BestHub
Sign in
Tagged articles

large language model

831 articles · Page 5 of 9
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Oct 11, 2025 · Artificial Intelligence

Recent Advances in Multivariate Time Series Forecasting: Paper Summaries (Sep 27 – Oct 10 2025)

This article summarizes eight newly released AI papers on multivariate time‑series forecasting and anomaly detection, detailing each work's motivation, proposed methodology, key innovations such as CRIB, TS‑JEPA, DSAT‑HD, DIMIGNN, ASTGI, IndexNet, TsLLM, Moon, TimeSeriesScientist, MLG‑4TS, and Augur, and reports their experimental validation on real‑world datasets.

Deep LearningTime Series ForecastingTransformer
0 likes · 23 min read
Recent Advances in Multivariate Time Series Forecasting: Paper Summaries (Sep 27 – Oct 10 2025)
DataFunSummit
DataFunSummit
Oct 10, 2025 · Artificial Intelligence

How Ping An Life Built ChatBI: An AI‑Powered Intelligent BI Platform

This article details Ping An Life's self‑developed large‑model reporting product ChatBI, covering its background, goals, solution architecture, technical stack, real‑world use cases, deployment challenges, and future outlook, offering practical insights for enterprises adopting AI‑driven business intelligence.

AIBusiness IntelligenceEnterprise AI
0 likes · 17 min read
How Ping An Life Built ChatBI: An AI‑Powered Intelligent BI Platform
DataFunTalk
DataFunTalk
Oct 9, 2025 · Artificial Intelligence

How Bilibili Uses Large Language Models to Solve Big Data Task Failures

This article explains Bilibili's massive data platform architecture, the common reasons offline tasks fail or slow down, and how the company is exploring large‑language‑model‑driven assistants to automatically diagnose and resolve these engineering issues.

AI assistanceBig Data PlatformBilibili
0 likes · 4 min read
How Bilibili Uses Large Language Models to Solve Big Data Task Failures
HyperAI Super Neural
HyperAI Super Neural
Oct 8, 2025 · Artificial Intelligence

From WeChat’s AI Podcast Trial to Google, ByteDance and Xiaohongshu: Can AI Podcasts Capture the Emerging AIGC Blue Ocean?

The article examines how breakthroughs in large language models and high‑fidelity TTS are powering AI‑generated podcasts, analyzes the technical advances behind the "human‑like" sound, surveys major players such as Google, ByteDance, Xiaohongshu and startups, and evaluates the market potential of this rapidly expanding AIGC niche.

AI podcastAIGCByteDance
0 likes · 9 min read
From WeChat’s AI Podcast Trial to Google, ByteDance and Xiaohongshu: Can AI Podcasts Capture the Emerging AIGC Blue Ocean?
DataFunSummit
DataFunSummit
Oct 7, 2025 · Artificial Intelligence

Bilibili’s AI‑Powered Assistant: Solving Big Data Task Failures with LLMs

This article details Bilibili's implementation of a large‑language‑model‑driven intelligent assistant that helps engineers diagnose and resolve massive offline and real‑time data‑processing failures, describing the platform’s five‑layer architecture, common failure and slowdown causes, and the need for AI‑powered troubleshooting support.

Big Data PlatformBilibiliIntelligent Assistant
0 likes · 4 min read
Bilibili’s AI‑Powered Assistant: Solving Big Data Task Failures with LLMs
DataFunSummit
DataFunSummit
Oct 6, 2025 · Artificial Intelligence

How Bilibili Leverages Large Language Models to Solve Big Data Platform Failures

This article explains Bilibili's massive video platform data architecture, the huge daily workload of offline and real‑time tasks, common user problems like task failures and slowdowns, their root causes, and how a large language model assistant is being used to automate troubleshooting.

AI assistanceBilibililarge language model
0 likes · 4 min read
How Bilibili Leverages Large Language Models to Solve Big Data Platform Failures
Fun with Large Models
Fun with Large Models
Sep 30, 2025 · Artificial Intelligence

DeepSeek-V3.2 Architecture Breakthrough: A 5‑Minute Guide to Its Core Features

The article introduces DeepSeek-V3.2, highlighting its new DeepSeek Sparse Attention (DSA) that boosts training and inference efficiency by up to 50%, cuts model usage costs dramatically, explains the updated API endpoints, and details the four‑stage post‑training pipeline that underpins the model’s performance improvements.

