Related papers: Emergence of Minimal Circuits for Indirect Object …

Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic posteriors, and large models conflate reasoning with memorization. We address this by…

Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where self-attentions are…

Linear Transformers and State Space Models have emerged as efficient alternatives to softmax Transformers for causal sequence modeling, enabling parallel training via matrix multiplication and efficient RNN-style inference. However, despite…

Why do models often attend to salient words, and how does this evolve throughout training? We approximate model training as a two stage process: early on in training when the attention weights are uniform, the model learns to translate…

Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many…

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any…

Recent Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses. Although they have achieved remarkable performance across a range of multi-modal tasks,…

Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities through training remain limited, particularly from a…

In-context learning \ -- performing tasks based on examples given in the prompt \ -- is an important capability that has emerged in large language models and has received significant attention in both theory and practice. Existing…

Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine. However, Transformer models, while lacking recurrence, are able to perform such reasoning…

Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial in the input length. However, generating explicit reasoning…

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…

Transformers are widely deployed in large language models (LLMs), yet most models still fail on basic arithmetic tasks such as multidigit addition. In contrast, we show that small transformers trained from scratch can solve n-digit addition…

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their…

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…