6 papers
When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer
Mayug Maniparambil, Arjun Karuvally, Terrence Sejnowski +1
Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why it does so -- remain under-expl…
TopoBench: Benchmarking LLMs on Hard Topological Reasoning
Mayug Maniparambil, Nils Hoehing, Janak Kapuriya +5
Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most…
Bridging Expressivity and Scalability with Adaptive Unitary SSMs
Arjun Karuvally, Franz Nowak, Anderson T. Keller +3
Recent work has revealed that state space models (SSMs), while efficient for long-sequence processing, are fundamentally limited in their ability to represent formal languages-part…
Exponential Dynamic Energy Network for High Capacity Sequence Memory
Arjun Karuvally, Pichsinee Lertsaroj, Terrence J. Sejnowski +1
The energy paradigm, exemplified by Hopfield networks, offers a principled framework for memory in neural systems by interpreting dynamics as descent on an energy surface. While po…
Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
Alexander Yeung, Peter DelMastro, Arjun Karuvally +3
Reservoir Computing is a machine learning approach that uses the rich repertoire of complex system dynamics for function approximation. Current approaches to reservoir computing us…
Transient Dynamics in Lattices of Differentiating Ring Oscillators
Peter DelMastro, Arjun Karuvally, Hananel Hazan +2
Recurrent neural networks (RNNs) are machine learning models widely used for learning temporal relationships. Current state-of-the-art RNNs use integrating or spiking neurons -- tw…