Scholar
Howard Chen
Google Scholar ID: wsNa_W4AAAAJ
Princeton University
Citations & Impact
Citations
1,852
H-index
14
i10-index
16
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- For up-to-date publications, please see his Google Scholar page.
Research Experience
- Worked as an ML researcher for three years at ASAPP Research and research assistant at Cornell NYC Tech. Will be interning at Meta AI over the summer working with Asli Celikyilmaz and Jason Weston.
Education
- Currently a final year PhD student in the Princeton NLP Group and the Princeton Language + Intelligence center, co-advised by Professor Danqi Chen and Professor Karthik Narasimhan. Previously, he received his M.Eng. from Cornell University and B.S. from National Taiwan University.
Background
- Research interests include building agents that can operate reliably over long interactive horizons and continually evolve. Approaches it through the lens of memory in both its in-context and parametric forms — designing challenging evaluations to stress test long-horizon capabilities (WebShop), developing algorithms that let models self-organize and manage its own in-context memory (MemWalker), examining reliability under context accumulation (Tracking Belief Shift), and understanding how models can adapt gracefully with minimal forgetting (Continual Memorization, RL Mitigates Forgetting). He is also broadly interested in topics such as interpretability and safety from the memory perspective.
