UNC CS presents computer vision research at WACV 2024
UNC CS researchers had two publications accepted at WACV 2023, one of which was selected for an oral presentation, a distinction reserved for the top 2.6 percent of papers at the conference.
UNC CS researchers had two publications accepted at WACV 2023, one of which was selected for an oral presentation, a distinction reserved for the top 2.6 percent of papers at the conference.
Winter graduate Pramit Thapa hopes to use his computer science experience to give back to the Nepalese community.
Perched atop a hill in the Kathmandu Valley, the ancient Swayambhu Temple proudly reflects Nepal’s rich cultural tapestry. In a groundbreaking initiative this past October, Religious Studies Professor Lauren Leve and Computer Science Research Scientist Jim Mahaney traveled to Swayambhu to start the long process of capturing the data needed to create an accurate 3D model of the entire temple complex.
UNC CS announces its participation in the Ego-Exo4D project, an innovative venture to revolutionize AI. An international consortium of 14 universities in partnership with Meta FAIR team will create a first-of-its-kind, large-scale, multimodal, multiview dataset that enhances AI’s perception, responsiveness, and understanding of human skill in real-world settings.
This fall, UNC Computer Science transformed into a hub of technological innovation and collaboration with two major student events: HackNC and the Carolina Data Challenge. These hackathons, led by student teams with department support, brought together more than 700 students from various colleges across North Carolina and beyond.
Professor Mohit Bansal earned the IIT Kanpur Young Alumnus Award, conferred annually to two alumni under 40 years old who have contributed significantly to achieve exemplary recognition and distinction in their careers. IIT Kanpur is one of the most prestigious academic institutions in India, and thousands of its alumni are eligible for the award.
In this exclusive interview, new professor Richard Marks reflects on the strategies he has developed over decades in the tech industry and offers a glimpse into the future of generative AI as well as what he hopes to bring to computer science education.
Branch-Solve-Merge (BSM) is a program for enhancing Large Language Models (LLMs) in complex natural language tasks. BSM includes branching, solving, and merging modules to plan, crack, and combine sub-tasks. Applied to LLM response evaluation and constrained text generation with several models, BSM boosts human-LLM agreement, reduces biases, and enables LLaMA-2-chat to match or surpass GPT-4 in most domains.
Assistant Professor Junier Oliva received a two-year NSF grant to improve the ability of machine learning models to extrapolate beyond the scope of their training dataset. The project will hopefully enhance scientific tasks across numerous disciplines, including chemical discovery and safety assessment.
Inbar Fried, Janine Hoelscher, and Ron Alterovitz received a Best Poster Award during the Data vs Model in Medical Robotics workshop held at the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). The award was only awarded to two posters submitted to the workshop.