Favyen is an Applied Research Scientist on PRIOR at AI2. Prior to AI2, he was a Ph.D. student at the Massachusetts Institute of Technology, advised by Sam Madden. In addition to tackling challenges with employing computer vision methods in application domains, Favyen is interested in building systems that make it easier for users with little expertise to develop ML pipelines for analyzing their large-scale image and video datasets. Outside of research, he enjoys cycling, hiking, and reading science fiction and fantasy.
Kristin is an Executive Assistant for AllenNLP and PRIOR supporting Hannaneh Hajishirzi, Noah Smith, and Ranjay Krishna. Before Ai2, Kristin was at Amazon for 7 years working in recruiting, AWS SageMaker, and Books.
Christopher Clark received a PhD from the University of Washington, where he worked with Luke Zettlemoyer. His PhD work was on preventing models from picking up shallow heuristics that work on the training data, but do not generalize to out-of-domain settings. More broadly, he is interested in better understanding how deep learning systems learn and generalize when used for natural language processing or computer vision. Outside of research, he enjoys hiking, skiing and board games.
I am a Research Engineer at the Allen Institute for Artificial Intelligence (AI2), where I work on the PRIOR team. I received my Bachelor's degree in Computer Science from the University of Washington. My research interests broadly lie in robotics and computer vision.
Abhay is a PYI in PRIOR. He is a full-stack roboticist, whose research is in the area of robotic manipulation, and primarily focuses on learning for robotic control.
Roy is a PYI in PRIOR. His research is at the intersection of computer vision and robotics, and focuses on data-centric AI and multimodal learning.
Tanmay received his Ph.D. from the University of Illinois Urbana-Champaign where he was advised by Prof. Derek Hoiem and closely collaborated with Prof. Alex Schwing. Tanmay's research interests include learning from vision and language, and building general purpose learning systems. Besides research, Tanmay enjoys playing guitar and creating somewhat musical acoustic covers.
Having received a Bachelor of Arts in Game Design from the DigiPen Institute of Technology, Winson Han hopes to bring modern Game Design principles to the Computer Vision team. His focus on User Experience, Game Feel, and Game Mechanics Design bridges the gap between immersion in a digital space and the potential of real world applications. Along with Game Design, his interests include piano, digital art, and playing games—MMOs being his favorite.
Rose is a research engineer on PRIOR, formerly of the AST team. She received her PhD from the University of Washington in Mechanical Engineering, where she researched human-robot interaction. Her current research interests center around reinforcement learning and embodied AI. Outside of work, she has too many interests and should probably narrow it down a little.
Alvaro Herrasti received a B.S. in computer science and engineering at ITESM in Mexico City. After graduating, he worked at Microsoft's Xbox Live Team. Alvaro's interests include machine learning, AI applied to interactive environments, computer vision and natural language hybrid tasks, graphics and game design. He is fond of music; from listening and collecting records, to DJing and production.
Yejin Kim is a Research Engineer on the PRIOR team, holding an undergraduate degree from Johns Hopkins University and a master's degree from Cornell University. Her prior experience encompasses diverse aspects of research and development in robotics, including mechatronics, computer vision, and simulation. Her research interests center on enhancing the capabilities of dexterous mobile robots. In addition, Yejin is a painter and mixed-media artist. She showcased her artwork in generative AI and robotics at various forums.
Ranjay Krishna is the director of PRIOR at AI2 and an Assistant Professor at the Paul G. Allen School of Computer Science & Engineering. His research lies at the intersection of computer vision and human computer interaction. This research has received best paper, outstanding paper, and orals at CVPR, ACL, CSCW, NeurIPS, UIST, and ECCV, and been reported by Science, Forbes, the Wall Street Journal, and PBS NOVA. His research has been supported by Google, Amazon, Cisco, Toyota Research Institute, NSF, ONR, and Yahoo. He holds a bachelors degree in Electrical & Computer Engineering and in Computer Science from Cornell University, a masters degree in Computer Science from Stanford University and a Ph.D. in Computer Science from Stanford University.
Duong Le is a Research Engineer on the PRIOR team. He graduated from Ho Chi Minh city University of Technology in 2020 with a B.eng in Computer Science. Before joining AI2, he was at VinAI Research and also spent past summers interning at Stanford, NUS, and TUAT. Duong's research interests are in the area of learning from unlabeled data in vision domain.
Sangho Lee is a Research Scientist at AI2 on the PRIOR team. His research interests include multimodal representation learning, especially for high-level video understanding and reasoning. He received his PhD in Computer Science and Engineering from Seoul National University where he was advised by Prof. Gunhee Kim. Beyond research, he enjoys watching baseball or soccer games.
Wilbert is currently a PYI at PRIOR, working on robotics simulation and mobile manipulation. His primary area of interest is robotics learning and benchmarking.
I am a research scientist at Ai2 working on machine learning for the environment. I am also the inventor of YOLO.
Jordi received his Ph.D. from the Universitat Politecnica de Catalunya (Barcelona) in September 2011 and two M.Sc.'s, in Research on Information Technologies and in Telecommunication Engineering, from the same university in 2008 and 2006. Before joining AI2, he worked for Technicolor R&I and Amazon as a research scientist. His research interests range from multi-view reconstruction and machine learning-based image processing to applications of deep learning with main focus on computer vision. Besides research, he loves cooking, hiking, every piece of art of the Romantic era, science fiction and graphic novels.
