Related papers: LADR: Locality-Aware Dynamic Rescue for Efficient …

As large language models (LLMs) become increasingly adopted on edge devices, Retrieval-Augmented Generation (RAG) is gaining prominence as a solution to address factual deficiencies and hallucinations by integrating external knowledge.…

3D lane detection from monocular images is a fundamental yet challenging task in autonomous driving. Recent advances primarily rely on structural 3D surrogates (e.g., bird's eye view) built from front-view image features and camera…

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

Conventional algorithms in autonomous exploration face challenges due to their inability to accurately and efficiently identify the spatial distribution of convex regions in the real-time map. These methods often prioritize navigation…

The rapid evolution of mobile edge computing (MEC) has introduced significant challenges in optimizing resource allocation in highly dynamic wireless communication systems, in which task offloading decisions should be made in real-time.…

In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scarce scenarios. Recently, DMs have opened up the possibility…

Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which…

Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting,…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems…

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic…

Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood", are preserved. Such methods usually require propagation on…

We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

The recovery of high-quality images from images corrupted by lens flare presents a significant challenge in low-level vision. Contemporary deep learning methods frequently entail training a lens flare removing model from scratch. However,…

Revolutionary advancements in text-to-image models have unlocked new dimensions for sophisticated content creation, such as text-conditioned image editing, enabling the modification of existing images based on textual guidance. This…

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency.…

Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. However, routine clinical MRI scans are typically in low-resolution (LR) and vary greatly in contrast and spatial…