Update Capture placeholder site

Author: luis-marques

content/_index.md

@@ -1,28 +1,27 @@
 +++
-title = "Local Conformal Calibration of Dynamics Uncertainty from Semantic Images"
+title = "Particle-based Conformal Prediction for Contact-Aware Uncertainty Calibration in Stratified Configuration Spaces"
 [extra]
-display_title = "Local Conformal Calibration of Dynamics Uncertainty from Semantic Images "
+display_title = "Particle-based Conformal Prediction for Contact-Aware Uncertainty Calibration in Stratified Configuration Spaces"
 authors = [
-    {name = "Luís Marques", url = "https://marquesluis.com/"},
+    {name = "Luís Marques", url = "https://marquesluis.com/", contribution = true},
+    {name = "Kristian Popov", url = "https://www.linkedin.com/in/kristian-c-popov/", contribution = true},
     {name = "Dmitry Berenson", url = "https://berenson.robotics.umich.edu/"}
 ]
-venue = {name = "17th International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2026", url = "https://algorithmic-robotics.org/"}
+contribution = "denotes equal contribution."
+venue = {name = "Under Review", url = ""}
 buttons = [
     # {name = "ArXiv", url = ""},
     # {name = "PDF", url = ""},
     # {name = "Code", url = "https://github.com/UM-ARM-Lab/ocular_code"}
 ]
 katex = true
-large_card = true
-favicon = true
+large_card = false
+favicon = false
 +++
 
 <!-- <div class="abstract-with-figure"> -->
 
 <!-- <div class="text-column"> -->
-
-We introduce **O**bservation-aware **C**onformal **U**ncertainty **L**ocal-C**a**lib**r**ation (**OCULAR**), a conformal prediction-based algorithm that uses perceptual information to provide uncertainty quantification guarantees for unseen test-time environments. While previous conformal approaches lack the ability to discriminate between state-action space regions leading to higher or lower model mismatch, and require environment-specific data, our method uses data collected from visually similar environments to provably calibrate a given linear Gaussian dynamics model of arbitrary fidelity. The prediction regions generated from **OCULAR** are guaranteed to contain the future system states with, at least, a user-set likelihood, despite both aleatoric and epistemic uncertainty—i.e., uncertainty arising from both stochastic disturbances and lack of data. Our guarantees are non-asymptotic and distribution-free, not requiring strong assumptions about the unknown real system dynamics. Our calibration procedure enables distinguishing between observation-velocity-action inputs leading to higher and lower next-state-uncertainty, which is helpful for probabilistically-safe planning. We numerically validate our algorithm on a double-integrator system subject to random perturbations and significant model mismatch, using both a simplified sensor and a more realistic simulated camera. Our approach appropriately quantifies uncertainty both when in-distribution and out-of-distribution, being comparatively volume-efficient to baselines requiring environment-specific data. 
-
 <!-- </div> -->
 
-More comming soon! Stay tuned.
+More comming soon! Stay tuned.

content/card.jpg

@@ -15,12 +15,12 @@ <h2>
                             <a href="{{ author.url | default(value = this.path ~ '#') | safe }}" target="_blank">
                                 {{- author.name -}}
                             </a>
+                            {%- if author.contribution -%}
+                                <sup><small>†</small></sup>
+                            {%- endif -%}
                             {%- if not loop.last -%}
                                 &comma;
                             {%- endif -%}
-                            {%- if author.contribution -%}
-                                <sup><small>*</small></sup>
-                            {%- endif -%}
                             {%- if not loop.last -%}
                                 &#32;
                             {% endif %}
@@ -29,7 +29,7 @@ <h2>
                 </h2>
                 {% if this.extra.contribution %}
                     <p>
-                        <sup><small>*</small></sup>{{ this.extra.contribution }}
+                        <sup><small>†</small></sup>{{ this.extra.contribution }}
                     </p>
                 {% endif %}
                 <div>

static/apple-touch-icon.png

@@ -1,7 +1,8 @@
 {% macro seo(page) %}
 {% set url = get_url(path = page.path, trailing_slash = true) %}
-{% set card_file = page.extra.card | default(value = 'card.jpg') %}
-{% set card = get_url(path = page.path ~ card_file) %}
+{% if page.extra.card %}
+    {% set card = get_url(path = page.path ~ page.extra.card) %}
+{% endif %}
 <meta property="og:title" content="{{ page.title }}">
 <meta name="author" content="{{ page.extra.authors | map(attribute = 'name') | join(sep = ', ') }}">
 {% if page.description %}
@@ -10,14 +11,17 @@
 {% endif %}
 <link rel="canonical" href="{{ url | safe }}">
 <meta property="og:url" content="{{ url | safe }}">
-<meta property="og:image" content="{{ card | safe }}">
-<meta property="og:image:type" content="image/png">
+{% if page.extra.card %}
+    <meta property="og:image" content="{{ card | safe }}">
+{% endif %}
 <meta property="og:type" content="article">
+{% if page.extra.card %}
+    <meta name="twitter:card" content="{% if page.extra.large_card %}summary_large_image{% else %}summary{% endif %}">
+    <meta property="twitter:image" content="{{ card | safe }}">
+{% endif %}
 {% if page.extra.venue.date or page.date %}
     <meta property="article:published_time" content="{{ page.extra.venue.date | default(value = page.date) | date(format='%+') }}">
 {% endif %}
-<meta name="twitter:card" content="{% if page.extra.large_card %}summary_large_image{% else %}summary{% endif %}">
-<meta property="twitter:image" content="{{ card | safe }}">
 <meta property="twitter:title" content="{{ page.title }}">
-<script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","author":[{% for author in page.extra.authors %}{"@type":"Person","name":"{{ author.name }}"}{% if not loop.last %},{% endif %}{% endfor %}],{% if page.extra.venue.date or page.date %}"dateModified":"{{ page.updated | default(value = page.extra.venue.date) | default(value = page.date) | date(format='%+') }}","datePublished":"{{ page.extra.venue.date | default(value = page.date) | date(format='%+') }}",{% endif %}{% if page.description %}"description":"{{ page.description }}",{% endif %}"headline":"{{ page.title }}","image":"{{ card | safe }}","mainEntityOfPage":{"@type":"WebPage","@id":"{{ url | safe }}"},"url":"{{ url | safe }}"}</script>
-{% endmacro %}
+<script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","author":[{% for author in page.extra.authors %}{"@type":"Person","name":"{{ author.name }}"}{% if not loop.last %},{% endif %}{% endfor %}],{% if page.extra.venue.date or page.date %}"dateModified":"{{ page.updated | default(value = page.extra.venue.date) | default(value = page.date) | date(format='%+') }}","datePublished":"{{ page.extra.venue.date | default(value = page.date) | date(format='%+') }}",{% endif %}{% if page.description %}"description":"{{ page.description }}",{% endif %}"headline":"{{ page.title }}",{% if page.extra.card %}"image":"{{ card | safe }}",{% endif %}"mainEntityOfPage":{"@type":"WebPage","@id":"{{ url | safe }}"},"url":"{{ url | safe }}"}</script>
+{% endmacro %}