What does it take to bridge the gap between today’s agentic systems and a human collaborator? Recent LLMs are increasingly strong at solving verifiable problems with clear feedback, but many tasks can’t be fully specified upfront. Instead, humans achieve task alignment in shared context through dialogue. Of the many communicative strategies people use, I’m especially interested in (i) iterative repair, (ii) convention formation, and (iii) building mutual mental models. I build interactive systems that embody these behaviors, so they are both natural to instruct and reliable in execution.
I started as an asst prof at NTU in June 2025. My lab broadly work on code generation, instruction following agents, and collaborative design. We publish mainly in AI/ML conferences, with a few extensions in Cogsci, Graphics, and HCI. Previously, I was a principal research scientist at Autodesk AI Lab, and I received my PhD under Armando Solar-Lezama and Leslie Kaelbling at MIT.
Representative Works
- Program Synthesis with Pragmatic Communication (NeuRIPS 2020)
Yewen Pu, Kevin Ellis, Marta Kryven, Josh Tenenbaum, Armando Solar-Lezama - Communicating Natural Programs to Humans and Machines (NeuRIPS 2022)
Samuel Acquaviva *, Yewen Pu *, Marta Kryven, Theodoros Sechopoulos, Catherine Wong, Gabrielle E Ecanow, Maxwell Nye, Michael Henry Tessler, Joshua B. Tenenbaum - mrCAD: Multimodal Refinement of Computer-aided Designs (arXiv 2025)
William P. McCarthy, Saujas Vaduguru, Karl D. D. Willis, Justin Matejka, Judith E. Fan, Daniel Fried, and Yewen Pu
Additional Information
Shoot me a twitter message or email any time if you want to chat !