works on

From the 2 of 7 linked papers with an AI index.

collaborators

7 papers

cs.FL2026

Algebraic Decomposition Theory for Transformer Length Generalization

Andy Yang, Blerta Veseli, Corentin Barloy +5

Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks admit lengt…

cs.MA2026

Benefits and Limitations of Communication in Multi-Agent Reasoning

Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi +2

The paper introduces a theoretical framework for analyzing how communication among multiple agents affects their ability to perform complex reasoning tasks, providing bounds on req…

cs.LG2026

From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP

Michael Rizvi-Martel, Satwik Bhattamishra, Guillaume Rabusseau +1

The paper derives preliminary sample complexity bounds for learning C‑RASP constructions with Transformer models, linking their expressive power to learnability.

cs.LG2026

Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions

Blanka Köver, Alexandra Butoi, Anej Svete +2

Transformers consistently fail to learn certain simple functions that are provably expressible with specific parameter settings. This gap between learnability and expressivity is p…

cs.LG2026

Discovering Interpretable Algorithms by Decompiling Transformers to RASP

Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra +2

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the…

cs.LG2026

Provably Learning Attention with Queries

Satwik Bhattamishra, Kulin Shah, Michael Hahn +1

We study the problem of learning Transformer-based sequence models with black-box access to their outputs. In this setting, a learner may adaptively query the oracle with any seque…