diff --git a/_data/pubs.yml b/_data/pubs.yml
index 7855ad7..0bb1420 100644
--- a/_data/pubs.yml
+++ b/_data/pubs.yml
@@ -1,3 +1,14 @@
+- title: "From Pixels to Torques with Linear Feedback"
+  authors: [Jeong Hun Lee, Sam Schoedel, Aditya Bhardwaj, Zachary Manchester]
+  projects: [linear_pixels_to_torques]
+  publisher: International Workshop on the Algorithmic Foundations of Robotics
+  abbrv: WAFR
+  pub-type: conference
+  venue: Chicago, IL
+  date: 2024-10-07
+  pdf: linear_pixels_to_torques.pdf
+  status: In Review
+
 - title: "Contingency-Aware Station-Keeping Control of Halo Orbits"
   authors: [fausto, zac, Martin Lo, Ricardo Restrepo]
   publisher: Conference on Decision and Control
diff --git a/_projects/linear_pixels_to_torques.md b/_projects/linear_pixels_to_torques.md
new file mode 100644
index 0000000..ce01263
--- /dev/null
+++ b/_projects/linear_pixels_to_torques.md
@@ -0,0 +1,20 @@
+---
+title: Pixels to Torques with Linear Feedback
+
+description: |
+  Data-driven, linear output-feedback policies can effectively control a robotic system using vision.
+
+people:
+  - jj
+  - sam
+  - zac 
+
+layout: project
+image: "/img/linear_pixels_to_torques/linear_pixels_to_torques.gif"
+last-updated: 2024-06-26
+---
+
+We demonstrate the effectiveness of simple observer-based linear feedback policies for "pixels-to-torques" control of robotic systems using only a robot-facing camera. Specifically, we show that the matrices of an image-based Luenberger observer (linear state estimator) for a "student" output-feedback policy can be learned from demonstration data provided by a "teacher" state-feedback policy via simple linear-least-squares regression. The resulting linear output-feedback controller maps directly from high-dimensional raw images to torques while being amenable to the rich set of analytical tools from linear systems theory, alowing us to enforce closed-loop stability constraints in the learning problem. We also investigate a nonlinear extension of the method via the Koopman embedding. Finally, we demonstrate the surprising effectiveness of linear pixels-to-torques policies on a cartpole system, both in simulation and on real-world hardware. The policy successfully executes both stabilizing and swing-up trajectory tracking tasks using only camera feedback while subject to model mismatch, process and sensor noise, perturbations, and occlusions.
+
+# Resources
+* Code coming soon!
\ No newline at end of file
diff --git a/img/linear_pixels_to_torques/linear_pixels_to_torques.gif b/img/linear_pixels_to_torques/linear_pixels_to_torques.gif
new file mode 100644
index 0000000..f488df9
Binary files /dev/null and b/img/linear_pixels_to_torques/linear_pixels_to_torques.gif differ
diff --git a/papers/linear_pixels_to_torques.pdf b/papers/linear_pixels_to_torques.pdf
new file mode 100644
index 0000000..519a39f
Binary files /dev/null and b/papers/linear_pixels_to_torques.pdf differ