AI architectureDSADeepSeek-V3.2
0 likes · 8 min read
DeepSeek-V3.2 Architecture Breakthrough: A 5‑Minute Guide to Its Core Features
HyperAI Super Neural
HyperAI Super Neural
Sep 30, 2025 · Artificial Intelligence

SpikingBrain-1.0 Achieves 100× Faster Inference with Brain‑Inspired Spiking Architecture

SpikingBrain-1.0, the first domestically‑produced brain‑inspired spiking large model, links spiking neuron dynamics to linear attention, delivering over 100× faster first‑token latency on 4‑million‑token sequences, 23.4% FLOP utilization, 69% sparsity, and a one‑click deployment tutorial on HyperAI.

SpikingBrain-1.0brain-inspired AIinference speedup
0 likes · 7 min read
SpikingBrain-1.0 Achieves 100× Faster Inference with Brain‑Inspired Spiking Architecture
Alipay Experience Technology
Alipay Experience Technology
Sep 29, 2025 · Artificial Intelligence

How a Constraint-Aware Multi-Agent AI Won the IJCAI‑2025 Travel Planning Challenge

Alipay’s AI research team, together with Ant Group and East China Normal University, leveraged a self‑developed large‑model‑plus‑optimization framework to create a constraint‑aware multi‑agent system that won both the Original OS Track and DSL Track at the IJCAI‑2025 Autonomous Travel Itinerary Planning Competition.

AIMulti-agentOptimization
0 likes · 8 min read
How a Constraint-Aware Multi-Agent AI Won the IJCAI‑2025 Travel Planning Challenge
DataFunTalk
DataFunTalk
Sep 28, 2025 · Artificial Intelligence

How Bilibili Leverages Large Language Models to Automate Big Data Operations

This article explores Bilibili’s implementation of a large‑language‑model‑driven intelligent assistant that helps troubleshoot massive offline and real‑time data processing tasks, detailing the platform’s five‑layer architecture, common failure causes, and how AI can streamline issue resolution.

AI operationsBig Data PlatformIntelligent Assistant
0 likes · 4 min read
How Bilibili Leverages Large Language Models to Automate Big Data Operations
DataFunTalk
DataFunTalk
Sep 27, 2025 · Artificial Intelligence

Bilibili’s AI Assistant: Using Large Language Models to Tackle Massive Data Tasks

This article explains how Bilibili leverages a large‑language‑model‑based intelligent agent to diagnose and resolve failures and slowdowns in its massive big‑data platform, detailing the platform architecture, workload scale, common user issues, and the need for automated assistance.

AI operationsBig Data PlatformBilibili
0 likes · 5 min read
Bilibili’s AI Assistant: Using Large Language Models to Tackle Massive Data Tasks
Data Party THU
Data Party THU
Sep 26, 2025 · Artificial Intelligence

How Keye‑VL‑1.5 Redefines Video Understanding with Slow‑Fast Encoding

Keye‑VL‑1.5, an 8‑billion‑parameter multimodal large language model, introduces a Slow‑Fast video encoding strategy, a four‑stage progressive pre‑training pipeline with 128K context, and a sophisticated post‑training regime that together achieve state‑of‑the‑art performance on video and vision‑language benchmarks while maintaining strong general capabilities.

Video Understandingbenchmarklarge language model
0 likes · 21 min read
How Keye‑VL‑1.5 Redefines Video Understanding with Slow‑Fast Encoding
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Sep 25, 2025 · Artificial Intelligence

Unlocking Trillion‑Parameter MoE Models: Expert Parallelism and Alibaba Cloud PAI‑EAS Deployment Guide

This article explains the opportunities and challenges of Mixture of Experts (MoE) models, introduces expert parallelism as a solution to scaling and deployment bottlenecks, and provides a step‑by‑step guide for deploying MoE models with Alibaba Cloud PAI‑EAS, including configuration tips and code examples.

