NIRC is based on the National Key Laboratory of Network and Switching Technology at Beijing University of Posts and Telecommunications. It has built a technology matrix across four AI domains—intelligent cloud networking, natural language processing, computer vision, and machine learning systems—dedicated to solving real‑world problems, creating top‑tier systems, publishing high‑impact papers, and contributing significantly to the rapid advancement of China's network technology.
The article recounts the authors' participation in the 2024 USENIX NSDI conference in Santa Clara, detailing the acceptance and presentation of their EPVerifier paper, the conference schedule, a poster dinner, and their travel experiences exploring San Francisco's landmarks.
This article presents a dynamic RAN slicing model and an online PW‑DRL approach that combines deep learning, reinforcement learning, and Lyapunov optimization to allocate resources adaptively, detailing a four‑step decision process, LSTM/CNN predictions, and experimental results showing improved transmission rates and acceptance ratios across DTT, DS, and TO slices.
This article explains how a deep reinforcement learning model, built on a graph‑based representation of urban elements and trained with PPO, can automate land‑use and road planning to achieve Service, Ecology, and Traffic objectives for 15‑minute city neighborhoods.
The article analyzes the limitations of traditional speech‑driven lip‑sync methods and explains how Wav2Lip introduces a pretrained multi‑frame expert sync discriminator, a two‑stage GAN training pipeline, and a specialized generator architecture to produce high‑quality, audio‑aligned facial videos.
The article reviews the CVPR 2021 MIST framework, explaining how a multiple‑instance pseudo‑label generator and a self‑guided attention encoder work together with sparse continuous sampling to improve context awareness and detection accuracy in weakly‑supervised video anomaly detection.
This article examines XDP (eXpress Data Path), a Linux kernel eBPF‑based technology that pushes packet processing to the earliest point in the network interface, delivering ultra‑low latency, enhanced security, and flexible custom processing for high‑performance routing, DDoS mitigation, and cloud environments.
The article reviews the paper "Robust High-Resolution Video Matting with Temporal Guidance", detailing a GRU‑based multi‑task network that achieves real‑time performance on 4K (76 FPS) and 1080p (104 FPS) video by leveraging temporal information and semantic segmentation.
MongoDB is an open‑source, C++‑based NoSQL document database that stores data as BSON documents in collections, offering schema‑less modeling, embedded structures, high scalability through sharding, and a rich set of CRUD commands for modern application needs.
DeepQueueNet combines discrete‑event and continuous simulation with deep neural networks to deliver highly accurate, generalizable, and GPU‑scalable network performance estimates at packet‑level granularity, outperforming existing DNN‑based estimators across diverse topologies and traffic scenarios.
LONGNET introduces dilated attention to enable Transformers to process sequences exceeding one billion tokens with linear computational cost, preserving performance on shorter inputs and demonstrating strong results on long‑sequence modeling and standard language tasks.
