1<!DOCTYPE html> 2<html lang="en"> 3<head> 4 <!-- Google tag (gtag.js) -->
vendor: 66 bytes, lines 4-5
4 5 <script async src="https://www.googletagmanager.com/gtag/js?id=
5G-E00L9PT3V9
vendor: 14 bytes, lines 5-6
5"></script> 6
6<script> 7
vendor: 139 bytes, lines 7-10
7window.dataLayer = window.dataLayer || []; 8 function gtag(){dataLayer.push(arguments);} 9 gtag('js', new Date()); 10 gtag('config', '
10G-E00L9PT3V9
vendor: 6 bytes, lines 10-11
10'); 11
11</script>
11 12 13 <meta charset="utf-8"> 14 <meta name="viewport" content="width=device-width, initial-scale=1"> 15 <meta name="author" content="Lennart Bastian"> 16 17 <!-- favicon: inline SVG emoji (no asset file) --> 18 <link rel="icon" href='data:image/svg+xml,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><text y=".9em" font-size="90">ðª¢</text></svg>'> 19 20 21 <title>Lennart Bastian</title> 22 23 24 <link rel="canonical" href="https://bastianlb.github.io/"> 25 <link rel="stylesheet" type="text/css" href="/style.css"> 26 <link href="https://fonts.googleapis.com/css?family=Lato:400,400italic,700,700italic&display=swap" rel="stylesheet" type="text/css"> 27</head> 28 29<body> 30 <svg width="0" height="0" class="icon-sprite" aria-hidden="true" focusable="false" style="position:absolute"> 31 <defs> 32 <symbol id="i-globe" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 33 <circle cx="12" cy="12" r="10"/><path d="M2 12h20"/><path d="M12 2a15.3 15.3 0 0 1 4 10 15.3 15.3 0 0 1-4 10 15.3 15.3 0 0 1-4-10 15.3 15.3 0 0 1 4-10z"/> 34 </symbol> 35 <symbol id="i-arxiv" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 36 <path d="M4 22h16a2 2 0 0 0 2-2V4a2 2 0 0 0-2-2H8a2 2 0 0 0-2 2v16a2 2 0 0 1-2 2Zm0 0a2 2 0 0 1-2-2v-9c0-1.1.9-2 2-2h2"/><path d="M18 14h-8"/><path d="M15 18h-5"/><path d="M10 6h8v4h-8V6Z"/> 37 </symbol> 38 <symbol id="i-paper" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 39 <path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/><path d="M14 2v6h6"/><path d="M16 13H8"/><path d="M16 17H8"/><path d="M10 9H8"/> 40 </symbol> 41 <symbol id="i-video" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 42 <path d="m22 8-6 4 6 4V8Z"/><rect width="14" height="12" x="2" y="6" rx="2" ry="2"/> 43 </symbol> 44 <symbol id="i-code" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 45 <path d="m18 16 4-4-4-4"/><path d="m6 8-4 4 4 4"/><path d="m14.5 4-5 16"/> 46 </symbol> 47 <symbol id="i-poster" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 48 <rect width="18" height="18" x="3" y="3" rx="2" ry="2"/><circle cx="9" cy="9" r="2"/><path d="m21 15-3.086-3.086a2 2 0 0 0-2.828 0L6 21"/> 49 </symbol> 50 <symbol id="i-slides" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 51 <path d="M2 3h20"/><path d="M21 3v11a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V3"/><path d="m7 21 5-5 5 5"/> 52 </symbol> 53 <symbol id="i-bibtex" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 54 <path d="M6 3h6a2 2 0 0 1 2 2v14a2 2 0 0 0-2-2H6a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2Z"/><path d="M18 3a2 2 0 0 1 2 2v10a2 2 0 0 1-2 2h-1"/> 55 </symbol> 56 <symbol id="i-mail" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"> 57 <rect width="20" height="16" x="2" y="4" rx="2"/><path d="m22 7-8.97 5.7a1.94 1.94 0 0 1-2.06 0L2 7"/> 58 </symbol> 59 <symbol id="i-github" viewBox="0 0 24 24" fill="currentColor"> 60 <path d="M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23A11.509 11.509 0 0 1 12 5.803c1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222 0 1.606-.014 2.898-.014 3.293 0 .322.216.694.825.576C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12"/> 61 </symbol>
