Abstract Understanding 3D scenes semantically and spatially is crucial for the safe navigation of robots and autonomous vehicles, aiding obstacle avoidance and accurate trajectory planning. Camera-based 3D semantic occupancy prediction, whi... Read More
Abstract Atomic layer deposition (ALD) is extensively used to fabricate doped dielectrics due to its ability to deposit conformal films with atomic-scale thickness control. Al-doped TiO2 (ATO) is a promising high-k dielectric for dynamic ra... Read More
Traditionally, chemical reactions have been described as one-line “equations” in which substrates, say A and B, convert purposefully but rigidly into a desired product, say C. Naturally, it has been recognized that byproducts ma... Read More
UNIST has been selected to participate in the ‘AI Star Fellowship‘ project, a key initiative supported by the Ministry of Science and ICT (MSIT) and the Institute for Info & communication Tech Planning & evaluation (IITP... Read More
![[Forbes Korea] CEO JaeMin Park of Thyroscope Inc. Named Among Y30s RISING AI LEADERS](https://news.unist.ac.kr/wp-content/uploads/2025/10/Forbes-Korea-Y30s-선정-800x520-216x122.jpg)
The latest scientific and technological achievements of student startups based at UNIST have garnered international acclaim. Thyroscope Inc. (CEO JaeMin Park), a university-led venture company, has pioneered the world’s first commerci... Read More
The UNIST Industry Intelligentization Institute has been selected to participate in a new collaborative research initiative, titled ‘Global Convergence Research in Humanities and Social Sciences (Consortium-type),’ established b... Read More
Abstract Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out... Read More
On August 13, UNIST participated in the APEC 2025 Women in STEM Symposium held in Songdo, Incheon. The event brought together policymakers, industry leaders, academics, and emerging female scientists from across the Asia-Pacific region to a... Read More
Abstract Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framewo... Read More
A research team, led by Professor Seulki Lee from the Department of Computer Science and Engineering at UNIST has been honored with the Outstanding Paper Award at the International Conference on Machine Learning (ICML), one of the world... Read More
![[UNIST Webinar] AI enabled Computational Imaging for Biomedical Applications](https://news.unist.ac.kr/wp-content/uploads/2022/10/Session-13.18-296x166.jpg)