Related papers: Priming: Hybrid State Space Models From Pre-traine…
Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…
Existing approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as…
State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their…
Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in…
Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba, that…
Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…
The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range dependency modeling between objects. Due to excellent long-range…
State-space models (SSMs) offer efficient alternatives to Transformers for long sequences, but their fixed-size recurrent state limits capability on algorithmic tasks, such as retrieving past context. In this work, we examine how in-context…
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…
We present a generative framework for inverse design of five-layer transmissive Huygens' metasurfaces (HMSs), addressing a longstanding challenge in achieving full-phase, high-efficiency unit cell designs with minimal full-wave simulations.…
State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…
State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent…
Spiking neural networks (SNNs) take inspiration from the brain to enable energy-efficient computations. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on modern sequential tasks, as they inherit…
The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…
Although transformers dominate many code-specific tasks, they have significant limitations. This paper explores State Space Models (SSMs) as a promising alternative for code understanding tasks such as retrieval, classification, and clone…
Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce…
We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…
State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient…
State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…
This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance…