Related papers: Decoder-Hybrid-Decoder Architecture for Efficient …

Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fading memory from SSMs. This yields smaller Key-Value caches and faster decoding than…

Efficiently modeling sequences with infinite context length has long been a challenging problem. Previous approaches have either suffered from quadratic computational complexity or limited extrapolation ability in length generalization. In…

Hybrid models that combine state space models (SSMs) with attention mechanisms have shown strong performance by leveraging the efficiency of SSMs and the high recall ability of attention. However, the architectural design choices behind…

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Linear models such as Mamba and sliding-window attention (SWA)…

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

We describe a family of architectures to support transductive inference by allowing memory to grow to a finite but a-priori unknown bound while making efficient use of finite resources for inference. Current architectures use such resources…

State Space Models (SSMs) are efficient alternatives to traditional sequence models, excelling at processing long sequences with lower computational complexity. Their reliance on matrix multiplications makes them ideal for compute-in-memory…

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…

To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core…

The task of recognising Handwritten Mathematical Expressions (HMER) is crucial in the fields of digital education and scholarly research. However, it is difficult to accurately determine the length and complex spatial relationships among…

Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity,…

Advanced deep learning architectures, particularly recurrent neural networks (RNNs), have been widely applied in audio, bioacoustic, and biomedical signal analysis, especially in data-scarce environments. While gated RNNs remain effective,…

We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Specifically, Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model…

Large language models (LLMs) have made significant advances in complex reasoning tasks, yet they remain bottlenecked by two core challenges: architectural inefficiency due to reliance on Transformers, and a lack of structured fine-tuning…

The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating…

State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. In this paper, we propose a multi-head state space (MH-SSM)…

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

The rise of test-time scaling has remarkably boosted the reasoning and agentic proficiency of Large Language Models (LLMs). Yet, standard Transformers struggle to scale inference-time compute efficiently, as conventional looping strategies…

State Space Models (SSMs) have emerged as a promising alternative to Transformers for long-context sequence modeling, offering linear $O(N)$ computational complexity compared to the Transformer's quadratic $O(N^2)$ scaling. This paper…