AI Model DeploymentExpert ParallelismMoE
0 likes · 11 min read
Unlocking Trillion‑Parameter MoE Models: Expert Parallelism and Alibaba Cloud PAI‑EAS Deployment Guide
DataFunSummit
DataFunSummit
Sep 25, 2025 · Artificial Intelligence

Can NL→MQL→SQL Bridge the Gap to End‑to‑End Intelligent BI?

Aloudata Agent introduces a novel NL→MQL→SQL framework that combines large language models with a custom metric query language, enabling business users to perform end‑to‑end intelligent data analysis, attribution, and reporting without technical expertise, while balancing accuracy, cost, and performance.

Intelligent BIMetric Query LanguageNL2SQL
0 likes · 18 min read
Can NL→MQL→SQL Bridge the Gap to End‑to‑End Intelligent BI?
Fighter's World
Fighter's World
Sep 24, 2025 · Artificial Intelligence

Aivis: Pioneering Autonomous Agents for Alibaba Cloud’s Next‑Gen Intelligent Services

The talk outlines how Alibaba Cloud’s Aivis autonomous service agent tackles the “impossible triangle” of ultra‑high experience, low cost, and complex services by evolving from tool‑based chatbots to teammate‑level agents, detailing a four‑layer architecture, domain‑model training, and actionable steps for enterprise AI service transformation.

AI AgentAgent ArchitectureCloud Service
0 likes · 14 min read
Aivis: Pioneering Autonomous Agents for Alibaba Cloud’s Next‑Gen Intelligent Services
AIWalker
AIWalker
Sep 23, 2025 · Artificial Intelligence

Manzano: A Small 3B Multimodal Model That Unifies Image Understanding and Generation with SOTA Performance

Manzano introduces a hybrid vision tokenizer and a three‑stage training recipe that let a 3‑billion‑parameter multimodal LLM achieve state‑of‑the‑art results on both image‑understanding benchmarks and text‑to‑image generation, while scaling smoothly to larger sizes and minimizing task conflict.

AI researchManzanohybrid tokenizer
0 likes · 25 min read
Manzano: A Small 3B Multimodal Model That Unifies Image Understanding and Generation with SOTA Performance
Meituan Technology Team
Meituan Technology Team
Sep 22, 2025 · Artificial Intelligence

LongCat-Flash-Thinking: The New SOTA Open-Source LLM for Deep Reasoning and Tool Use

Meituan’s LongCat team unveiled LongCat-Flash-Thinking, an open‑source large language model that combines deep logical reasoning with tool‑calling capabilities, achieving state‑of‑the‑art performance across logic, mathematics, code, and agentic tasks, and introducing novel training frameworks such as domain‑parallel RL and DORA.

AIbenchmarklarge language model
0 likes · 7 min read
LongCat-Flash-Thinking: The New SOTA Open-Source LLM for Deep Reasoning and Tool Use
Data Party THU
Data Party THU
Sep 20, 2025 · Artificial Intelligence

How DeepSeek Trained a $30M LLM for Just $29.4K – Inside the R1 Model

The article reports that DeepSeek’s R1 large language model, detailed in a peer‑reviewed Nature paper, was built with roughly $300 k in total cost—about $29.4 k for training—using Nvidia H800 chips and novel pure reinforcement‑learning techniques, achieving competitive performance while remaining open‑source.

DeepSeekModel training costNvidia H800
0 likes · 9 min read
How DeepSeek Trained a $30M LLM for Just $29.4K – Inside the R1 Model
DataFunTalk
DataFunTalk
Sep 18, 2025 · Artificial Intelligence

How DeepSeek‑R1’s Reinforcement Learning Earned a Nature Cover

DeepSeek‑R1, the first peer‑reviewed large language model, leveraged a pure reinforcement‑learning framework and the novel GRPO algorithm to achieve breakthrough reasoning performance, low training cost, and widespread acclaim, culminating in a Nature magazine cover story.

