7.8k citations · 21.1k across the 144 of their papers we have counts for
14 papers · 1 filter
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Xiangming Gu, Soham De, Larisa Markeeva +2
Large Reasoning Models (LRMs) have shown remarkable performance on challenging questions, such as math and coding. However, to obtain a high quality solution, one may need to sampl…
The Illusion of Stochasticity in LLMs
Xiangming Gu, Soham De, Michalis Titsias +3
In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents. Agentic systems ar…
RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling
Xiuying Wei, Anunay Yadav, Razvan Pascanu +1
Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and infere…
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan +7
Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relati…
Why do LLMs attend to the first token?
Federico Barbero, Álvaro Arroyo, Xiangming Gu +4
Large Language Models (LLMs) tend to attend heavily to the first token in the sequence -- creating a so-called attention sink. Many works have studied this phenomenon in detail, pr…
How do language models learn facts? Dynamics, curricula and hallucinations
Nicolas Zucchet, Jörg Bornschein, Stephanie Chan +3
Large language models accumulate vast knowledge during pre-training, yet the dynamics governing this acquisition remain poorly understood. This work investigates the learning dynam…
Round and Round We Go! What makes Rotary Positional Encodings useful?
Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos +2
Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position informatio…
Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis
Xiuying Wei, Skander Moalla, Razvan Pascanu +1
State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting pe…
Transformers meet Neural Algorithmic Reasoners
Wilfried Bounsi, Borja Ibarz, Andrew Dudzik +5
Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unma…
Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers
Xiuying Wei, Skander Moalla, Razvan Pascanu +1
State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' pa…
Transformers need glasses! Information over-squashing in language tasks
Federico Barbero, Andrea Banino, Steven Kapturowski +5
We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoreti…
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu +5
We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach impr…
Towards Robust and Efficient Continual Language Learning
Adam Fisch, Amal Rannen-Triki, Razvan Pascanu +4
As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a…
A simple neural network module for relational reasoning
Adam Santoro, David Raposo, David G. T. Barrett +4
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation…