Related papers: Native Hybrid Attention for Efficient Sequence Mod…
To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive…
Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…
We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL)…
Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…
Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily…
Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…
Unlocking the potential of transformers on datasets of large physical systems depends on overcoming the quadratic scaling of the attention mechanism. This work explores combining the Erwin architecture with the Native Sparse Attention (NSA)…
Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…
While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…
Despite the success of Transformers, handling long contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention. Thus Transformers often require post-training with a larger attention…
Multi-Head Latent Attention (MLA) is a recent attention mechanism adopted in state-of-the-art LLMs such as DeepSeek-v3 and Kimi K2. Thanks to its novel formulation, MLA allows two functionally equivalent but computationally distinct kernel…
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…
Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadratically with the sequence length. While state-space models…
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…
Transformer self-attention computes pairwise token interactions, yet protein sequence to phenotype relationships often involve cooperative dependencies among three or more residues that dot product attention does not capture explicitly. We…
Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn,…
Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…
Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on neuromorphic hardware are often considered for…