->ac

Author: bamos

cv.yaml

@@ -993,10 +993,31 @@ advising:
     url: https://phillipkwang.com/
 
 service:
+  main:
+    - details: NeurIPS Learning Meets Combinatorial Optimization Workshop Organizer
+      year: 2020
+      url: https://sites.google.com/view/lmca2020/home
+    - details: CVPR Deep Declarative Networks Workshop Organizer
+      url: https://anucvml.github.io/ddn-cvprw2020/
+      year: 2020
+    - details: ECCV Deep Declarative Networks Tutorial Organizer
+      url: https://anucvml.github.io/ddn-eccvt2020/
+      year: 2020
+    - details: CMU CSD MS Admissions
+      year: 2014--2015
+
+  area_chair:
+    - "Artificial Intelligence and Statistics (AISTATS)"
+    - "Association for the Advancement of Artificial Intelligence (AAAI)"
+    - "International Conference on Learning Representations (ICLR)"
+    - "International Conference on Machine Learning (ICML)"
+    - "Neural Information Processing Systems (NeurIPS)"
+    - "Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks"
+
   reviewing:
-    - "AAAI Conference on Artificial Intelligence"
     - "American Controls Conference (ACC)"
     - "Artificial Intelligence and Statistics (AISTATS)"
+    - "Association for the Advancement of Artificial Intelligence (AAAI)"
     - "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"
     - "IEEE Conference on Decision and Control (CDC)"
     - "IEEE Control Systems Letters (L-CSS)"
@@ -1020,41 +1041,6 @@ service:
     - "Transactions on Machine Learning Research (TMLR)"
     - "Uncertainty in Artificial Intelligence (UAI)"
 
-  main:
-    - details: ICML Area Chair
-      year: 2026
-    - details: AAAI Senior Program Committee
-      year: 2026
-    - details: AISTATS Area Chair
-      year: 2026
-    - details: NeurIPS Area Chair
-      year: 2025
-    - details: AAAI Senior Program Committee
-      year: 2025
-    - details: NeurIPS Area Chair
-      year: 2024
-    - details: NeurIPS Datasets and Benchmarks Area Chair
-      year: 2024
-    - details: AAAI Senior Program Committee
-      year: 2024
-    - details: NeurIPS Area Chair
-      year: 2023
-    - details: NeurIPS Datasets and Benchmarks Area Chair
-      year: 2023
-    - details: AAAI Senior Program Committee
-      year: 2023
-    - details: NeurIPS Learning Meets Combinatorial Optimization Workshop Organizer
-      year: 2020
-      url: https://sites.google.com/view/lmca2020/home
-    - details: CVPR Deep Declarative Networks Workshop Organizer
-      url: https://anucvml.github.io/ddn-cvprw2020/
-      year: 2020
-    - details: ECCV Deep Declarative Networks Tutorial Organizer
-      url: https://anucvml.github.io/ddn-eccvt2020/
-      year: 2020
-    - details: CMU CSD MS Admissions
-      year: 2014--2015
-
 skills:
   - title: Programming
     details: C, C++, Fortran, Haskell, Java,

publications/all.bib

@@ -256,6 +256,7 @@ @misc{zhao2025fullyfirstorderlayerdifferentiable
   author={Zihao Zhao and Kai-Chia Mo and Shing-Hei Ho and Brandon Amos and Kai Wang},
   year={2025},
   url={https://arxiv.org/abs/2512.02494},
+  codeurl={https://github.com/guaguakai/FFOLayer},
   abstract={Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is both compute- and memory-intensive. To address this challenge, we propose a novel algorithm that computes the gradient using only first-order information. The key insight is to rewrite the differentiable optimization as a bilevel optimization problem and leverage recent advances in bilevel methods. Specifically, we introduce an active-set Lagrangian hypergradient oracle that avoids Hessian evaluations and provides finite-time, non-asymptotic approximation guarantees. We show that an approximate hypergradient can be computed using only first-order information in about constant time (up to logarithmic factors), leading to an overall complexity on the order of δ⁻¹ε⁻³ for constrained bilevel optimization, which matches the best known rate for non-smooth non-convex optimization. Furthermore, we release an open-source Python library that can be easily adapted from existing solvers.},
   _venue={arXiv}
 }

templates/latex/sections/service.tex

@@ -10,6 +10,11 @@
     \hfill << item.year >> \\
 ~< endfor >~
 
+\subsection{Area Chair}
+~< for item in items.area_chair >~
+<< item >> \\
+~< endfor >~
+
 \subsection{Reviewing}
 ~< for item in items.reviewing >~
 << item >> \\

templates/markdown/sections/service.md

@@ -19,6 +19,15 @@
 {% endfor %}
 </table>
 
+### Area Chair
+<table class="table table-hover">
+{% for item in items.area_chair %}
+<tr>
+  <td style='padding-right:0;'>{{ item }}</td>
+</tr>
+{% endfor %}
+</table>
+
 ### Reviewing
 <table class="table table-hover">
 {% for item in items.reviewing %}