Author

Baidu Tech Salon

Baidu Tech Salon, organized by Baidu's Technology Management Department, is a monthly offline event that shares cutting‑edge tech trends from Baidu and the industry, providing a free platform for mid‑to‑senior engineers to exchange ideas.

283

Articles

Likes

466

Views

Comments

Latest from Baidu Tech Salon

100 recent articles max

Baidu Tech Salon

Apr 16, 2025 · Artificial Intelligence

Release of the 'Fangsheng' Large Model Benchmark Results (Q1 2025) and Overview of Baidu's Wenxin 4.5 and X1 Models

The China AI Industry Alliance unveiled its Q1 2025 Fangsheng benchmark, showing Baidu’s new multimodal models—Wenxin 4.5 leading basic abilities and Wenxin X1 excelling in reasoning—available for free on the Wenxin Yiyan platform, while Baidu pledges major 2025 investments in AI, data‑center and cloud infrastructure.

AIFactTestingWenxin

0 likes · 4 min read

Release of the 'Fangsheng' Large Model Benchmark Results (Q1 2025) and Overview of Baidu's Wenxin 4.5 and X1 Models

Baidu Tech Salon

Apr 2, 2025 · Artificial Intelligence

PaddlePaddle Framework 3.0 Released: Five Core Innovations for Large Models and Scientific Computing

PaddlePaddle 3.0, launched on April 1 2025, introduces five core innovations—including dynamic‑static unified automatic parallelism, a training‑inference integrated PIR, high‑order automatic differentiation for scientific computing, a one‑stage CINN compiler, and heterogeneous multi‑chip adaptation—that dramatically reduce distributed‑training code, boost performance up to four‑fold, and extend the framework to aerospace, automotive, meteorology and life‑science applications while remaining fully compatible with the 2.0 API.

PaddlePaddleautomatic parallelismdeep learning

0 likes · 21 min read

PaddlePaddle Framework 3.0 Released: Five Core Innovations for Large Models and Scientific Computing

Baidu Tech Salon

Mar 21, 2025 · Artificial Intelligence

Semantic Embedding with Large Language Models: A Comprehensive Survey

This survey reviews the evolution of semantic embedding—from Word2vec and GloVe to BERT, Sentence‑BERT, and recent contrastive methods—then examines how large language models improve embeddings via synthetic data generation and backbone architectures, detailing techniques such as contrastive prompting, in‑context learning, knowledge distillation, and discussing resource, privacy, and interpretability challenges.

Information RetrievalIn‑context LearningNLP

0 likes · 27 min read

Semantic Embedding with Large Language Models: A Comprehensive Survey

Baidu Tech Salon

Mar 13, 2025 · Artificial Intelligence

How PaddlePaddle 3.0 Boosts Large‑Model Inference with 4‑Bit Quantization and MLA Optimizations

PaddlePaddle 3.0 introduces a full‑stack inference engine that supports FP8, INT8, and 4‑bit quantization for popular LLMs such as DeepSeek V3/R1, delivers up to 2× token throughput on a single H800 GPU, and provides detailed deployment scripts for single‑node and multi‑node setups, including MTP speculative decoding and SageAttention for long‑sequence acceleration.

DockerMLAMTP

0 likes · 13 min read

How PaddlePaddle 3.0 Boosts Large‑Model Inference with 4‑Bit Quantization and MLA Optimizations

Baidu Tech Salon

Mar 6, 2025 · Big Data

Real-Time Anti-Fraud Streaming System Based on Flink: Architecture, Challenges, and Optimizations

The article describes a Flink‑based real‑time anti‑fraud streaming system that combines a risk‑control platform, configurable YAML‑driven pipelines, and optimized state handling—using early event‑time triggers, micro‑batch caching, and coarse‑grained key reduction—to compute multi‑dimensional features, support rapid strategy updates, simulation filtering, and seamless output to ClickHouse, Hive, and Redis for both instant monitoring and offline analysis.

ConfigurationFlinkReal-time Streaming

0 likes · 26 min read

Real-Time Anti-Fraud Streaming System Based on Flink: Architecture, Challenges, and Optimizations

Baidu Tech Salon

Feb 26, 2025 · Artificial Intelligence

Graph‑Engine‑Driven Workflow for Building Intelligent Agents

The article presents a graph‑engine‑driven workflow platform that lets developers assemble, orchestrate, and execute intelligent LLM‑based agents with low‑code visual design, fine‑grained path control, hierarchical sub‑flows, and event‑driven hooks, addressing perception, reasoning, planning, and scalability challenges while surpassing existing frameworks.

Data DecouplingIntelligent AgentsLLM

0 likes · 19 min read

Graph‑Engine‑Driven Workflow for Building Intelligent Agents

Baidu Tech Salon

Feb 24, 2025 · Frontend Development

How Baidu Boosted Live‑Stream Interactivity: Performance & Stability Techniques

An in‑depth technical case study reveals how Baidu’s live‑stream platform integrated a “music + red‑packet” experience, employing page partitioning, SSG/SSR/ISR, data and resource prefetch, view prerender, and robust fallback mechanisms to dramatically improve concurrency, load speed, and interaction stability.

OptimizationPerformancefrontend

0 likes · 17 min read

How Baidu Boosted Live‑Stream Interactivity: Performance & Stability Techniques

Baidu Tech Salon

Feb 20, 2025 · Backend Development

Avalanche Prevention Architecture in Baidu Netdisk: Practices and Solutions

Baidu Netdisk engineers protect its billion‑user service from cascading failures by deploying dynamic circuit‑breaker overload control, priority‑based traffic isolation, request‑validity filtering, socket‑level disconnect detection, and unified timestamp handling, a combination that dramatically reduces avalanche incidents and boosts overall availability.

avalanche preventionbackend architecturecircuit breaker

0 likes · 17 min read

Avalanche Prevention Architecture in Baidu Netdisk: Practices and Solutions

Baidu Tech Salon

Jan 21, 2025 · Artificial Intelligence

How AI Is Transforming Legal Research: Inside the YuanDian WenDa Smart Q&A Engine

Faced with billions of legal documents and the shortcomings of keyword search, Chinese legal professionals are turning to the AI‑powered YuanDian WenDa engine, which leverages Baidu's Wenxin model, a structured legal database, and prompt‑engineering to deliver trustworthy, citation‑rich answers and rapid research reports.

AIInformation RetrievalKnowledge Graph

0 likes · 10 min read

How AI Is Transforming Legal Research: Inside the YuanDian WenDa Smart Q&A Engine

Baidu Tech Salon

Jan 10, 2025 · Industry Insights

How Baidu’s PaddlePaddle Fuels AI Ecosystem Growth in Wuhan – Key Takeaways from the Wenxin China Tour

The Wenxin China Tour’s Wuhan stop showcased the launch of Baidu’s PaddlePaddle AI Empowerment Center, presented industry‑wide AI ecosystem data, highlighted regional collaborations with universities and enterprises, and featured workshops and award ceremonies that illustrate the rapid adoption of large‑model technologies in Wuhan’s emerging AI market.

AIAI educationIndustry Ecosystem

0 likes · 10 min read

How Baidu’s PaddlePaddle Fuels AI Ecosystem Growth in Wuhan – Key Takeaways from the Wenxin China Tour