Bio: Ken Goldberg is William S. Floyd Distinguished Professor of Engineering at UC Berkeley, President of the international Robot Learning Foundation, member of the US National Academy of Engineering, IEEE Fellow, co-founder and Editor-in-Chief emeritus of the IEEE Transactions on Automation Science and Engineering (T-ASE), Co-Founder of Jacobi Robotics, and Co-Founder/Chief Scientist of Ambi Robotics.  Ken leads research in robotics and automation: grasping, manipulation, and learning for applications in warehouses, homes, agriculture, and robot-assisted surgery.  He is Distinguished Professor of IEOR, EECS, and Art Practice.  Ken has published 10 US patents, over 450 refereed papers, and has presented over 600 invited lectures to academic and corporate audiences. http://goldberg.berkeley.edu

Talk Title: "Blox-Net: Generative Design-for-Robot-Assembly using VLM Supervision, Physics Simulation, and A Robot with Reset"

Abstract — Generative AI systems have shown impressive capabilities in creating text, code, and images. Inspired by the rich history of research in industrial “Design for Assembly”, we introduce a novel problem: Generative Design-for-Robot- Assembly (GDfRA). The task is to generate an assembly based on a natural language prompt (e.g., “giraffe”) and an image of available physical components, such as 3D-printed blocks.  The output is an assembly, a spatial arrangement of these components, and instructions for a robot to build this assembly.  The output must 1) resemble the requested object and 2) be reliably assembled by a 6 DoF robot arm with a suction gripper.  We then present Blox-Net, a GDfRA system that combines generative vision language models with well-established methods in computer vision, simulation, perturbation analysis, motion planning, and self-supervised physical robot experimentation to solve a class of GDfRA problems with minimal human supervision. Blox-Net achieved a Top-1 accuracy of 63.5% in the “recognizability” of its designed assemblies (eg, resembling giraffe as judged by a VLM). These designs, after automated pertubation redesign, were reliably assembled by a robot, achieving near-perfect success across 10 consecutive assembly iterations with human intervention only during reset prior to assembly. Surprisingly, this entire design process from textual word (“giraffe”) to reliable physical assembly is performed with zero human intervention.

Website: https://goldberg.berkeley.edu/

Bio: Manling Li is an Assistant Professor at Northwestern University and an Amazon Scholar. She was a postdoc at Stanford University, and obtained the PhD in CS at University of Illinois Urbana-Champaign in 2023. She works on Reasoning, Planning and Compositionality, in the intersection of Language, Vision, and Robotics. Her work has been recognized as ACL 2025 Dissertation Award Honorable Mention, Outstanding Paper Award at ACL’24, Best Demo Paper Award at NAACL’21 and ACL’20, MIT Tech Review 35 Innovators Under 35, etc. She led the tutorials/workshops/challenges of Foundation Models meet Embodied Agents. Additional information is available at limanling.github.io/.

Talk Title: "Foundation Models for Embodied Reasoning"

Website: https://limanling.github.io/

Bio: Yiqing Xu is a postdoctoral researcher at Stanford University, working with Professor Jiajun Wu. She received her PhD in Computer Science from the National University of Singapore, advised by Professor David Hsu. Her research focuses on translating human intent into representations and objectives that robots can reason about and optimize. Her work spans language- and sketch-conditioned object arrangement, compositional generative models, stable structure generation for robotic manipulation and assembly. Her recent projects include Set It Up, which generates functional object arrangements from natural-language specifications, and Stack It Up, which constructs stable 3D structures from hand-drawn sketches. Her broader research interests include neuro-symbolic robot learning, task and motion planning, and compositional representations for generalizable robotic behavior.

Talk Title: "From Human Intent to Stable Structures: Compositional Generative Models for Robotic Assembly"

Website: https://eeching.github.io/