AI reasoningDeepSeekGRPO
0 likes · 14 min read
How DeepSeek‑R1’s Reinforcement Learning Earned a Nature Cover
DataFunSummit
DataFunSummit
Sep 17, 2025 · Artificial Intelligence

How Tencent’s Large Language Model Powers Real-World AI Applications

This article explores Tencent’s large language model across diverse business scenarios—content generation, intelligent customer service, role‑playing, and more—detailing the principles and practical uses of Retrieval‑Augmented Generation (RAG), GraphRAG, and Agent technologies, and how they enhance model intelligence and user experience.

AIAgentKnowledge Graph
0 likes · 4 min read
How Tencent’s Large Language Model Powers Real-World AI Applications
DataFunSummit
DataFunSummit
Sep 14, 2025 · Artificial Intelligence

How Tencent’s Large Language Models Boost Business with RAG, GraphRAG, and AI Agents

This article examines Tencent's large language model deployments across various business scenarios, detailing the use of Retrieval‑Augmented Generation, GraphRAG for role‑playing, and Agent technologies, while also outlining core application areas and the three main technical approaches—SFT, RAG, and Agents.

AI AgentsAI ApplicationsGraphRAG
0 likes · 4 min read
How Tencent’s Large Language Models Boost Business with RAG, GraphRAG, and AI Agents
Data Party THU
Data Party THU
Sep 13, 2025 · Artificial Intelligence

How a Multi‑Agent Large Model Transforms Ecological Big‑Data Analysis

This report details a university project that built a flexible, high‑performance multi‑agent large‑model framework for ecological environment big‑data analysis, covering system architecture, individual agents, memory mechanisms, report generation, a FastAPI‑LangGraph backend, a React frontend, testing methodology, and future directions.

AIBig DataFastAPI
0 likes · 7 min read
How a Multi‑Agent Large Model Transforms Ecological Big‑Data Analysis
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 11, 2025 · Artificial Intelligence

Fin-PRM: Alibaba’s Dianjin Team Introduces a Domain-Specific Process Reward Model for Financial Reasoning

Fin‑PRM, a domain‑specific process reward model for financial reasoning introduced by Alibaba’s Dianjin team, employs dual‑level step and trajectory rewards to provide fine‑grained supervision, achieving up to 12.9% accuracy gains in supervised fine‑tuning and 5.1% improvements in Best‑of‑N inference on benchmarks such as CFLUE and FinQA.

CFLUEFin-PRMFinQA
0 likes · 11 min read
Fin-PRM: Alibaba’s Dianjin Team Introduces a Domain-Specific Process Reward Model for Financial Reasoning
DataFunSummit
DataFunSummit
Sep 10, 2025 · Artificial Intelligence

Claude’s Exit from China: How Domestic AI Models Can Fill the Void

Anthropic’s new policy blocks Chinese‑controlled firms from using Claude and Claude Code, prompting a deep dive into the model’s strengths and exploring fast‑growing domestic AI alternatives—such as Qwen3‑Coder, GLM‑4.5, and others—to understand their capabilities, gaps, and future opportunities for Chinese developers.

AIChinese AIClaude
0 likes · 11 min read
Claude’s Exit from China: How Domestic AI Models Can Fill the Void
Eric Tech Circle
Eric Tech Circle
Sep 10, 2025 · Artificial Intelligence

Deploy High‑Performance Local LLMs with vLLM: A Step‑by‑Step Guide

This article walks through installing and configuring vLLM for local large language model inference, compares it with Ollama and LM Studio, details environment setup, model download, testing scripts, and shows how to expose an OpenAI‑compatible API for production use.

ModelScopeOpenAI APIPython
0 likes · 11 min read
Deploy High‑Performance Local LLMs with vLLM: A Step‑by‑Step Guide
Wuming AI
Wuming AI
Sep 6, 2025 · Artificial Intelligence

Can Qwen3-Max-Preview Outperform Claude? A Deep Dive into China’s New 1‑T LLM

The article reviews Alibaba's 1‑trillion‑parameter Qwen3‑Max‑Preview model, comparing its benchmark scores, hallucination rate, math and coding accuracy, and SVG generation quality against Claude, Kimi K2, and DeepSeek, while providing usage links and real‑world user impressions.

