Text to Figure文生图poster

CinDM: Compositional Inverse Design Poster

A conference poster presenting CinDM, a method for compositional inverse design in dynamical systems. It details the motivation, approach using energy-based models and diffusion, and results on N-body tasks and 2D airfoil generation, demonstrating superior performance over baselines.

论文上下文

Paper title: Compositional Generative Inverse Design Abstract: A conference poster presenting CinDM, a method for compositional inverse design in dynamical systems. It details the motivation, approach using energy-based models and diffusion, and results on N-body tasks and 2D airfoil generation, demonstrating superior performance over baselines. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>Compositional Generative Inverse Design</title>  <meta content="width=device-width, initial-scale=1, shrink-to-fit=no" name="viewport"/> <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv_0.7.4.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/latexml_styles.css" rel="stylesheet" type="text/css"/> <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/html2canvas/1.3.3/html2canvas.min.js"></script> <script src="/static/browse/0.3.4/js/addons.js"></script> <script src="/static/browse/0.3.4/js/feedbackOverlay.js"></script> <base href="/html/2401.13171v1/"/></head> <body> <nav class="ltx_page_navbar"> <nav class="ltx_TOC"> <ol class="ltx_toclist"> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="#S1" title="1 Introduction ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1 </span>Introduction</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="#S2" title="2 Related Work ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2 </span>Related Work</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="#S3" title="3 Method ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3 </span>Method</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S3.SS1" title="3.1 Problem setup ‣ 3 Method ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.1 </span>Problem setup</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S3.SS2" title="3.2 Generative Inverse Design ‣ 3 Method ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.2 </span>Generative Inverse Design</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S3.SS3" title="3.3 Compositional Generative Inverse Design ‣ 3 Method ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.3 </span>Compositional Generative Inverse Design</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="#S4" title="4 Experiments ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4 </span>Experiments</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S4.SS1" title="4.1 Compositional inverse design in time ‣ 4 Experiments ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.1 </span>Compositional inverse design in time</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S4.SS2" title="4.2 Compositional inverse design generalizing to more objects ‣ 4 Experiments ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.2 </span>Compositional inverse design generalizing to more objects</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#S4.SS3" title="4.3 2D compositional design for multiple airfoils ‣ 4 Experiments ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.3 </span>2D compositional design for multiple airfoils</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="#S5" title="5 Conclusion ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">5 </span>Conclusion</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A1" title="Appendix A Additional details for compositional inverse design in time ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">A </span>Additional details for compositional inverse design in time</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A2" title="Appendix B Full results for compositional inverse design of the N-body task ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">B </span>Full results for compositional inverse design of the N-body task</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A3" title="Appendix C Additional baseline for time composition of the N-body task ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">C </span>Additional baseline for time composition of the N-body task</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"> <a class="ltx_ref" href="#A4" title="Appendix D Additional details for compositional inverse design of 2D airfoils ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">D </span>Additional details for compositional inverse design of 2D airfoils</span></a> <ol class="ltx_toclist ltx_toclist_appendix"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#A4.SS1" title="D.1 Details for the main experiment ‣ Appendix D Additional details for compositional inverse design of 2D airfoils ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">D.1 </span>Details for the main experiment</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#A4.SS2" title="D.2 Surrogate Model for Force Prediction ‣ Appendix D Additional details for compositional inverse design of 2D airfoils ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">D.2 </span>Surrogate Model for Force Prediction</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A5" title="Appendix E Visualization of N-body inverse design. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">E </span>Visualization of N-body inverse design.</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A6" title="Appendix F Visualization results of 2D inverse design by our CinDM ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">F </span>Visualization results of 2D inverse design by our CinDM</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A7" title="Appendix G some visualization results of 2d inverse design baseline. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">G </span>some visualization results of 2d inverse design baseline.</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A8" title="Appendix H Comparison to additional works ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">H </span>Comparison to additional works</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"> <a class="ltx_ref" href="#A9" title="Appendix I performance sensitivity to hyperparameters, initialization and sampling steps. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">I </span>performance sensitivity to hyperparameters, initialization and sampling steps.</span></a> <ol class="ltx_toclist ltx_toclist_appendix"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#A9.SS1" title="I.1 Influence of the hyperparameter 𝜆 ‣ Appendix I performance sensitivity to hyperparameters, initialization and sampling steps. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">I.1 </span>Influence of the hyperparameter <math alttext="\lambda" class="ltx_Math" display="inline"><semantics><mi>λ</mi><annotation-xml encoding="MathML-Content"><ci>𝜆</ci></annotation-xml><annotation encoding="application/x-tex">\lambda</annotation><annotation encoding="application/x-llamapun">italic_λ</annotation></semantics></math></span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#A9.SS2" title="I.2 Influence of initialization ‣ Appendix I performance sensitivity to hyperparameters, initialization and sampling steps. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">I.2 </span>Influence of initialization</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="#A9.SS3" title="I.3 Influence of the number of sampling steps in inference ‣ Appendix I performance sensitivity to hyperparameters, initialization and sampling steps. ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">I.3 </span>Influence of the number of sampling steps in inference</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="#A10" title="Appendix J Broader impacts and limitations ‣ Compositional Generative Inverse Design"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">J </span>Broader impacts and limitations</span></a></li> </ol></nav> </nav> <div class="ltx_page_main"> <div class="ltx_page_content"><div class="section" id="target-section"><div id="license-tr">License: CC BY 4.0</div><div id="watermark-tr">arXiv:2401.13171v1 [cs.LG] 24 Jan 2024</div></div> <article class="ltx_document ltx_authors_1line"> <h1 class="ltx_title ltx_title_document">Compositional Generative Inverse Design</h1> <div class="ltx_authors"> <span class="ltx_creator ltx_role_author"> <span class="ltx_personname"> <span class="ltx_text ltx_font_bold" id="id3.3.2">Tailin Wu<math alttext="{}^{1}" class="ltx_Math" display="inline" id="id1.1.1.m1.1"><semantics id="id1.1.1.m1.1a"><msup id="id1.1.1.m1.1.1" xref="id1.1.1.m1.1.1.cmml"><mi id="id1.1.1.m1.1.1a" xref="id1.1.1.m1.1.1.cmml"></mi><mn id="id1.1.1.m1.1.1.1" mathvariant="normal" xr

完整 Prompt

Above I've shared:
(1) the full paper text,
(2) all paper figures labeled by figure number,
(3) the caption for the central poster figure I'm building.

TASK: This is a CONFERENCE POSTER. **NOT** an academic-paper figure.
Style requirements:

  - Multi-section layout with a clear poster structure: large title banner
    at the top with the paper title + author/affiliation strip, then 3-6
    distinct content panels arranged in columns or a grid.
  - Large legible fonts (text must be readable at 2 m viewing distance) —
    headings ≥ 60 pt visual size in the final image.
  - Use colour blocks / panel backgrounds to delineate sections (this is
    what makes it a poster, not a single-figure diagram).
  - Aspect ratio: portrait or landscape rectangle, NOT square.

If your output looks like a standard academic-paper figure (single panel,
no title banner, dense small text, no colour blocks), you've failed the
task. Render the COMPLETE poster, not just the central figure.

Just give me the final poster image.

立即试用此 Prompt

在生成器中自动预填此 prompt。

试用此 Prompt

CinDM: Compositional Inverse Design Poster

论文上下文

完整 Prompt

立即试用此 Prompt

相关 Prompt

PINN Framework Pipeline for Microscopy Data

DP-FTRL Privacy Amplification Analysis — Conference Poster

NC-TTT: Noise-Contrastive Test-Time Training Poster