Tagged articles
ERNIE
15 articles · Page 1 of 1
The ERNIE‑4.5‑VL visual‑language model breaks single‑modality limits by delivering breakthrough image, video, and text understanding across more than 100 languages, offering lightweight yet competitive performance against models like Qwen2.5‑VL, supporting 128K context, dual “thinking” modes, and extensive deployment resources.
AI researchERNIElarge language model
0 likes · 4 min read

Baidu has open‑sourced ten Ernie 4.5 models ranging from 0.3B to 424B parameters, featuring multimodal MoE pre‑training, advanced infrastructure, and post‑training tricks that deliver benchmark results surpassing DeepSeek‑V3 and OpenAI‑o1, sparking worldwide industry attention and reshaping AI competition.
AI competitionBaiduERNIE
0 likes · 8 min read


21CTOApr 26, 2025 · Artificial Intelligence
Baidu unveiled upgraded ERNIE 4.5 Turbo and ERNIE X1 Turbo models with enhanced multimodal abilities, lower costs and free access, while analysts debated the performance of its new P800 chip cluster and its strategic impact in the global AI race.
AI competitionBaiduERNIE
0 likes · 5 min read

Baidu announced that its upcoming Ernie 4.5 series will be open‑source from June 30, marking a shift from paid, closed‑source models to free, community‑driven AI and highlighting technical innovations like knowledge‑enhanced learning, continual learning, and multimodal capabilities.
AI industryBaiduERNIE
0 likes · 5 min read

Baidu’s sudden open‑source of ERNIE 4.5, triggered by DeepSeek R1’s rapid adoption and impressive performance gains, signals a market shift from closed AI ecosystems to open‑source dominance, forcing giants to rethink power, control, and user‑centric strategies.
AI modelsBaiduDeepSeek
0 likes · 5 min read

The article chronicles Baidu Search’s Model Architecture Group’s evolution of deep‑learning‑driven search, detailing the shift from inverted‑index to semantic vector indexing, the use of transformer‑based models for text and image queries, large‑scale offline/online pipelines, and extensive GPU‑centric optimizations such as pruning, quantization and distillation, all aimed at delivering precise, cost‑effective results to hundreds of millions of users.
ERNIEGPU InferenceSearch Architecture
0 likes · 14 min read

This article details Baidu Fengchao's practical use of large language models to improve search advertising satisfaction, covering search ad relevance, the transition from DNN to ERNIE, prompt-based industry isolation, AIGC applications, and a Q&A on model architecture and optimization.
AIERNIEad satisfaction
0 likes · 22 min read

IDC’s 2023 AI Large Model Technology Capability Assessment names Baidu’s Wenxin (ERNIE) series as the overall leader, earning seven full scores across twelve dimensions—including the sole perfect score for algorithm model—thanks to its four‑layer stack, knowledge‑enhanced core, PaddlePaddle platform, and extensive industry deployments with over 150,000 enterprises.
AI large modelsBaiduERNIE
0 likes · 6 min read

This article explores the rapid evolution of Baidu's semantic search models, the large GPU consumption they entail, and how extensive INT8 quantization, sensitivity analysis, calibration data augmentation, hyper‑parameter auto‑tuning, and advanced methods like Quantization‑Aware Training and SmoothQuant dramatically improve inference performance while preserving business metrics.
ERNIEINT8 quantizationSemantic Search
0 likes · 17 min read

Baidu applied large‑scale INT8 quantization to its ERNIE search semantic models, achieving over 25% inference speedup with less than 1% degradation in relevance metrics by selectively quantizing less‑sensitive fully‑connected layers, using automated calibration, hyper‑parameter tuning, and techniques such as QAT and SmoothQuant, while paving the way for even lower‑bit quantization and token pruning.
ERNIEINT8 quantizationSemantic Search
0 likes · 15 min read

The article presents a side‑by‑side demonstration of Baidu’s newly released Wenxin Yiyan and OpenAI’s GPT‑4 across literary creation, business copywriting, mathematical reasoning, Chinese idiom interpretation, acrostic poetry, and multimodal generation, then explains the underlying six‑core technologies and Baidu’s hardware‑cloud strategy while reporting audience reactions.
Chinese NLPERNIEGPT-4
0 likes · 11 min read

This article explains how Baidu's anti‑spam team tackled large‑scale promotional spam on Baidu Zhidao by combining the Ernie pretrained model with SimCSE contrastive learning, detailing the problem background, traditional methods, text‑representation stages, the SimCSE approach, training pipeline, optimizations, and experimental results.
Contrastive LearningERNIENLP
0 likes · 15 min read

This article reviews Baidu's knowledge‑enhanced semantic understanding models, detailing the evolution from early semantic techniques to ERNIE 1.0, 2.0 and the large‑scale ERNIE 3.0, its architecture, training strategies, performance benchmarks, and real‑world applications across industry.
AIERNIENLP
0 likes · 19 min read

This article introduces knowledge‑enhanced graph semantic understanding techniques, detailing the ERNIE pre‑training models, GraphSAGE, and the ERNIESage family of node, edge, and multi‑neighbor architectures, and demonstrates their explicit and implicit knowledge integration in industrial search, recommendation, and map‑POI applications.
ERNIEGraph Neural Networksindustrial applications
0 likes · 14 min read

This article reviews Baidu's research on semantic computing, covering the evolution of semantic representation, the development and evaluation of the ERNIE and SimNet models, their industrial applications, model compression techniques, and outlines future research priorities in multilingual and multimodal semantic understanding.
ERNIESimNetdeep learning
0 likes · 12 min read
