You have found Clemens Rosenbaum's web site. I am a PhD candidate at the College of Information and Computer Sciences at the University of Massachusetts Amherst, where I am advised by Sridhar Mahadevan.
My interests span several machine learning disciplines, in particular deep learning and reinforcement learning.

About me and my interests

I am interested in a subfield of artificial intelligence called machine learning, the automated discovery of models to solve particular problems. My research focuses on compositional computation, i.e., trying to learn modular and composable models that may change for different tasks, contexts or even samples. I mostly employ deep learning and reinforcement learning techniques.

A very short CV:


A more detailed discription of what I do:

My main research interest is developing algorithms that allow a machine learning model to change its structure if a different structure is more fitting to the problem at hand. In particular, I am interested in modularizing models, i.e., in learning specialized sub-models that a meta-learning algorithm can compose to solve complex problems. I believe that this line of research can yield several desireable results. One is smaller models that require less computation; my particular interest, however, revolves around the question if modularized models allow better generalization by composing less complex transformations to fit new, previously unseen, tasks. This, I believe, is a core part of our human ability to learn from so few examples - we solve new tasks by mapping each required step individually to already acquired ones.

Projects and Papers


  • I maintain the "Routing Networks" PyTorch package Github
  • I co-maintain the Stanford Corpus of Implicatives Project Page


  • Clemens Rosenbaum, Ignacio Cases, Matthew Riemer, Atticus Geiger, Lauri Karttunen, Joshua D. Greene, Dan Jurafsky, Christopher Potts "Dispatched Routing Networks" (Stanford Tech Report 2019). SCI Project Page
  • Clemens Rosenbaum, Ignacio Cases, Matthew Riemer and Tim Klinger "Routing Networks and the Challenges of Modular and Compositional Computation" (arxiv 2019). arxiv
  • Ignacio Cases, Clemens Rosenbaum, Matthew Riemer, Atticus Geiger, Tim Klinger, Alex Tamkin, Olivia Li, Sandhini Agarwal, Joshua D. Greene, Dan Jurafsky, Christopher Potts and Lauri Karttunen "Recursive Routing Networks: Learning to Compose Modules for Language Understanding" (NAACL 2019). ACL Web
  • Clemens Rosenbaum, Tim Klinger, and Matthew Riemer "Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning" (ICLR 2018). openreview
  • Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo, Miao Liu, Gerald Tesauro, and Murray Campbell, "Eigenoption Discovery through the Deep Successor Representation" (ICLR 2018). openreview
  • Clemens Rosenbaum, Tian Gao, and Tim Klinger, "e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations" (WHI@ICML 2017). arxiv
  • Xiaoxiao Guo, Tim Klinger, Clemens Rosenbaum, Joseph P. Bigus, Murray Campbell, B. Kawass, Kartik Talamadupula, and Gerald Tesauro. "Learning to query, reason and answer question on ambiguous texts." (ICLR 2017). openreview
  • Ishan P. Durugkar, Clemens Rosenbaum, Stefan Dernbach, Sridhar Mahadevan. "Deep Reinforcement Learning With Macro-Actions" (arxiv 2016). arxiv
  • Clemens Rosenbaum and Sridhar Mahadevan. "Boosting Gradient Algorithms for Multi-Agent Games" (LICMAS@NIPS 2015).


My preferred type of contact is via email at cgbr@cs.umass.edu.