<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Alternative Architectures and Paradigms on AAP 2026 — Alternative Architectures and Paradigms</title><link>https://AAP-INLG.github.io/</link><description>Recent content in Alternative Architectures and Paradigms on AAP 2026 — Alternative Architectures and Paradigms</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://AAP-INLG.github.io/index.xml" rel="self" type="application/rss+xml"/><item><title>Call for Papers</title><link>https://AAP-INLG.github.io/cfp/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://AAP-INLG.github.io/cfp/</guid><description>&lt;h2 id="overview"&gt;Overview&lt;/h2&gt;
&lt;p&gt;In the past few years, autoregressive transformers have been the dominant method in Natural Language Generation (NLG). While scaling these models has brought astounding results, this approach relies on a single core method (neural networks), a single generative paradigm (sequential next-token prediction), and a single architecture (the transformer decoder). This layout comes with significant limitations: quadratic computational cost, hallucinations, and a lack of learning during inference time, just to name a few. Furthermore, relying on scaling alone becomes more difficult high-quality training data is becoming scarce and compute more expensive.&lt;/p&gt;</description></item><item><title>Organizers</title><link>https://AAP-INLG.github.io/organizers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://AAP-INLG.github.io/organizers/</guid><description>&lt;p&gt;This workshop is organised by members of the &lt;a href="https://utrechtnlphub.sites.uu.nl/"&gt;NLP@Utrecht&lt;/a&gt; community, a research group spanning Utrecht University and UMC Utrecht. The group works at the intersection of natural language processing, machine learning, and real-world applications — combining expertise in language model evaluation, explainable AI, and clinical NLP. AAP 2026 grows directly out of this shared interest in broadening the architectural foundations of language generation.&lt;/p&gt;
&lt;hr&gt;
&lt;div style="display:flex;align-items:flex-start;gap:1.5rem;margin-bottom:2rem;"&gt;
&lt;img src="https://AAP-INLG.github.io/images/robert.jpg" alt="Robert Bagheri" class="br-100 ba b--black-10 flex-shrink-0" style="width:120px;height:120px;object-fit:cover;"&gt;
&lt;div&gt;
&lt;h3 id="robert-bagheri--utrecht-university"&gt;Robert Bagheri — Utrecht University&lt;/h3&gt;
&lt;p&gt;Robert A. Bagheri is an Associate Professor of NLP, Machine Learning, and Interpretability at Utrecht University, where he leads the Natural Language and Text Processing lab. His research centres on explainable AI for NLP and the evaluation and application of language models in societal contexts, while actively driving interdisciplinary collaboration through initiatives such as the Utrecht NLP Hub. He holds multiple leadership roles across Utrecht University and the EWUU alliance, contributing to AI strategy, interdisciplinary research, and early-career researcher development.&lt;/p&gt;</description></item><item><title>Program</title><link>https://AAP-INLG.github.io/program/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://AAP-INLG.github.io/program/</guid><description>&lt;p&gt;&lt;em&gt;18 October 2026, Utrecht, Netherlands (TBC)&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;The full program will be announced after the paper acceptance notification (1 September 2026). The schedule below shows the planned structure.&lt;/p&gt;
&lt;hr&gt;
&lt;h2 id="schedule"&gt;Schedule&lt;/h2&gt;
&lt;style&gt;table td:first-child { white-space: nowrap; }&lt;/style&gt;
&lt;table&gt;
	&lt;thead&gt;
			&lt;tr&gt;
					&lt;th&gt;Time&lt;/th&gt;
					&lt;th&gt;Session&lt;/th&gt;
			&lt;/tr&gt;
	&lt;/thead&gt;
	&lt;tbody&gt;
			&lt;tr&gt;
					&lt;td&gt;09:00–09:15&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Opening&lt;/strong&gt; — Coffee and welcome&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;09:15–09:30&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Introduction&lt;/strong&gt; — Overview of the AAP workshop&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;09:30–10:15&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Keynote / Oral Session 1&lt;/strong&gt; — Invited talk and presentations&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;10:15–10:30&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Coffee Break&lt;/strong&gt; — Poster viewing&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;10:30–11:30&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Oral Session 2&lt;/strong&gt; — 3 oral presentations&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;11:30–11:45&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Coffee Break&lt;/strong&gt; — Poster viewing&lt;/td&gt;
			&lt;/tr&gt;
			&lt;tr&gt;
					&lt;td&gt;11:45–12:30&lt;/td&gt;
					&lt;td&gt;&lt;strong&gt;Poster Session&lt;/strong&gt;&lt;/td&gt;
			&lt;/tr&gt;
	&lt;/tbody&gt;
&lt;/table&gt;
&lt;hr&gt;
&lt;h2 id="keynote-speaker"&gt;Keynote Speaker&lt;/h2&gt;
&lt;p&gt;&lt;em&gt;To be announced.&lt;/em&gt;&lt;/p&gt;</description></item></channel></rss>