Related papers: Geometric Attention: A Regime-Explicit Operator Se…
Self-attention in Transformers is typically implemented as $\mathrm{softmax}(QK^\top/\sqrt{d})V$, where $Q=XW_Q$, $K=XW_K$, and $V=XW_V$ are learned linear projections of the input $X$. We ask whether these learned projections are…
\textit{Attention} computes the dependency between representations, and it encourages the model to focus on the important selective features. Attention-based models, such as Transformer and graph attention network (GAT), are widely utilized…
Understanding whether attention mechanisms converge to the kernel regime is foundational to the validity of influence functions for transformer accountability. Exact NTK characterization of softmax attention is precluded by its exponential…
The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…
As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks,…
We present an approach to modifying Transformer architectures by integrating graph-aware relational reasoning into the attention mechanism, merging concepts from graph neural networks and language modeling. Building on the inherent…
This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation…
Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new…
Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the…
We present a geometric framework for analysing multi-head attention in large language models (LLMs). Without altering the mechanism, we view standard attention through a top-N selection lens and study its behaviour directly in value-state…
We propose a novel attention mechanism, named Cog Attention, that enables attention weights to be negative for enhanced expressiveness, which stems from two key factors: (1) Cog Attention enhances parameter flexibility. For example, unlike…
Linear attention methods offer a compelling alternative to softmax attention due to their efficiency in recurrent decoding. Recent research has focused on enhancing standard linear attention by incorporating gating while retaining its…
The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to…
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks (GCNs) can alleviate the typical oversmoothing of features…
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…
Although deep neural networks generally have fixed network structures, the concept of dynamic mechanism has drawn more and more attention in recent years. Attention mechanisms compute input-dependent dynamic attention weights for…
Attention regulates information transfer between tokens. For this, query and key vectors are compared, typically in terms of a scalar product, $\mathbf{Q}^T\mathbf{K}$, together with a subsequent softmax normalization. In geometric terms,…
Graph Attention Networks (GATs) are one of the most popular GNN architectures and are considered as the state-of-the-art architecture for representation learning with graphs. In GAT, every node attends to its neighbors given its own…
Learning solution operators for systems with complex, varying geometries and parametric physical settings is a central challenge in scientific machine learning. In many-query regimes such as design optimization, control and inverse…
While Transformer architecture excel at modeling long-range dependencies contributing to its widespread adoption in vision tasks the quadratic complexity of softmax-based attention mechanisms imposes a major bottleneck, particularly when…