Predoctoral researcher on AI2's PRIOR team, specializing in image/video generation and agentic AI. He holds an M.S. in Statistics from UW (2024) and a B.A. in Mathematics from Santa Clara University.
Rohun is a research engineer in PRIOR. Before AI2, he was working at Amazon in video generation and scene understanding. His research interests are in generative computer vision, scene understanding and 3D vision. He attended school at Cornell Tech and IIT Kanpur. When he is not working, he enjoys basketball, snowboarding, reading and petting dogs on the street.
Eli VanderBilt graduated from the University of Idaho in 2012, with a Bachelor of Science in 3D Art and Animation. Since then, he has worked as an artist in the fields of gaming, virtual reality, and architecture, with an emphasis on visual storytelling through player interaction. His hobbies include traveling, film study, fantasy/sci-fi literature, and arts & crafts.
Piper received her B.S. and M.S. degrees in Computer Science from Western Washington University in 2019 and 2021, where her research focused on few-shot learning for audio classification and event detection, as well as climate data emulation using generative adversarial networks. Piper's current research interests revolve around employing computer vision methods to various application domains. In her free time, she enjoys mountain biking, climbing, skiing, backpacking, and traveling.
Jitesh is a Ph.D. student in the School of Interactive Computing at Georgia Tech. His research interests revolve around developing multimodal systems. His previous works are based on analyzing and improving the visual perception ability in Multimodal Large Language Models, building upon his experience from working on developing models for dense prediction tasks.
Snehal is a PhD candidate at the PEARL group at TU Darmstadt, Germany. His research is focused on machine learning & computer vision for robotic perception and mobile manipulation, supervised by Georgia Chalvatzaki. At PRIOR, he is working on whole-body robot learning for mobile manipulation with Rose Hendrix!
Harris is a PhD student at the University of Wisconsin-Madison. His research interest is in developing generalist large multimodal models that excels in large variety of tasks. His previous works focused on improving spatial and temporal reasoning in VLMs, and his recent interest is on token pruning/compression.
Boyuan Zheng is a Research Intern on the PRIOR team. He is a Ph.D. student at The Ohio State University, advised by Prof. Yu Su. He received his M.S. degree from Johns Hopkins University and his B.S. degree from Northeastern University. His research focuses on building autonomous agents that use language as a vehicle for reasoning and communication. Outside of work, Boyuan enjoys hiking, traveling, and exploring delicious food.
Chenhao is a student researcher at AI2. He is a first year PhD student at the University of Washington, advised by Prof. Ranjay Krishna.
Research Intern at AI2, 2nd year PhD at UW
Tanush is a research intern on the PRIOR team interested in video understanding. He is also a rising senior at the University of Washington, where he studies computer science and mathematics. Outside of work, he enjoys running and hiking.
Jiafei Duan is a third year Ph.D. student at the Paul G. Allen School of Computer Science and Engineering, advised by Professors Dieter Fox and Ranjay Krishna. His research focuses on robot data generation and scaling multimodal large language models for robotics. His work is supported by A*STAR National Science PhD Fellowship.
I’m a Ph.D. student in Computer Science at the University of Washington, Seattle
I am a fourth-year Machine Learning PhD Student in the School of Interactive Computing at Georgia Institute of Technology co-advised by Professors Judy Hoffman (Georgia Tech) and Ranjay Krishna (UW).
I am a fourth year PhD student in computer science at the The University of Washington, where I work with Hannaneh Hajishirzi and Ali Farhadi. My research spans pretraining, post-training, and benchmarking multi-modal large language models, specifically video language models. Prior to UW, I received my B.Sc. in computer engineering from Sharif University of Technology. I publish under my full name Mohammadreza, and go by Reza among my friends.
Jae Sung is a PhD student at University of Washington and student researcher at AI2. His main interests are visual perception and language understanding for reasoning about the visual world, with a focus on visual commonsense reasoning, multimodal grounding, and evaluation of vision-language models.
Diego received his B.S in computer science in 2024, and will be receiving his Masters in 2025. His research in his undergrad and masters was focused on applications of machine learning for hyperspectral imagery and remote sensing. In their free time they run, bike, hike, climb, ski, and play bike polo.
I am a PhD student at the University of Washington in Computer Science and Engineering supervised by Prof. Ali Farhadi and Prof. Ranjay Krishna (RAIVN Lab). I'm also a graduate student researcher with PRIOR team at the Allen Institute for AI (AI2). In the summers of 2023 and 2024, I was a research intern with at the Allen Institute for AI (AI2), where I worked closely with Kuo-Hao Zeng and Kiana Ehsani. Previously, I received my Bachelor of Science in Computer Engineering from Sharif University of Technology. During the final year of my bachelor's program, I was a visiting student at EPFL where I worked in VILAB under the supervision of Prof. Amir Zamir. My research interests lie in the intersection of computer vision, machine learning, embodied-AI, and Robotics.
Haoquan is an undergraduate student at the University of Washington, pursuing a double major in computer science (with honors) and statistics, with a minor in mathematics. He is also a research collaborator working with the PRIOR team at the Allen Institute for AI. His research mainly focuses on robot learning, foundation models for robotics, and policy training.
Jason is a student researcher at the Allen Institute for AI with the PRIOR team and a master's student at the University of Washington, Seattle. His research focuses on robot learning and building internet scale robotics foundation models that can generalize to the real world.