AI BenchmarkQwen3SVG generation
0 likes · 4 min read
Can Qwen3-Max-Preview Outperform Claude? A Deep Dive into China’s New 1‑T LLM
Kuaishou Tech
Kuaishou Tech
Sep 5, 2025 · Artificial Intelligence

How Keye‑VL‑1.5‑8B Sets New Benchmarks in Multimodal AI

Fast‑search platform Kwai has open‑sourced the 8‑billion‑parameter multimodal LLM Keye‑VL‑1.5, which introduces a slow‑fast frame encoding, a progressive four‑stage pre‑training pipeline, and an automated data construction workflow, achieving state‑of‑the‑art results on video and vision‑language benchmarks and surpassing many closed‑source models.

Multimodal AIVideo Understandingbenchmark performance
0 likes · 12 min read
How Keye‑VL‑1.5‑8B Sets New Benchmarks in Multimodal AI
Efficient Ops
Efficient Ops
Sep 2, 2025 · Artificial Intelligence

How AI Is Revolutionizing Knowledge‑Base Building for Smarter Operations

At the 27th GOPS Global Operations Conference in Shanghai (Oct 17‑18, 2025), Professor Wang Peng of Fudan University will reveal how large language models can extract and structure heterogeneous operational data into high‑quality knowledge bases, and how RAG‑driven Q&A enhances fault diagnosis, SOP generation, and automated decision‑making.

Artificial IntelligenceIntelligent OperationsRAG
0 likes · 3 min read
How AI Is Revolutionizing Knowledge‑Base Building for Smarter Operations
Baobao Algorithm Notes
Baobao Algorithm Notes
Sep 2, 2025 · Artificial Intelligence

How LongCat‑Flash Achieves Record Speed and Efficiency for a 560B MoE Model

LongCat‑Flash is a 560‑billion‑parameter Mixture‑of‑Experts LLM that combines a dynamic zero‑computation expert design, shortcut‑connected MoE communication, variance‑aligned scaling, and a three‑stage agent‑centric pre‑training pipeline, delivering over 100 TPS on H800 GPUs at a cost of $0.70 per million tokens.

Artificial IntelligenceLongCat-FlashMixture of Experts
0 likes · 23 min read
How LongCat‑Flash Achieves Record Speed and Efficiency for a 560B MoE Model
Java Tech Enthusiast
Java Tech Enthusiast
Sep 1, 2025 · Artificial Intelligence

How Meituan’s LongCat‑Flash‑Chat Beats Top LLMs with Zero‑Computation Experts

LongCat‑Flash‑Chat, Meituan’s newly open‑sourced 560B MoE model, outperforms leading LLMs on agent tool use and instruction following benchmarks, introduces zero‑computation experts and shortcut‑connected MoE for higher throughput, and demonstrates strong programming and reasoning abilities across diverse evaluation tasks.

Meituan AIZero Computation Expertsbenchmark performance
0 likes · 12 min read
How Meituan’s LongCat‑Flash‑Chat Beats Top LLMs with Zero‑Computation Experts
DataFunTalk
DataFunTalk
Sep 1, 2025 · Artificial Intelligence

Unlocking 560B‑Parameter AI: Inside LongCat‑Flash‑Chat’s Zero‑Computation MoE

LongCat‑Flash‑Chat, a 560‑billion‑parameter Mixture‑of‑Experts model with Zero‑Computation Experts, delivers top‑tier benchmark scores and fast inference while activating only a fraction of its parameters, and is fully open‑sourced with easy deployment scripts.

Artificial IntelligenceMixture of ExpertsModel deployment
0 likes · 6 min read
Unlocking 560B‑Parameter AI: Inside LongCat‑Flash‑Chat’s Zero‑Computation MoE
DataFunTalk
DataFunTalk
Aug 29, 2025 · Artificial Intelligence

Grok Code Fast 1: xAI’s New Coding Model 3× Faster, 6× Cheaper

Elon Musk’s xAI has launched Grok Code Fast 1, a new code‑generation model that claims to be three times faster and six times cheaper than GPT‑5, offering agentic programming capabilities, broad language support, free‑week trials on major IDE platforms, and competitive pricing with high cache hit rates.

