BestHub
Sign in
Network Intelligence Research Center (NIRC)
Author

Network Intelligence Research Center (NIRC)

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.

118
Articles
0
Likes
416
Views
0
Comments
Recent Articles

Latest from Network Intelligence Research Center (NIRC)

100 recent articles max
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Mar 26, 2025 · Artificial Intelligence

Enable Traditional LLMs to Use DeepSeek’s Multi‑Head Latent Attention Without Retraining

The paper introduces MHA2MLA, a data‑efficient fine‑tuning framework that converts pre‑trained multi‑head attention LLMs to DeepSeek’s Multi‑Head Latent Attention architecture, achieving up to 92% KV‑cache compression with less than 0.5% performance loss on long‑context tasks.

LLMLow-Rank ApproximationMulti-Head Attention
0 likes · 8 min read
Enable Traditional LLMs to Use DeepSeek’s Multi‑Head Latent Attention Without Retraining
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Mar 19, 2025 · Game Development

Quickly Build a MetaXR Interaction Lab in Unity

This guide walks through setting up Meta XR SDK in Unity, using Building Blocks to add camera rigs, hand tracking and passthrough, binding interaction events, accessing hand‑tracking data via OVRSkeleton/OVRHand, and integrating ONNX machine‑learning models for XR experiments.

BuildingBlocksHandTrackingMetaXR
0 likes · 7 min read
Quickly Build a MetaXR Interaction Lab in Unity
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Mar 12, 2025 · Artificial Intelligence

How Sparse Autoencoders Uncover Monosemantic Features in Large Language Models

The article reviews the paper ‘Towards Monosemanticity: Decomposing Language Models With Dictionary Learning’, showing how Anthropic’s sparse autoencoders extract interpretable, monosemantic concepts from transformer layers, enable controlled generation, and reveal trade‑offs such as data‑intensive training and potential performance impacts.

Dictionary LearningFeature ControlLLM Interpretability
0 likes · 9 min read
How Sparse Autoencoders Uncover Monosemantic Features in Large Language Models
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Mar 10, 2025 · Artificial Intelligence

Revisiting Knowledge Distillation for Autoregressive Language Models

The article analyzes why larger teacher models can hurt student performance in autoregressive language model distillation, reveals that different tokens require distinct teaching modes, proposes an Adaptive Token‑wise Knowledge Distillation (ATKD) method, and shows through extensive experiments that ATKD consistently improves accuracy by about 3 % and enhances generalization across model sizes.

adaptive teachingautoregressive language modelsknowledge distillation
0 likes · 9 min read
Revisiting Knowledge Distillation for Autoregressive Language Models
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jan 9, 2025 · User Experience Design

Introducing a Bare-Hand VR Whiteboard for Natural Handwriting

The article presents a VR bare‑hand whiteboard system that replaces controllers with natural hand gestures, detailing its evolution, technical challenges, error‑filtering and smoothing algorithms, multi‑board synchronization, required Unity SDKs, and its validation through a CSCW research paper and user studies.

UnityVRbare-hand interaction
0 likes · 14 min read
Introducing a Bare-Hand VR Whiteboard for Natural Handwriting
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Oct 8, 2024 · Artificial Intelligence

Two NIRC Papers Accepted at NeurIPS 2024: FM-Delta Compression and GLAFF Forecasting

The Beijing University of Posts and Telecommunications' Network Intelligent Research Center (NIRC) had two papers accepted to NeurIPS 2024, presenting FM-Delta, a lossless compression technique that halves storage and cuts cloud costs by over 40%, and GLAFF, a global‑local fusion framework that markedly improves the robustness of time‑series forecasting across multiple domains.

AI researchFM-DeltaGLAFF
0 likes · 8 min read
Two NIRC Papers Accepted at NeurIPS 2024: FM-Delta Compression and GLAFF Forecasting
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Mar 18, 2024 · Artificial Intelligence

Deep Reinforcement Learning for Online Resource Allocation in Network Slicing

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.

Lyapunov optimizationNetwork SlicingOFDMA
0 likes · 6 min read
Deep Reinforcement Learning for Online Resource Allocation in Network Slicing
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Nov 9, 2023 · Artificial Intelligence

How Wav2Lip Achieves Accurate Speech‑Driven Lip Sync with Expert Discriminators

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.

Computer VisionGaNWav2Lip
0 likes · 7 min read
How Wav2Lip Achieves Accurate Speech‑Driven Lip Sync with Expert Discriminators