62 <symbol id="i-linkedin" viewBox="0 0 24 24" fill="currentColor"> 63 <path d="M20.447 20.452h-3.554v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286zM5.337 7.433a2.062 2.062 0 0 1-2.063-2.065 2.064 2.064 0 1 1 2.063 2.065zm1.782 13.019H3.555V9h3.564v11.452zM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003z"/> 64 </symbol> 65 <symbol id="i-scholar" viewBox="0 0 24 24" fill="currentColor"> 66 <path d="M5.242 13.769L0 9.5 12 0l12 9.5-5.242 4.269C17.548 11.249 14.978 9.5 12 9.5c-2.977 0-5.548 1.748-6.758 4.269zM12 10a7 7 0 1 0 0 14 7 7 0 0 0 0-14z"/> 67 </symbol> 68 <symbol id="i-twitter" viewBox="0 0 24 24" fill="currentColor"> 69 <path d="M18.901 1.153h3.68l-8.04 9.19L24 22.846h-7.406l-5.8-7.584-6.638 7.584H.474l8.6-9.83L0 1.154h7.594l5.243 6.932 6.064-6.933zm-1.291 19.527h2.039L6.486 3.24H4.298l13.312 17.44z"/> 70 </symbol> 71 <symbol id="i-youtube" viewBox="0 0 24 24" fill="currentColor"> 72 <path d="M23.498 6.186a3.016 3.016 0 0 0-2.122-2.136C19.505 3.545 12 3.545 12 3.545s-7.505 0-9.377.505A3.017 3.017 0 0 0 .502 6.186C0 8.07 0 12 0 12s0 3.93.502 5.814a3.016 3.016 0 0 0 2.122 2.136c1.871.505 9.376.505 9.376.505s7.505 0 9.377-.505a3.015 3.015 0 0 0 2.122-2.136C24 15.93 24 12 24 12s0-3.93-.502-5.814zM9.545 15.568V8.432L15.818 12l-6.273 3.568z"/> 73 </symbol> 74 </defs> 75</svg> 76 77 <!-- Animated flow-field backdrop (decorative; ignored by AT) --> 78<canvas id="bg-field" class="bg-field" aria-hidden="true"></canvas>
79<script src="/assets/background.js" defer></script>
79 80 81 <header class="site-header"> 82 <a class="brand" href="/">Lennart Bastian</a> 83 <nav class="site-nav" aria-label="Primary"> 84 <a href="/" aria-current="page">Home</a> 85 <a href="/publications/">Publications</a> 86 <a href="/news/">News</a> 87 <span class="nav-ext"> 88 <a href="https://scholar.google.com/citations?user=huXOVHgAAAAJ&hl=en">Scholar</a> 89 <a href="https://github.com/bastianlb">GitHub</a> 90 </span> 91 </nav> 92</header> 93 94 95 <main class="page"> 96 97 <section class="hero"> 98 <img class="hero-photo" src="/images/defense-sunset-circle.png" alt="Lennart Bastian"> 99 <div class="hero-text"> 100 <h1>Lennart Bastian</h1> 101 <p> 102 I am a Research Fellow at Imperial College London, supported through the UK Royal Society <a href="https://royalsociety.org/news/2025/11/early-career-fellowships-2025/">Newton International Fellowship</a>, 103 where I pursue topics at the intersection of geometry, topology, and machine learning with exciting applications in the natural and physical sciences. 104 </p> 105 <p> 106 I completed my PhD with highest distinction (<i>summa cum laude</i>) at the <a href="https://www.cs.cit.tum.de/camp/">Chair for Computer Aided Medical Procedures</a> (CAMP) in Munich, supervised by <a href="https://www.cs.cit.tum.de/camp/members/cv-nassir-navab/nassir-navab/">Prof. Nassir Navab</a>, where I also coordinated research of the <a href="https://www.cs.cit.tum.de/camp/research/surgical-data-science/">Surgical Data Science</a> team. 107 Prior to this, I conducted my M.Sc. in Applied Mathematics at the Technical University of Munich with an emphasis on optimization and statistics, and Bachelor's in Mathematics and Computer Science from New York University's Courant Institute. 108 </p> 109 <p> 110 I also enjoyed stints in software and data science at <
