Add slides from agentic session and July talk

_config.yml

@@ -1,6 +1,7 @@
 # Site settings
 title: Workflows Community Initiative
 subtitle: Bringing the Scientific Workflows Community Together
+url: https://workflows.community
 
 markdown: kramdown
 enable-mathjax: yes

_layouts/talk.html

@@ -26,7 +26,13 @@ <h1>{{ page.title }}</h1>
                         <a href="https://docs.google.com/forms/d/1XTJFRJ5Ivu2-Z-i9dnq2umv-OuE2UlVreea_dLawd2c"
                             target="_blank" class="btn btn-primary talk-cta-btn">Register</a>
                         {% endunless %}
-                        {% if page.presentation %}
+                        {% if page.presentations %}
+                        {% for p in page.presentations %}
+                        <a href="{{ p.file }}" target="_blank" class="btn btn-outer">
+                            <i class="fa fa-file"></i> Presentation{% if p.speaker %} &mdash; {{ p.speaker }}{% endif %}
+                        </a>
+                        {% endfor %}
+                        {% elsif page.presentation %}
                         <a href="{{ page.presentation }}" target="_blank" class="btn btn-outer">
                             <i class="fa fa-file"></i> Presentation
                         </a>
@@ -61,7 +67,19 @@ <h2>Overview</h2>
                     <div class="talk-content">{{ content }}</div>
                 </section>
 
-                {% if page.video %}
+                {% if page.videos %}
+                <section class="talk-section">
+                    <h3>Watch the recordings</h3>
+                    {% for v in page.videos %}
+                    {% if v.speaker %}<h4>{{ v.speaker }}</h4>{% endif %}
+                    <div class="talk-video">
+                        <iframe src="{{ v.url }}" title="YouTube video player" frameborder="0"
+                            allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+                            referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+                    </div>
+                    {% endfor %}
+                </section>
+                {% elsif page.video %}
                 <section class="talk-section">
                     <h3>Watch the recording</h3>
                     <div class="talk-video">

_talks/2026_05_20.html

@@ -1,15 +1,23 @@
 ---
 layout: talk
-title: "The Agentic Revolution: Lightning Sessions on Agentic Workflows"
-authors: Woong Shin, Jan Janssen, Du Ming, Xiangyu Yin
+title: "The Agentic Revolution: Double Bill on Agentic Workflows"
+authors: Woong Shin, Jan Janssen
 event_date: May 20, 2026
 times: 11:00am PST / 2:00pm EST / 20:00 CEST
 talk_number: 13
-speakers: [woong_shin, jan_janssen,ming_du, xiangyu_yin]
-given: false
+speakers: [woong_shin, jan_janssen]
+given: true
 image: /images/talks/agentic_banner.jpg
-<!-- presentation: /files/talks/20260415-AgenticRevolution.pdf -->
-<!-- video: https://www.youtube.com/embed/TPAz4bbmW_0?si=JO3ARdoIYRji-TKl -->
+presentations:
+  - speaker: Woong Shin
+    file: /files/talks/20260520-Woong-Agentic.pdf
+  - speaker: Jan Janssen
+    file: /files/talks/20260520-Jannsen-llm-agents.pdf
+# videos:
+#   - speaker: Woong Shin
+#     url: https://www.youtube.com/embed/REPLACE
+#   - speaker: Jan Janssen
+#     url: https://www.youtube.com/embed/REPLACE
 ---
 
 <strong>The (R)evolution of Scientific Workflows in the Agentic AI era: Towards Autonomous Science</strong><br />
@@ -54,22 +62,3 @@
 synergy between LLMs and scientific workflows in materials science.
 
 <br /><br />
-
-<strong>Agentic AI for experiments and data analyses at the APS</strong><br />
-<em>Du Ming, Xiangyu Yin (Argone National Laboratory)</em>
-
-<br /><br />
-
-We will introduce the current efforts of using vision language model (VLM) agents
-for automated and low-barrier beamline operations and data processing algorithm
-research. We first present Experiment Automation Agents (EAA), an agent capable
-of controlling beamline instruments and making decisions based on image semantics,
-with a few cases demonstrating how it automates and democratizes experimental
-operations at APS beamlines. We will then introduce works on agentic data
-processing, which includes PEAR, a domain-expert system that tunes
-ptychographic reconstruction hyperparameters using reconstructed image as
-feedback, and Pty-Chi-Evolve, an auto-research agent that autonomously searches
-for regularization operators during iterative reconstructions to enhance result
-quality.
-
-<br /><br />

_talks/2026_07_23.html

@@ -0,0 +1,27 @@
+---
+layout: talk
+title: "Agentic AI for experiments and data analyses at the APS"
+authors: Du Ming, Xiangyu Yin (Argonne National Laboratory)
+event_date: July 23, 2026
+times: 11:00am PST / 2:00pm EST / 20:00 CEST
+talk_number: 14
+speakers: [ming_du, xiangyu_yin]
+given: false
+<!-- image: /images/talks/REPLACE.jpg -->
+<!-- presentation: /files/talks/REPLACE.pdf -->
+<!-- video: https://www.youtube.com/embed/REPLACE -->
+---
+
+We will introduce the current efforts of using vision language model (VLM) agents
+for automated and low-barrier beamline operations and data processing algorithm
+research. We first present Experiment Automation Agents (EAA), an agent capable
+of controlling beamline instruments and making decisions based on image semantics,
+with a few cases demonstrating how it automates and democratizes experimental
+operations at APS beamlines. We will then introduce works on agentic data
+processing, which includes PEAR, a domain-expert system that tunes
+ptychographic reconstruction hyperparameters using reconstructed image as
+feedback, and Pty-Chi-Evolve, an auto-research agent that autonomously searches
+for regularization operators during iterative reconstructions to enhance result
+quality.
+
+<br /><br />