Related papers: Akasha 2: Hamiltonian State Space Duality and Visu…
Future wireless systems increasingly require predictive and transferable representations that can support multiple physical-layer (PHY) tasks under dynamic environments. However, most existing supervised learning-based methods are designed…
In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building upon its predecessor, VideoLLaMA…
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…
High-definition (HD) maps are essential for autonomous driving, as they provide precise road information for downstream tasks. Recent advances highlight the potential of temporal modeling in addressing challenges like occlusions and…
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.…
This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across inputs, which can…
Selective state-space models excel at long-sequence modeling, but their capacity for language representation -- in complex hierarchical reasoning -- remains underexplored. Most large language models rely on \textit{flat} Euclidean…
Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue…
Multimodal sentiment analysis (MSA) integrates various modalities, such as text, image, and audio, to provide a more comprehensive understanding of sentiment. However, effective MSA is challenged by alignment and fusion issues. Alignment…
Large language models (LLMs) have demonstrated remarkable proficiency in a wide range of natural language processing applications. However, the high energy and latency overhead induced by the KV cache limits the edge deployment, especially…
Multi-modal learning that combines pathological images with genomic data has significantly enhanced the accuracy of survival prediction. Nevertheless, existing methods have not fully utilized the inherent hierarchical structure within both…
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…
Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by…
Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…
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…
Many natural phenomena involve processes that happen simultaneously at different characteristic length- and timescales. Typically, the region where the process of interest happens is affected by fluctuations in its surroundings. Modeling…
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…
With the rapid development of deep learning, low-light RAW image enhancement (LLRIE) has achieved remarkable progress. However, the challenge that how to simultaneously achieve strong enhancement quality and high efficiency still remains.…
Modern high-energy physics (HEP) experiments are increasingly challenged by the vast size and complexity of their datasets, particularly regarding large-scale point cloud processing and long sequences. In this study, to address these…
Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image, enabling diverse real-world applications. However, existing methods are often constrained by the local receptive field of…