110a href="https://h2ometrics.com/">H2oMetrics</a>, a cloud water management startup, and as a research assistant at the MSKCC <a href="https://www.mskcc.org/research-areas/labs/ross-levine">Levine Lab</a>, developing computational tools for the genetic analysis of myeloid leukemias. 111 </p> 112 <p class="hero-links"> 113 <a target="_blank" href="https://mailhide.io/e/kALrRC4M" title="Email" aria-label="Email"><svg class="ico"><use href="#i-mail"></use></svg></a> 114 <a href="https://www.linkedin.com/in/lennart-bastian-4a867421/" title="LinkedIn" aria-label="LinkedIn"><svg class="ico"><use href="#i-linkedin"></use></svg></a> 115 <a href="https://x.com/lennart_bastian" title="X" aria-label="X (Twitter)"><svg class="ico"><use href="#i-twitter"></use></svg></a> 116 <a href="https://scholar.google.com/citations?user=huXOVHgAAAAJ&hl=en" title="Google Scholar" aria-label="Google Scholar"><svg class="ico"><use href="#i-scholar"></use></svg></a> 117 <a href="https://github.com/bastianlb" title="GitHub" aria-label="GitHub"><svg class="ico"><use href="#i-github"></use></svg></a> 118 </p> 119 </div> 120 </section> 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146<section id="news" class="news" aria-labelledby="news-heading"> 147 <h2 id="news-heading">Recent Updates</h2> 148 <ul class="news-list"> 149 150 <li> 151 <time datetime="2026-10-01">Oct 2026</time> 152 <span class="news-text"><a href='/publications/#topoor-a-unified-topological-scene-representation-for-the-operating-room'><strong>TopoOR</strong></a> received the <strong>Young Scientist Award</strong> at MICCAI 2026.</span> 153</li> 154 155 156 <li> 157 <time datetime="2026-09-25">Sep 2026</time> 158 <span class="news-text"><a href='/publications/#compose-hypergraph-cover-optimization-for-multi-view-3d-human-pose-estimation'><strong>COMPOSE</strong></a> accepted to NeurIPS 2026.</span> 159</li> 160 161 162 <li> 163 <time datetime="2026-09-08">Sep 2026</time> 164 <span class="news-text">Co-hosted the first edition of <a href='https://geo-int.github.io/'><strong>Geometric Intelligence</strong></a> at ECCV 2026 in Malmö, where I was also nominated outstanding reviewer (Top 6.4%)</span> 165</li> 166 167 168 <li> 169 <time datetime="2026-05-18">May 2026</time> 170 <span class="news-text">Recognized as an <strong>Outstanding Reviewer</strong> for CVPR 2026 (Top 5%) and a <strong>Gold Reviewer</strong> for ICML 2026 (Top 25%).</span> 171</li> 172 173 174 <li> 175 <time datetime="2026-05-15">May 2026</time> 176 <span class="news-text">Two papers — <a href='/publications/#dispose-projected-polystochastic-diffusion-for-self-supervised-3d-multi-view-human-pose-estimation'><strong>DisPOSE</strong></a> and <a href='/publications/#collapsed-effective-operators-for-higher-order-structures'><strong>Collapsed Effective Operators</strong></a> — accepted to ICML 2026.</span> 177</li> 178 179 180 <li> 181 <time datetime="2026-05-10">May 2026</time> 182 <span class="news-text"><a href='/publications/#topoor-a-unified-topological-scene-representation-for-the-operating-room'><strong>TopoOR</strong></a> accepted to MICCAI 2026 (Early Accept, Top 9%).</span> 183</li> 184 185 186 <li> 187 <time datetime="2026-02-15">Feb 2026</time> 188 <span class="news-text">Co-leading <strong>TopoFound</strong>, a £1.3m AIRR-funded grant.</span> 189</li> 190 191 192 <li> 193 <time datetime="2026-02-01">Feb 2026</time> 194 <span class="news-text"><a href="https://profiles.imperial.ac.uk/l.bastian">Started as a research fellow at Imperial College London.</a></span> 195</li> 196 197 198 </ul> 199 200 201 <p class="news-actions"> 202 203 <a href="/news/">All news →</a> 204 </p> 205 206</section>
