Related papers: SA-OOSC: A Multimodal LLM-Distilled Semantic Commu…

Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus on sample-level objectives via contrastive learning while overlooking the crucial…

Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-level lexical variation, limiting semantic exploration. In this paper, we propose…

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g.,…

Misinformation is a prevalent societal issue due to its potential high risks. Out-of-context (OOC) misinformation, where authentic images are repurposed with false text, is one of the easiest and most effective ways to mislead audiences.…

Identifying wireless modulation schemes is essential for cognitive radio, but standard supervised models often degrade under distribution shift, and training domain-specific wireless foundation models from scratch is computationally…

Semantic Scene Completion (SSC) constitutes a pivotal element in autonomous driving perception systems, tasked with inferring the 3D semantic occupancy of a scene from sensory data. To improve accuracy, prior research has implemented…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), such as CLIP, for dense prediction. However, VLMs, pre-trained…

Semantic communications are expected to accomplish various semantic tasks with relatively less spectrum resource by exploiting the semantic feature of source data. To simultaneously serve both the data transmission and semantic tasks, joint…

In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP) model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) to leverage…

Scaling test-time computation--generating and analyzing multiple or sequential outputs for a single input--has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances…

Large language models (LLMs) have garnered increasing attention owing to their powerful logical reasoning capabilities. Generally, larger LLMs (L-LLMs) that require paid interfaces exhibit significantly superior performance compared to…

We present an AI-based framework for semantic transmission of multimedia data over band-limited, time-varying channels. The method targets scenarios where large content is split into multiple packets, with an unknown number potentially…

The integration of machine learning (ML) has significantly enhanced the capabilities of Earth Observation (EO) systems by enabling the extraction of actionable insights from complex datasets. However, the performance of data-driven EO…

Task-oriented semantic communications have achieved significant performance gains. However, the employed deep neural networks in semantic communications have to be updated when the task is changed or multiple models need to be stored for…

Scene segmentation and classification (SSC) serve as a critical step towards the field of video structuring analysis. Intuitively, jointly learning of these two tasks can promote each other by sharing common information. However, scene…

Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object grounding and contextual reasoning, limiting their ability…

It remains a significant challenge to compress images at extremely low bitrate while achieving both semantic consistency and high perceptual quality. Inspired by human progressive perception mechanism, we propose a Semantically Disentangled…

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on…

In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and…