Related papers: Beyond Hallucinations: A Multimodal-Guided Task-Aw…
Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related…
Transferring large amount of high resolution images over limited bandwidth is an important but very challenging task. Compressing images using extremely low bitrates (<0.1 bpp) has been studied but it often results in low quality images of…
Diffusion models have demonstrated impressive performance in text-to-image generation. They utilize a text encoder and cross-attention blocks to infuse textual information into images at a pixel level. However, their capability to generate…
Recent developments in Transformers have achieved notable strides in enhancing video comprehension. Nonetheless, the O($N^2$) computation complexity associated with attention mechanisms presents substantial computational hurdles when…
Domain-specific image generation aims to produce high-quality visual content for specialized fields while ensuring semantic accuracy and detail fidelity. However, existing methods exhibit two critical limitations: First, current approaches…
Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive…
Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…
Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hallucinations, meaning that VLMs tend to generate responses…
The rapid advancement of generative artificial intelligence has spurred innovative approaches to semantic communication, giving rise to a new paradigm known as generative semantic communication (GSC). The integration of flexible cross-modal…
Accurate 3D reconstruction in degraded imaging conditions remains a key challenge in photogrammetry and neural rendering. In underwater environments, spatially varying visibility caused by scattering, attenuation, and sparse observations…
Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos…
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…
Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object…
Discrete representation has emerged as a powerful tool in task-oriented semantic communication (ToSC), offering compact, interpretable, and efficient representations well-suited for low-power edge intelligence scenarios. Its inherent…
Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding. They have long coding times and highly customized data format, making it difficult for widespread…
Semi-supervised semantic segmentation (SSSS) is vital in computational pathology, where dense annotations are costly and limited. Existing methods often rely on pixel-level consistency, which propagates noisy pseudo-labels and produces…
Multi-modal image fusion aggregates information from multiple sensor sources, achieving superior visual quality and perceptual features compared to single-source images, often improving downstream tasks. However, current fusion methods for…
In this work, we study the problem of generating novel images from complex multimodal prompt sequences. While existing methods achieve promising results for text-to-image generation, they often struggle to capture fine-grained details from…
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce…
This paper proposes new framework of communication system leveraging promising generation capabilities of multi-modal generative models. Regarding nowadays smart applications, successful communication can be made by conveying the perceptual…