207<script src="/assets/news.js"></script>
207 208 209 210 211 <section class="selected"> 212 <div class="section-head"> 213 <h2>Selected Work</h2> 214 <p class="section-intro"> 215 I study the geometry and topology hidden in data, building machine learning methods that exploit it. 216 The resulting algorithms are relevant to numerous fields: i'm particular fond of applications in the natural sciences, including medicine, biology and physical systems. 217 </p> 218 </div> 219 220 <div class="pub-list"> 221 222 223 224<article class="pub-card" id="compose-hypergraph-cover-optimization-for-multi-view-3d-human-pose-estimation"> 225 <figure class="pub-thumb"> 226 <a href="/publications/#compose-hypergraph-cover-optimization-for-multi-view-3d-human-pose-estimation" aria-label="COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation â see on publications page"> 227 <img src="/tn/images/compose.jpg" alt="COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation teaser" loading="lazy"> 228 <figcaption class="banner">NeurIPS</figcaption> 229 </a> 230 </figure> 231 <div class="pub-body"> 232 <h3 class="pub-title"><a href="/publications/#compose-hypergraph-cover-optimization-for-multi-view-3d-human-pose-estimation">COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation</a></h3> 233 <p class="pub-authors">Tony Danjun Wang, Tolga Birdal, Nassir Navab, <strong>Lennart Bastian</strong></p> 234 <p class="pub-venue"><em>Neural Information Processing Systems (<strong>NeurIPS</strong>)</em>, 2026</p> 235 <p class="pub-links"><a href="https://wngtn.github.io/COMPOSE/" title="Webpage" aria-label="Webpage"><svg class="ico"><use href="#i-globe"></use></svg></a><a href="https://arxiv.org/abs/2601.09698" title="arXiv" aria-label="arXiv"><svg class="ico"><use href="#i-arxiv"></use></svg></a><a href="https://github.com/wngTn/COMPOSE" title="Code" aria-label="Code"><svg class="ico"><use href="#i-code"></use></svg></a></p> 236 237 </div> 238</article> 239 240 241 242 243<article class="pub-card" id="topoor-a-unified-topological-scene-representation-for-the-operating-room"> 244 <figure class="pub-thumb"> 245 <a href="/publications/#topoor-a-unified-topological-scene-representation-for-the-operating-room" aria-label="TopoOR: A Unified Topological Scene Representation for the Operating Room â see on publications page"> 246 <img src="/tn/images/topoor.png" alt="TopoOR: A Unified Topological Scene Representation for the Operating Room teaser" loading="lazy"> 247 <figcaption class="banner oral">MICCAI</figcaption> 248 </a> 249 </figure> 250 <div class="pub-body"> 251 <h3 class="pub-title"><a href="/publications/#topoor-a-unified-topological-scene-representation-for-the-operating-room">TopoOR: A Unified Topological Scene Representation for the Operating Room</a></h3> 252 <p class="pub-authors">Tony Danjun Wang, Ka Young Kim, Tolga Birdal, Nassir Navab, <strong>Lennart Bastian</strong></p> 253 <p class="pub-venue"><em>Medical Image Computing and Computer Assisted Intervention (<strong>MICCAI</strong>) - <strong><span style='color: #d4582a;'>Early Accept (Top 9%)</span></strong> · <strong><span style='color: #b8860b;'>Young Scientist Award</span></strong></em>, 2026</p> 254 <p