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 explains RDMA's low‑latency, CPU‑bypass communication by detailing the roles of Queue Pairs, Work Queue Entries, and the Doorbell mechanism, comparing them with traditional TCP/IP and outlining their state machines, data structures, and notification workflow.
The article explains how AI compilers transform high‑level models into efficient hardware code, using TVM to illustrate operator optimization, automated scheduling, and end‑to‑end compilation workflow with concrete code examples and performance considerations.
This article surveys the most prominent AI agent development platforms—including Coze, Dify, CrewAI, Manus, and AutoGen—detailing their core features, integration capabilities, open‑source status, and how they enable developers to build, orchestrate, and deploy intelligent agents across diverse applications.
Perception‑R1, a post‑training framework that applies rule‑based reinforcement learning to existing multimodal LLMs, dramatically improves visual perception tasks such as grounding, OCR, counting and object detection, as demonstrated by extensive benchmarks and ablation studies.
The article shares a hands‑on review of Claude Code, a terminal‑based AI coding assistant, covering setup with custom API endpoints, the use of Claude.md for project context, subagent parallel development, comparisons with GeminiCLI and Cursor, and practical tips for effective use.
Dexterous hand grasping, a core challenge in embodied intelligence due to high degrees of freedom, is categorized into three approaches—ego-centric, object-centric, and ego-object interaction—each with distinct trade-offs, and the article cites representative works such as UniDexGrasp, GraspTTA, and DRO_Grasp.
This article explains the DCQCN end‑to‑end congestion control algorithm for RoCEv2, describes its three roles (RP, CP, NP), and provides detailed NS‑3 code implementations for ECN marking, CNP generation, and rate‑adjustment logic, including scheduling and parameter calculations.
The article compares three cross‑platform file‑synchronization solutions—LocalSend for LAN point‑to‑point transfers, Syncthing for decentralized multi‑device syncing, and JianGuoyun's WebDAV cloud—detailing their features, limitations, and practical usage tips.
This article introduces OpenAI's Triton language, compares its block‑wise programming model to traditional CUDA, walks through vector‑addition and fused‑softmax kernel implementations, and presents benchmark results that demonstrate significant speedups over native PyTorch operations.
This guide walks through the Hugging Face Transformers Trainer library, explaining its core features such as configurable training loops, mixed‑precision and gradient‑accumulation support, seamless distributed training via Accelerate and DeepSpeed, and provides a step‑by‑step example of converting a simple PyTorch CNN model to use Trainer.
