相关论文: Engineering Verifiable Modularity in Transformers …

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective…

Hybrid language models combining attention with state space models (SSMs) or linear attention offer improved efficiency, but whether both components are genuinely utilized remains unclear. We present a functional component ablation…

Attention mechanisms in deep learning architectures have often been used as a means of transparency and, as such, to shed light on the inner workings of the architectures. Recently, there has been a growing interest in whether or not this…

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

What structural inductive bias helps transformers reason over knowledge graphs? Through controlled ablations of a minimal transformer modification with four independently removable components (sparse adjacency masking, edge-type biases,…

Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for…

Variational quantum algorithms (VQAs) rely on parameterized quantum circuits (PQCs), whose performance is governed by expressibility and trainability. Existing studies typically evaluate these properties at the logical circuit level,…

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This degradation has been measured behaviorally but not…

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised…

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Owing to success in the data-rich domain of natural images, Transformers have recently become popular in medical image segmentation. However, the pairing of Transformers with convolutional blocks in varying architectural permutations leaves…

Transformers have reshaped machine learning by utilizing attention mechanisms to capture complex patterns in large datasets, leading to significant improvements in performance. This success has contributed to the belief that "bigger means…

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficiency challenges for real-world deployment. Despite some…

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…