Related papers: Hierarchical Mamba Meets Hyperbolic Geometry: A Ne…

The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…

While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised learning (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore…

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…

Explanations for \emph{black-box} models help us understand model decisions as well as provide information on model biases and inconsistencies. Most of the current explainability techniques provide a single level of explanation, often in…

Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual…

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity.…

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing…

Deep unfolding methods have made impressive progress in restoring 3D hyperspectral images (HSIs) from 2D measurements through convolution neural networks or Transformers in spectral compressive imaging. However, they cannot efficiently…

The hyperbolic manifold is a smooth manifold of negative constant curvature. While the hyperbolic manifold is well-studied in the literature, it has gained interest in the machine learning and natural language processing communities lately…

Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics…

In recent years, Visual Question Localized-Answering in robotic surgery (Surgical-VQLA) has gained significant attention for its potential to assist medical students and junior doctors in understanding surgical scenes. Recently, the rapid…

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resolution images remains suboptimal. While existing approaches often attribute this limitation to…

Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of…

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these…

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes…

Many high-dimensional practical data sets have hierarchical structures induced by graphs or time series. Such data sets are hard to process in Euclidean spaces and one often seeks low-dimensional embeddings in other space forms to perform…

Heterogeneous multirobot systems show great potential in complex tasks requiring coordinated hybrid cooperation. However, existing methods that rely on static or task-specific models often lack generalizability across diverse tasks and…

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting…

Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based,…