class="pub-links"><a href="https://wngtn.github.io/TopoOR/" title="Webpage" aria-label="Webpage"><svg class="ico"><use href="#i-globe"></use></svg></a><a href="https://arxiv.org/abs/2603.09466" title="Paper" aria-label="Paper"><svg class="ico"><use href="#i-arxiv"></use></svg></a></p> 255 256 </div> 257</article> 258 259 260 261 262<article class="pub-card" id="topological-neural-operators"> 263 <figure class="pub-thumb"> 264 <a href="/publications/#topological-neural-operators" aria-label="Topological Neural Operators â see on publications page"> 265 <img src="/tn/images/tno.png" alt="Topological Neural Operators teaser" loading="lazy"> 266 <figcaption class="banner">Preprint</figcaption> 267 </a> 268 </figure> 269 <div class="pub-body"> 270 <h3 class="pub-title"><a href="/publications/#topological-neural-operators">Topological Neural Operators</a></h3> 271 <p class="pub-authors"><strong>Lennart Bastian</strong>, Samuel Leventhal, Mustafa Hajij, Tolga Birdal</p> 272 <p class="pub-venue"><em>Preprint</em>, 2026</p> 273 <p class="pub-links"><a href="https://arxiv.org/abs/2606.09806" title="arXiv" aria-label="arXiv"><svg class="ico"><use href="#i-arxiv"></use></svg></a></p> 274 275 </div> 276</article> 277 278 279 280 281<article class="pub-card" id="dispose-projected-polystochastic-diffusion-for-self-supervised-3d-multi-view-human-pose-estimation"> 282 <figure class="pub-thumb"> 283 <a href="/publications/#dispose-projected-polystochastic-diffusion-for-self-supervised-3d-multi-view-human-pose-estimation" aria-label="DisPOSE: Projected Polystochastic Diffusion for Self-Supervised 3D Multi-View Human Pose Estimation â see on publications page"> 284 <img src="/tn/images/dispose.jpg" alt="DisPOSE: Projected Polystochastic Diffusion for Self-Supervised 3D Multi-View Human Pose Estimation teaser" loading="lazy"> 285 <figcaption class="banner">ICML</figcaption> 286 </a> 287 </figure>
288 <div class="pub-body"> 289 <h3 class="pub-title"><a href="/publications/#dispose-projected-polystochastic-diffusion-for-self-supervised-3d-multi-view-human-pose-estimation">DisPOSE: Projected Polystochastic Diffusion for Self-Supervised 3D Multi-View Human Pose Estimation</a></h3> 290 <p class="pub-authors">Tony Danjun Wang, Tolga Birdal, Nassir Navab, <strong>Lennart Bastian</strong></p> 291 <p class="pub-venue"><em>International Conference on Machine Learning (<strong>ICML</strong>)</em>, 2026</p> 292 <p class="pub-links"><a href="https://wngtn.github.io/DisPOSE/" title="Webpage" aria-label="Webpage"><svg class="ico"><use href="#i-globe"></use></svg></a><a href="https://arxiv.org/abs/2606.07419" title="arXiv" aria-label="arXiv"><svg class="ico"><use href="#i-arxiv"></use></svg></a><a href="https://github.com/wngTn/DisPOSE" title="Code" aria-label="Code"><svg class="ico"><use href="#i-code"></use></svg></a></p> 293 294 </div> 295</article> 296 297 298 299 300<article class="pub-card" id="collapsed-effective-operators-for-higher-order-structures"> 301 <figure class="pub-thumb"> 302 <a href="/publications/#collapsed-effective-operators-for-higher-order-structures" aria-label="Collapsed Effective Operators for Higher-order Structures â see on publications page"> 303 <img src="/tn/images/collapsed.jpg" alt="Collapsed Effective Operators for Higher-order Structures teaser" loading="lazy"> 304 <figcaption class="banner">ICML</figcaption> 305 </a> 306 </figure> 307 <div class="pub-body"> 308 <h3 class="pub-title"><a