3 papers
cs.FL2026
When Does Tool Use Increase the Expressive Power of Finite-Precision Recurrent Models?
Nikola Zubić, Qian Li, Yuyi Wang +1
Modern sequence models are increasingly deployed as agents that interleave token generation with calls to external tools. We study when such tool access increases computational exp…
cs.LG2026
On the Expressive Power and Limitations of Multi-Layer SSMs
Nikola Zubić, Qian Li, Yuyi Wang +1
We study how depth, finite precision, state dimension, and chain-of-thought (CoT) affect the expressive power of multi-layer state-space models (SSMs). For the explicit-table -f…
cs.DC2025
Robust and Scalable Renaming with Subquadratic Bits
Sirui Bai, Xinyu Fu, Yuheng Wang +2
In the renaming problem, a set of nodes, each with a unique identity from a large namespace , needs to obtain new unique identities in a smaller namespace . A renamin…