Related papers: Snakes and Ladders: Two Steps Up for VideoMamba

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., the Mamba deep learning model, have shown great potential for long sequence modeling. Meanwhile building efficient and generic vision backbones purely upon…

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…

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is…

Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range…

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…

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…

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…

Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly…

The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends…

Advances in speech synthesis intensify security threats, motivating real-time deepfake detection research. We investigate whether bidirectional Mamba can serve as a competitive alternative to Self-Attention in detecting synthetic speech.…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate temporal dependencies and substantial sequence length. The…

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…

State Space Models (SSMs), particularly the Mamba architecture, have recently emerged as powerful alternatives to Transformers for sequence modeling, offering linear computational complexity while achieving competitive performance. Yet,…