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.

112

Articles

Likes

228

Views

Comments

Latest from Network Intelligence Research Center (NIRC)

100 recent articles max

Network Intelligence Research Center (NIRC)

Jan 14, 2026 · Artificial Intelligence

From Black‑Box Guessing to Quantitative Deconstruction: Unveiling the Mystery Inside Large Language Models

At EMNLP 2025, the BUPT NIRC team presented a paper that introduces the ARR metric to quantitatively separate latent reasoning from factual shortcuts in LLMs, using Logit Lens and Attention Knockout to reveal distinct internal pathways and shares their conference experience.

ARR metricAttention KnockoutEMNLP2025

0 likes · 6 min read

From Black‑Box Guessing to Quantitative Deconstruction: Unveiling the Mystery Inside Large Language Models

Network Intelligence Research Center (NIRC)

Jan 11, 2026 · Artificial Intelligence

Insights from NeurIPS 2025: Modeling Distributions and Venturing Beyond Them

The report summarizes NeurIPS 2025 in San Diego, highlighting four NIRC papers on noise‑robust 3D human pose estimation, LVLM video‑anomaly understanding, and hand‑object reconstruction, and discusses broader industry trends such as feed‑forward generation and large‑scale pre‑training showcased by leading AI companies.

3D human pose estimationAI ResearchLVLM

0 likes · 5 min read

Insights from NeurIPS 2025: Modeling Distributions and Venturing Beyond Them

Network Intelligence Research Center (NIRC)

Jan 7, 2026 · Operations

From Minutes to Milliseconds: Atlas Architecture Solves Verification Bottlenecks

The paper presents Atlas, a native three‑layer distributed verification system that replaces centralized tools with switch, region, and center adapters, achieving sub‑20 ms validation for thousands of nodes and up to 1500× speedup over EPVerifier, while supporting incremental updates and preserving scalability.

ATLASDistributed ArchitecturePerformance

0 likes · 7 min read

From Minutes to Milliseconds: Atlas Architecture Solves Verification Bottlenecks

Network Intelligence Research Center (NIRC)

Jan 4, 2026 · Artificial Intelligence

How UniCodebook’s Unified 2D‑3D Discrete Priors Boost Noise‑Robust, Calibration‑Free 3D Human Pose Estimation

UniCodebook introduces a unified 2D‑3D discrete prior that combines continuous and discrete representations, enabling calibration‑free multiview 3D human pose estimation with superior noise robustness and higher accuracy, as demonstrated by state‑of‑the‑art results on Human3.6M and MPI‑INF‑3DHP.

3D pose estimationNeurIPS 2025Transformer

0 likes · 8 min read

How UniCodebook’s Unified 2D‑3D Discrete Priors Boost Noise‑Robust, Calibration‑Free 3D Human Pose Estimation

Network Intelligence Research Center (NIRC)

Dec 31, 2025 · Artificial Intelligence

Why AI Inference Is Slow and How Cutting‑Edge Tech Boosts It in Industrial Settings

The article analyzes the severe inference bottlenecks of large language models, CNNs, and recommendation systems and presents a suite of research‑driven accelerations—including token‑level pipeline parallelism (HPipe), KV‑cache clustering (ClusterAttn), quantization (QoKV), heterogeneous edge frameworks (DeepZoning, PICO), delay‑aware edge‑cloud scheduling (DECC), and operator choreography (RACE)—validated on real‑world industrial workloads.

AI inferenceedge AIheterogeneous computing

0 likes · 16 min read

Why AI Inference Is Slow and How Cutting‑Edge Tech Boosts It in Industrial Settings

Network Intelligence Research Center (NIRC)

Dec 30, 2025 · Artificial Intelligence

Bridging Tokenizer Gaps: Cross-Tokenizer Knowledge Distillation at AAAI 2026

This paper introduces SeDi, a semantics‑ and distribution‑aware cross‑tokenizer knowledge distillation framework that aligns teacher and student token spaces via bipartite graph components and top‑K re‑encoding, achieving state‑of‑the‑art performance and lower exposure bias on multiple LLM benchmarks.

AI ResearchKnowledge Distillationcross-tokenizer distillation

0 likes · 10 min read

Bridging Tokenizer Gaps: Cross-Tokenizer Knowledge Distillation at AAAI 2026

Network Intelligence Research Center (NIRC)

Dec 26, 2025 · Artificial Intelligence

Introducing MCP: A Standard Protocol to Empower Large Models with System Capabilities

MCP (Model Context Protocol) is an open standard that lets AI applications connect to external systems through a unified client‑server model, exposing Tools, Resources, and Prompts, while addressing security, permission, and audit concerns to make large‑model deployments more reusable and controllable.

AI integrationModel Context ProtocolTool Calling

0 likes · 4 min read

Introducing MCP: A Standard Protocol to Empower Large Models with System Capabilities

Network Intelligence Research Center (NIRC)

Dec 23, 2025 · Artificial Intelligence

ClusterAttn: Compressing KV Cache with Intrinsic Attention Clustering

ClusterAttn tackles the KV‑cache bottleneck of large language models by exploiting the natural clustering of attention scores, achieving up to 92% compression without accuracy loss, boosting throughput 2.6–4.8×, handling 128K‑token sequences on a single GPU, and outperforming existing training‑free compression methods.

KV cache compressionattention clusteringdensity clustering

0 likes · 8 min read

ClusterAttn: Compressing KV Cache with Intrinsic Attention Clustering

Network Intelligence Research Center (NIRC)

Dec 19, 2025 · Databases

DIVER: A Robust Text-to-SQL System Unveiled at SIGMOD 2026, Powering ChatBI

The paper introduces DIVER, an automated expert system that gives large language models human‑like exploration, reasoning, and verification abilities for Text‑to‑SQL, addressing the severe performance drop without expert evidence by innovating dynamic interactive value linking, multi‑agent automation, and adaptive evidence generation, and demonstrates up to 10.82% accuracy gains and strong robustness on real‑world benchmarks.

Automated Expert AgentChatBIDIVER

0 likes · 11 min read

DIVER: A Robust Text-to-SQL System Unveiled at SIGMOD 2026, Powering ChatBI

Network Intelligence Research Center (NIRC)

Dec 15, 2025 · Artificial Intelligence

Turning LLM-Generated Network Configurations into Verified, Safe Updates with Artanis

The paper introduces Artanis, an intent‑based network configuration update framework that combines large‑language‑model generation with a verification‑feedback loop and reinforcement‑learning optimization, addressing hallucination‑induced errors and ensuring safe, policy‑compliant deployments across diverse network scales.

Configuration ManagementIntent-based NetworkingLLM

0 likes · 9 min read

Turning LLM-Generated Network Configurations into Verified, Safe Updates with Artanis