2 papers
cs.AI2026
How Many Thoughts Can a Vector Hold? The Capacity of Reasoning by Superposition
Hongyu Gu, Chang Liu, Jingwen Fu
Large language models solve hard problems through intermediate computations across multi-step reasoning. Traditional chain-of-thought encodes these computations as tokens. Recent c…
cs.LG2026
Emergence of Frontier Superposition: Möbius attractor and Cascade Supervision
Hongyu Gu, Jingwen Fu
Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead of unrolling serial chain-of-th…