We do research on natural language processing, machine learning and combining vision and language. We work on information and semantic extraction from language. We investigate methodologies to interplay between learning and reasoning and develop techniques to include declarative and procedural world knowledge in statistical/neural learning. We develop research software and build prototypes to facilitate designing AI systems. We also aim to apply our techniques and tools on real world-problems and conduct multi-disciplinary research to impact the society for making the world a better place to live.
Congratulations to our great member Dr. Yue Zhang (Joslin) who officially graduated today! We all wish the best for the next phase of her life!
January 29th 2025
Dr. Parisa has been selected for a Fulbright award to Vietnam!
January 22nd 2025Two more papers for NAACL 2025!🎉 'Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models', led by Darius, accepted for the main conference! Congratulations Darius, very well done! AND 'Neuro-symbolic Training for Reasoning over Spatial Language', led by Tanawan Premsri, accepted for Findings. Congratulations Tanawan! Congratulations to HLR team!
January 22nd 2025Two Papers from Our HLR Lab Accepted at ICLR 2025!🎉 'SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models', led by Joslin. Second: 'Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities', in collaboration with UMich SLED lab. Many congratulations to HLR team!
January 15th 2025Dr. Parisa was interviewed by 517 Magazine about the impact of AI on business! [More Info]
December 27th 2024Dr. Parisa will give a collaborative Tutorial in NAACL-2025 entitled 'Learning Language through Grounding', with Freda Shi, Ziqiao Ma, Jiayuan Mao, and Joyce Chai
December 9th 2024Two papers accepted for AAAI-2025! Congratulations to Darius and Danial for your hard work and Great achievements! 'Reasoning over Uncertain Text by Generative Large Language Models', first-authored by Darius and 'NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization', first-authored by Danial.
Novemeber 15th 2024Congratulate Joslin for her paper accepted by TMLR Journal! 'Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models'
November 14th 2024Danial was presenting the work of 'NesyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization' in EMNLP GenBench Workshop 2024, Miami
