Related papers: Shaking Up VLMs: Comparing Transformers and Struct…

The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context…

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…

Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features…

Transformers bring significantly improved performance to the light field image super-resolution task due to their long-range dependency modeling capability. However, the inherently high computational complexity of their core self-attention…

Vision Mamba has recently received attention as an alternative to Vision Transformers (ViTs) for image classification. The network size of Vision Mamba scales linearly with input image resolution, whereas ViTs scale quadratically, a feature…

The rapid development of large language and vision models (LLVMs) has been driven by advances in visual instruction tuning. Recently, open-source LLVMs have curated high-quality visual instruction tuning datasets and utilized additional…

Recent years have witnessed significant advancements in light field image super-resolution (LFSR) owing to the progress of modern neural networks. However, these methods often face challenges in capturing long-range dependencies (CNN-based)…

With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a…

Mamba is an efficient State Space Model (SSM) with linear computational complexity. Although SSMs are not suitable for handling non-causal data, Vision Mamba (ViM) methods still demonstrate good performance in tasks such as image…

Voice user interfaces (VUIs) have facilitated the efficient interactions between humans and machines through spoken commands. Since real-word acoustic scenes are complex, speech enhancement plays a critical role for robust VUI. Transformer…

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…

The strength of modern large-scale neural networks lies in their ability to efficiently adapt to new tasks with few examples. Although extensive research has investigated the transferability of Vision Transformers (ViTs) to various…

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense…

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM),…

Recently, a novel visual state space (VSS) model, referred to as Mamba, has demonstrated significant progress in modeling long sequences with linear complexity, comparable to Transformer models, thereby enhancing its adaptability for…

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the…

While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structured state space sequence models (SSMs) and Selective SSMs.…