activity
20242026
collaborators

5 papers

cs.CL2026

Bootstrapping Embeddings for Low Resource Languages

Merve Basoz, Andrew Horne, Mattia Opper

Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised finetuning data. For high resource languag…

cs.AI2025

Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks

Paul Smolensky, Roland Fernandez, Zhenghao Herbert Zhou +3

Large Language Models (LLMs) have demonstrated impressive abilities in symbol processing through in-context learning (ICL). This success flies in the face of decades of critiques a…

cs.LG2025

TRA: Better Length Generalisation with Threshold Relative Attention

Mattia Opper, Roland Fernandez, Paul Smolensky +1

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of th…

cs.CL2025

Banyan: Improved Representation Learning with Explicit Structure

Mattia Opper, N. Siddharth

We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-r…

cs.AI2024

Compositional Generalization Across Distributional Shifts with Sparse Tree Operations

Paul Soulos, Henry Conklin, Mattia Opper +3

Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neur…