<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Papers on Arjun Ramesh Kaushik</title><link>https://arjunrkaushik.github.io/papers/</link><description>Recent content in Papers on Arjun Ramesh Kaushik</description><generator>Hugo -- 0.147.2</generator><language>en</language><atom:link href="https://arjunrkaushik.github.io/papers/index.xml" rel="self" type="application/rss+xml"/><item><title>Forget Less by Learning from Parents through Hierarchical Relationships</title><link>https://arjunrkaushik.github.io/papers/paper2/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://arjunrkaushik.github.io/papers/paper2/</guid><description>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.</description></item><item><title>Forget Less by Learning Together through Concept Consolidation</title><link>https://arjunrkaushik.github.io/papers/paper3/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://arjunrkaushik.github.io/papers/paper3/</guid><description>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.</description></item><item><title>Learning Action Hierarchies via Hybrid Geometric Diffusion</title><link>https://arjunrkaushik.github.io/papers/paper1/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://arjunrkaushik.github.io/papers/paper1/</guid><description>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.</description></item></channel></rss>