AI code modelAgentic Programmingcoding efficiency
0 likes · 6 min read
Grok Code Fast 1: xAI’s New Coding Model 3× Faster, 6× Cheaper
DataFunTalk
DataFunTalk
Aug 26, 2025 · Artificial Intelligence

Exploring Cutting-Edge AI & Knowledge Graph Applications: A Curated Resource Guide

This resource guide presents a curated list of cutting‑edge topics—including multimodal GraphRAG, knowledge‑graph‑driven large‑model applications in finance, traditional Chinese medicine, automotive manufacturing, and knowledge‑management trends—offering insights into AI‑powered knowledge services, and invites readers to scan the QR code to download the full e‑book.

AIData IntegrationKnowledge Graph
0 likes · 2 min read
Exploring Cutting-Edge AI & Knowledge Graph Applications: A Curated Resource Guide
Alibaba Cloud Native
Alibaba Cloud Native
Aug 25, 2025 · Artificial Intelligence

How 1688 AI App Redefines B2B E‑commerce with AI‑Powered Search and Multimodal Interfaces

The article examines the design shift from the traditional 1688 App to the AI‑native 1688 AI App, detailing how AI‑driven interfaces, system prompts, embedding‑based retrieval, multi‑agent routing, and AI gateways transform B2B product discovery, recommendation, and customization.

AI SearchB2B e-commerceSystem Prompt Engineering
0 likes · 20 min read
How 1688 AI App Redefines B2B E‑commerce with AI‑Powered Search and Multimodal Interfaces
Baidu Geek Talk
Baidu Geek Talk
Aug 25, 2025 · Artificial Intelligence

How ERNIE‑4.5‑VL Redefines Multimodal AI with 100+ Language Support

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 researchERNIEMultimodal AI
0 likes · 4 min read
How ERNIE‑4.5‑VL Redefines Multimodal AI with 100+ Language Support
Data Party THU
Data Party THU
Aug 24, 2025 · Artificial Intelligence

Can a ‘Centaur’ AI Model Truly Predict Human Decisions? A Deep Dive

This article reviews the Centaur foundation model—fine‑tuned from Llama 3‑70B on the Psych‑101 dataset—to assess its ability to predict human choices, brain activity, and decision rationales across diverse psychological experiments, while discussing generalization, over‑fitting, and future research limits.

CentaurFoundation Modelcognitive modeling
0 likes · 17 min read
Can a ‘Centaur’ AI Model Truly Predict Human Decisions? A Deep Dive
Kuaishou Tech
Kuaishou Tech
Aug 23, 2025 · Artificial Intelligence

How Thyme Enables Models to Think Beyond Images with Code‑Driven Multimodal Reasoning

The Kwai Keye team presents Thyme, a novel multimodal reasoning framework that lets large language models generate and safely execute Python code for image manipulation and complex calculations, achieving significant performance gains over existing vision‑language models across perception, reasoning, and hallucination‑reduction benchmarks.

AI researchcode generationlarge language model
0 likes · 12 min read
How Thyme Enables Models to Think Beyond Images with Code‑Driven Multimodal Reasoning
Open Source Tech Hub
Open Source Tech Hub
Aug 22, 2025 · Artificial Intelligence

Automate User Feedback Classification with a Large‑Model API in PHP

This guide shows how to use the Tongyi Qianwen large‑model API with PHP to automatically classify user feedback into predefined categories, eliminating manual analysis and complex NLP development while providing clear steps, code, and result interpretation for rapid business insights.

APIAutomationPHP
0 likes · 7 min read
Automate User Feedback Classification with a Large‑Model API in PHP
AI Algorithm Path
AI Algorithm Path
Aug 20, 2025 · Artificial Intelligence

DeepSeek V3.1 Open‑Source: Unlocking a New Era of Long‑Context AI

DeepSeek V3.1, a 685‑billion‑parameter open‑source model, supports up to 128,000 tokens, delivers mixed‑architecture capabilities, matches top‑tier closed systems in benchmarks, and its rapid community adoption signals a shift toward democratized AI development and new industry dynamics.

