Arjun Ramesh Kaushikhttps://arjunrkaushik.github.io/Recent content on Arjun Ramesh KaushikHugo -- 0.147.2enWed, 08 May 2024 00:00:00 +0000Locationhttps://arjunrkaushik.github.io/location/Wed, 08 May 2024 00:00:00 +0000https://arjunrkaushik.github.io/location/Arjun's office addressOffice Hourshttps://arjunrkaushik.github.io/officehours/Wed, 08 May 2024 00:00:00 +0000https://arjunrkaushik.github.io/officehours/Schedule and location for Professor Dr von Igelfeld's office hours.List of Irregular Verbs Across Romance Languageshttps://arjunrkaushik.github.io/data/data1/Thu, 07 Mar 2013 00:00:00 +0000https://arjunrkaushik.github.io/data/data1/This dataset contains all irregular verbs in known Romance languages.Lectures at the Villa of Reduced Circumstanceshttps://arjunrkaushik.github.io/courses/course1/Mon, 10 Mar 2003 00:00:00 +0000https://arjunrkaushik.github.io/courses/course1/This graduate course presents classical results in Romance philology.Portugese Irregular Verbshttps://arjunrkaushik.github.io/books/book1/Wed, 01 Jan 1997 00:00:00 +0000https://arjunrkaushik.github.io/books/book1/This book discusses Portugese irregular verbs in great details.Profanity in Early Irishhttps://arjunrkaushik.github.io/courses/course2/Sat, 16 Jun 1990 00:00:00 +0000https://arjunrkaushik.github.io/courses/course2/This undergraduate course discusses profanity in Early Irish.Forget Less by Learning from Parents through Hierarchical Relationshipshttps://arjunrkaushik.github.io/papers/paper2/Mon, 01 Jan 0001 00:00:00 +0000https://arjunrkaushik.github.io/papers/paper2/Catastrophic forgetting is a persistent challenge for Custom Diffusion Models in continual learning, often addressed by minimizing interference between concepts. Instead, we exploit this very interference to learn common features among concepts.Forget Less by Learning Together through Concept Consolidationhttps://arjunrkaushik.github.io/papers/paper3/Mon, 01 Jan 0001 00:00:00 +0000https://arjunrkaushik.github.io/papers/paper3/Catastrophic forgetting is a persistent challenge for Custom Diffusion Models in continual learning, often addressed by minimizing interference between concepts. Instead, we exploit this very interference to learn common features among concepts.Learning Action Hierarchies via Hybrid Geometric Diffusionhttps://arjunrkaushik.github.io/papers/paper1/Mon, 01 Jan 0001 00:00:00 +0000https://arjunrkaushik.github.io/papers/paper1/Human actions unfold through multiple levels of abstraction, yet current action segmentation approaches typically consider a flat, Euclidean relationship between actions. This paper remedies this limitation by enforcing hierarchical structure amongst actions.