href="/publications/#collapsed-effective-operators-for-higher-order-structures">Collapsed Effective Operators for Higher-order Structures</a></h3> 309 <p class="pub-authors">Maximilian Krahn*, <strong>Lennart Bastian</strong>*, Vikas Garg, Björn Schuller, Tolga Birdal</p> 310 <p class="pub-venue"><em>International Conference on Machine Learning (<strong>ICML</strong>)</em>, 2026</p> 311 <p class="pub-links"><a href="https://arxiv.org/abs/2606.23517" title="arXiv" aria-label="arXiv"><svg class="ico"><use href="#i-arxiv"></use></svg></a><a href="https://github.com/mk2510/CollapsedEffectiveOperators" title="Code" aria-label="Code"><svg class="ico"><use href="#i-code"></use></svg></a><a href="https://collapsedeffectiveoperators.github.io" title="Website" aria-label="Website"><svg class="ico"><use href="#i-globe"></use></svg></a></p> 312 313 </div> 314</article> 315 316 317 318 319<article class="pub-card" id="non-rigid-3d-shape-correspondences-from-foundations-to-open-challenges-and-opportunities"> 320 <figure class="pub-thumb"> 321 <a href="/publications/#non-rigid-3d-shape-correspondences-from-foundations-to-open-challenges-and-opportunities" aria-label="Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities â see on publications page"> 322 <img src="/tn/images/nonrigid-survey.jpg" alt="Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities teaser" loading="lazy"> 323 <figcaption class="banner">Eurographics STAR</figcaption> 324 </a> 325 </figure> 326 <div class="pub-body"> 327 <h3 class="pub-title"><a href="/publications/#non-rigid-3d-shape-correspondences-from-foundations-to-open-challenges-and-opportunities">Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities</a></h3> 328 <p class="pub-authors">Aleksei Zhuravlev*, <strong>Lennart Bastian</strong>*, Dongliang Cao, Nafie El Amrani, Paul Roetzer, Viktoria Ehm, Riccardo Marin, Hiroki Nishizawa, Shigeo Morishima, Christian Theobalt, Nassir Navab, Daniel Cremers, Florian Bernard, Zorah Lähner, Vladislav Golyanik</p> 329 <p class="pub-venue"><em>Computer Graphics Forum (Eurographics <strong>STAR</strong>) 2026</em>, 2026</p> 330 <p class="pub-links"><a href="https://nonrigid-shape-correspondences.github.io/" title="Webpage" aria-label="Webpage"><svg class="ico"><use href="#i-globe"></use></svg></a><a href="https://arxiv.org/abs/2604.01274" title="arXiv" aria-label="arXiv"><svg class="ico"><use href="#i-arxiv"></use></svg></a><a href="https://doi.org/10.1111/cgf.70397" title="Paper" aria-label="Paper"><svg class="ico"><use href="#i-paper"></use></svg></a></p> 331 332 </div> 333</article> 334 335 336 337 338<article class="pub-card" id="copresheaf-topological-neural-networks-a-generalized-deep-learning-framework"> 339 <figure class="pub-thumb"> 340 <a href="/publications/#copresheaf-topological-neural-networks-a-generalized-deep-learning-framework" aria-label="Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework â see on publications page"> 341 <img src="/tn/images/copresheaf.png" alt="Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework teaser" loading="lazy"> 342 <figcaption class="banner">NeurIPS</figcaption> 343 </a> 344 </figure>
