Researcher, International Business Machines
2 papers at NeurIPS 2025
We introduce a novel, scalable framework to evaluate compositional generalization, leverage it to evaluate more than 5k models, and propose a family of neural models pushing the Pareto frontier on this task.
We propose a parametrisation of SSM transition matrices that enables SSMs to track states of arbitrary finite-state automata while keeping the cost of the parallel scan comparable to that of diagonal SSMs.
