activity
20222026
most citedHidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks

2 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

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…

cs.AI2026

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…