相关论文: TimeViper: A Hybrid Mamba-Transformer Vision-Langu…

Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Convolutional neural network (CNN) and Transformer-based architectures are two dominant deep learning models for polyp segmentation. However, CNNs have limited capability for modeling long-range dependencies, while Transformers incur…

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…

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…

Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…

Temporal Action Detection (TAD) in untrimmed videos poses significant challenges, particularly for Activities of Daily Living (ADL) requiring models to (1) process long-duration videos, (2) capture temporal variations in actions, and (3)…

While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…

With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the…

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…

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…

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…

Extracting actionable knowledge from industrial visual data is fundamentally bottlenecked by extreme class imbalance and the prohibitive computational complexity of modern foundation models. In semi-conductor manufacturing, identifying…

Robot grasping, whether handling isolated objects, cluttered items, or stacked objects, plays a critical role in industrial and service applications. However, current visual grasp detection methods based on Convolutional Neural Networks…

Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can…

Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the…

Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core…

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…