bachelor's and Master's degrees from Stanford and Cornell

His work has received best paper, outstanding paper, and orals at top conferences like CVPR, ACL, CSCW, NeurIPS, UIST, and ECCV. Media outlets including Science, Forbes, and PBS NOVA have covered his research. He has been supported by grants from Google, Apple, NFS, and others.

Ranjay advises a diverse group of 15 PhD and postdoctoral researchers, including Jieyu Zhang, Benlin Liu, and Cheng-Yu Hsieh. His teams have developed benchmarks like MemoryBench and The Colosseum, and his PathFinder framework achieved 74% accuracy in skin melanoma diagnosis—surpassing human experts by 9%.

Notable contributions include:

• Perception Tokens for visual reasoning in MLMs
• SAM2Act for robotic manipulation with memory
• Synthetic Visual Genome dataset with 5.6M relationships