Related papers: Variational Linear Attention: Stable Associative M…

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks. While attention is a staple of modern network architectures, it is also notoriously expensive to deploy due to resource…

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling,…

We study efficient reasoning under tight compute. We ask how to make structured, correct decisions without increasing test time cost. We add two training only components to small and medium Transformers that also transfer to broader…

Transformers have significantly advanced AI and machine learning through their powerful attention mechanism. However, computing attention on long sequences can become a computational bottleneck. FlashAttention mitigates this by fusing the…

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Vision-language-action (VLA) models increasingly rely on auxiliary world modules to plan over long horizons, yet how such modules should be parameterized on top of a pretrained VLA remains an open design question. Existing…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as…

Transformer language models have driven significant progress across various fields, including natural language processing and computer vision. A central component of these models is the self-attention (SA) mechanism, which learns rich…

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…

Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However,…

Transformers' quadratic computational complexity limits their scalability despite remarkable performance. While linear attention reduces this to linear complexity, pre-training such models from scratch remains, in most cases, prohibitively…

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…

We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such…

Sparse attention, which selectively attends to a subset of tokens in the context was supposed to be efficient. However, its theoretical reduction in FLOPs has rarely translated into wall-clock speed-up over its dense attention counterparts…