Hugging Face Trending Papers

Chain-of-Thought Shows the Path to a Tree: Realizing Branching Complexity

Read the original on Hugging Face Trending Papers →

Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes. What remains largely missing are concrete instantiations with explicit, depth-bounded constructions, and the traversal procedures such characterizations presuppose.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 19

Efficiently Representing Algorithms With Chain-of-Thought Transformers

arXiv:2606. 19697v1 Announce Type: cross Abstract: The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation.

By Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill
Hugging Face Trending Papers
Aug 4

Separating quantum circuits from classical LLMs

Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes.

arXiv Machine Learning
Jun 18

Compact Geometric Representations of Hierarchies

arXiv:2606. 18520v1 Announce Type: cross Abstract: Computing geometric representations of data is a cornerstone of modern machine learning, typically achieved by training dual encoders which map queries and documents into a shared embedding space.

By Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal, Tony Chang Wang, Haike Xu
arXiv Machine Learning
Jun 3

Why Are Linear RNNs More Parallelizable?

arXiv:2603. 03612v3 Announce Type: replace Abstract: The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability.

By William Merrill, Hongjian Jiang, Yanhong Li, Anthony Lin, Ashish Sabharwal