345 <div class="pub-body"> 346 <h3 class="pub-title"><a href="/publications/#copresheaf-topological-neural-networks-a-generalized-deep-learning-framework">Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework</a></h3> 347 <p class="pub-authors">Mustafa Hajij, <strong>Lennart Bastian</strong>, Sarah Osentoski, ..., Theodore Papamarkou, Tolga Birdal</p> 348 <p class="pub-venue"><em>Advances in Neural Information Processing Systems (<strong>NeurIPS</strong>)</em>, 2025</p> 349 <p class="pub-links"><a href="https://arxiv.org/abs/2505.21251" title="Paper" aria-label="Paper"><svg class="ico"><use href="#i-arxiv"></use></svg></a></p> 350 351 </div> 352</article> 353 354 355 356 357<article class="pub-card" id="forecasting-continuous-non-conservative-dynamical-systems-in-so-3"> 358 <figure class="pub-thumb"> 359 <a href="/publications/#forecasting-continuous-non-conservative-dynamical-systems-in-so-3" aria-label="Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) â see on publications page"> 360 <img src="/tn/images/forecasting_rot_dyn_teaser.jpg" alt="Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) teaser" loading="lazy"> 361 <figcaption class="banner oral">ICCV (Oral)</figcaption> 362 </a> 363 </figure> 364 <div class="pub-body"> 365 <h3 class="pub-title"><a href="/publications/#forecasting-continuous-non-conservative-dynamical-systems-in-so-3">Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)</a></h3> 366 <p class="pub-authors"><strong>Lennart Bastian</strong>*, Mohammad Rashed*, Nassir Navab, Tolga Birdal</p> 367 <p class="pub-venue"><em>IEEE International Conference on Computer Vision (<strong>ICCV</strong>) - <strong><span style='color: #d4582a;'>Oral (Top 2.6%) </span></strong></em>, 2025</p> 368 <p class="pub-links"><a href="https://arxiv.org/abs/2508.07775" title="Paper" aria-label="Paper"><svg class="ico"><use href="#i-arxiv"></use></svg></a><a href="https://github.com/bastianlb/forecasting-rotational-dynamics" title="Code" aria-label="Code"><svg class="ico"><use href="#i-code"></use></svg></a><a href="https://bastianlb.github.io/forecasting-rotational-dynamics/" title="Website" aria-label="Website"><svg class="ico"><use href="#i-globe"></use></svg></a></p> 369 370 </div> 371</article> 372 373 374 375 376<article class="pub-card" id="beyond-role-based-surgical-domain-modeling"> 377 <figure class="pub-thumb"> 378 <a href="/publications/#beyond-role-based-surgical-domain-modeling" aria-label="Beyond Role-Based Surgical Domain Modeling â see on publications page"> 379 <img src="/tn/images/beyond_role_teaser.jpg" alt="Beyond Role-Based Surgical Domain Modeling teaser" loading="lazy"> 380 <figcaption class="banner">MedIA</figcaption> 381 </a> 382 </figure> 383 <div class="pub-body"> 384 <h3 class="pub-title"><a href="/publications/#beyond-role-based-surgical-domain-modeling">Beyond Role-Based Surgical Domain Modeling</a></h3> 385 <p class="pub-authors">Tony Wang*, <strong>Lennart Bastian</strong>*, Tobias Czempiel, Christian Heiliger, Nassir Navab</p> 386 <p class="pub-venue"><em>Medical Image Analysis (<strong>MedIA</strong>) (Journal IF 10.7, <a href='https://scholar.google.com/citations?view_op=top_venues&hl=en&vq=eng_computervisionpatternrecognition'>rank</a> among CV venues)</em>, 2025</p> 387 <p class="pub-links"><a href="https://arxiv.org/abs/2503.13028" title="Paper" aria-label="Paper"><svg class="ico"><use href="#i-arxiv"></use></svg></a></p> 388 389 </div> 390</article> 391 392 393 </div> 394 <p class="see-all"><a href="/publications/">See all publications →</a></p> 395 </section> 396 397 </main> 398 399 <footer class="site-footer"> 400 <p>Design adapted from <a href="https://jonbarron.info">Jon Barron</a>.</p> 401</footer> 402 403</body> 404</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.