Related papers: SAGE: Training-Free Semantic Evidence Composition …

Cloud applications are increasingly shifting from large monolithic services to complex graphs of loosely-coupled microservices. Despite the advantages of modularity and elasticity microservices offer, they also complicate cluster management…

Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph,…

The rapid proliferation of the Internet of Things (IoT) continues to expose critical security vulnerabilities, necessitating the development of efficient and robust intrusion detection systems (IDS). Machine learning-based intrusion…

The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their…

Despite several signs of progress have been made recently, limited research has been conducted for an inductive setting where embeddings are required for newly unseen nodes -- a setting encountered commonly in practical applications of deep…

Accurate cancer diagnosis remains a critical challenge in digital pathology, largely due to the gigapixel size and complex spatial relationships present in whole slide images. Traditional multiple instance learning (MIL) methods often…

Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs are dynamically evolving with the constant addition of…

As artificial intelligence continues to evolve, it is increasingly capable of handling a wide range of video analytics tasks with merely one large model. One of the key foundation technologies is the Segment Anything Model (SAM), which…

Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under question variants that test the same knowledge in different…

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distribution across these sparsely connected learning agents can be…

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…

Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…

Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has…

Image classification technology and performance based on Deep Learning have already achieved high standards. Nevertheless, many efforts have conducted to improve the stability of classification via ensembling. However, the existing ensemble…

Deep Neural Networks (DNNs) have been widely applied in Internet of Things (IoT) systems for various tasks such as image classification and object detection. However, heavyweight DNN models can hardly be deployed on edge devices due to…

We focus on collaborative edge inference over wireless, which enables multiple devices to cooperate to improve inference performance in the presence of corrupted data. Exploiting a key-query mechanism for selective information exchange (or,…

We introduce SAGE; a Generative LLM for inferring attribute values for products across world-wide e-Commerce catalogs. We introduce a novel formulation of the attribute-value prediction problem as a Seq2Seq summarization task, across…

In today's era of Internet of Things (IoT), where massive amounts of data are produced by IoT and other devices, edge computing has emerged as a prominent paradigm for low-latency data processing. However, applications may have diverse…

The field of text-to-image generation has undergone significant advancements with the introduction of diffusion models. Nevertheless, the challenge of editing real images persists, as most methods are either computationally intensive or…