Add APS talk description and bios

Author: shuds13

_data/speakers.yml

@@ -299,9 +299,12 @@
   link: https://www.anl.gov/profile/ming-du
   photo: ming_du.jpeg
   bio: >
-    Ming Du is an Assistant Computational Scientist at Argonne National Laboratory where
-    he works on computer vision and generative AI for imaging and agentic AI for
-    automation.
+    Ming Du is a computational scientist in the Computational Science and AI Group (CAI) of
+    the Advanced Photon Source. He obtained his PhD degree in Materials Science and Engineering
+    from Northwestern University in 2019, and was a postdoc at the APS from 2019 to 2021. He
+    worked as an algorithm engineer in KLA Corporation between 2021 and 2023. Ming’s primary
+    research areas include traditional and AI-based methods for microscopy imaging and automated
+    calibration and measurement at synchrotron beamlines.
 
 - id: xiangyu_yin
   name: Xiangyu Yin
@@ -314,9 +317,6 @@
   link: https://www.anl.gov/profile/xiangyu-yin
   photo: xiangyu_yin.jpg
   bio: >
-    Xiangyu Yin is an Assistant Computational Scientist at Argonne National Laboratory,
-    where he works at the intersection of computational imaging, artificial intelligence,
-    and scientific automation. He joined Argonne in 2023 as a Postdoctoral Appointee.
-    Before that, he studied computational materials and process systems engineering at
-    Carnegie Mellon University. He is interested in developing intelligent systems to
-    accelerate, automate, and advance scientific discovery.
+    Xiangyu Yin is an Assistant Computational Scientist at APS working on computational algorithms,
+    artificial intelligence, and scientific automation. He joined Argonne in 2023 as a Postdoctoral
+    Appointee. Before that, he studied computational materials at Carnegie Mellon University.

_talks/2026_04_15.html

@@ -1,11 +1,11 @@
 ---
 layout: talk
 title: "The Agentic Revolution: Lightning Sessions on Agentic Workflows"
-authors: Woong Shin, Jan Jensen, Du Ming, Xiangyu Yin, Stephen Hudson
+authors: Woong Shin, Jan Jensen, Du Ming, Xiangyu Yin
 event_date: April 15, 2026
 times: 11:00am PST / 2:00pm EST / 20:00 CEST
 talk_number: 13
-speakers: [woong_shin, ming_du, xiangyu_yin, jan_janssen]
+speakers: [woong_shin, jan_janssen,ming_du, xiangyu_yin]
 given: false
 image: /images/talks/agentic_banner.jpg
 <!-- presentation: /files/talks/20260415-AgenticRevolution.pdf -->
@@ -31,15 +31,29 @@
 accelerate discovery by factors of 10 to 100, transforming exploratory science
 into a continuous, machine-augmented process.
 
+<br /><br />
+
+<strong>Title: TBD</strong><br />
+<em>Jan Jensen (Max Planck Institute for Sustainable Materials)</em>
+
+
 <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 />
 
-<strong>Title: TBD</strong><br />
-<em>Jan Jensen (Max Planck Institute for Sustainable Materials)</em>
+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 />
-