AI performanceDeepSeeklarge language model
0 likes · 6 min read
DeepSeek V3.1 Open‑Source: Unlocking a New Era of Long‑Context AI
Fun with Large Models
Fun with Large Models
Aug 20, 2025 · Artificial Intelligence

DeepSeek V3.1 Review: 128K Context, Knowledge, Programming & Agent Skills Near Claude 4

DeepSeek V3.1, released on August 19, expands context length to 128 K tokens and updates its knowledge base to July 2024, and the author’s benchmarks show its programming and agent capabilities now rival Claude 4, with detailed prompt examples, code generation demos, and performance comparisons.

Agent EvaluationClaude 4Context Length
0 likes · 9 min read
DeepSeek V3.1 Review: 128K Context, Knowledge, Programming & Agent Skills Near Claude 4
Instant Consumer Technology Team
Instant Consumer Technology Team
Aug 15, 2025 · Artificial Intelligence

Master the iFLYTEK Prohibited Words Classification Challenge: Baselines & BERT

This article introduces the iFLYTEK AI Developer Competition on prohibited‑word classification, outlines the task, dataset, evaluation metric, and provides three baseline solutions—including a logistic‑regression model, a BERT fine‑tuning approach, and a large‑model prompt method—along with code snippets and performance notes.

BERTCompetitionLogistic Regression
0 likes · 15 min read
Master the iFLYTEK Prohibited Words Classification Challenge: Baselines & BERT
Data Party THU
Data Party THU
Aug 11, 2025 · Artificial Intelligence

What Makes GPT‑5 the Most Powerful AI Model Yet? A Deep Dive into Its Architecture and Benchmarks

The article analyzes GPT‑5’s unified system, advanced reasoning models, and impressive benchmark gains across programming, creative writing, and health domains, highlighting its new router, Verbosity API, and record‑setting performance on tasks such as Aider polyglot, AIME 2025, and HealthBench.

AI benchmarksAI reasoningGPT-5
0 likes · 7 min read
What Makes GPT‑5 the Most Powerful AI Model Yet? A Deep Dive into Its Architecture and Benchmarks
AI Algorithm Path
AI Algorithm Path
Aug 8, 2025 · Artificial Intelligence

GPT‑5 Is Here: In‑Depth Technical Walkthrough of Architecture, Features, and Benchmarks

OpenAI’s GPT‑5, released on August 7 2025, introduces a unified system with real‑time routing, up to 400 k token context windows, multiple model families, refined safety mechanisms, new API controls, and benchmark results that show it surpasses GPT‑4 across intelligence, coding, instruction following, function calling and multimodal tasks.

AI architectureAPIGPT-5
0 likes · 9 min read
GPT‑5 Is Here: In‑Depth Technical Walkthrough of Architecture, Features, and Benchmarks
AntTech
AntTech
Aug 6, 2025 · Artificial Intelligence

Ring-lite-2507: Boosted Deep Reasoning and Balanced General Capabilities

The AntBailing team releases Ring-lite-2507, enhancing deep reasoning through a Two‑staged RL pipeline while simultaneously balancing overall model abilities, showcasing notable gains on benchmarks like ARC‑AGI‑v1 and offering the model as an open‑source resource across major platforms.

RL TrainingRing-litedeep reasoning
0 likes · 5 min read
Ring-lite-2507: Boosted Deep Reasoning and Balanced General Capabilities
AI Info Trend
AI Info Trend
Aug 4, 2025 · Industry Insights

How AI Agents and Small Models Are Redefining Productivity in 2025 H1

The report analyzes first‑half‑2025 AI breakthroughs, covering the rise of general‑purpose agents, rapid inference improvements, small‑model proliferation, reinforcement‑learning compute dominance, evolving transformer architectures, and shifting industry dynamics, offering actionable insights for researchers, product leaders, and decision‑makers.

AIAgentindustry
0 likes · 9 min read
How AI Agents and Small Models Are Redefining Productivity in 2025 H1
Baobao Algorithm Notes
Baobao Algorithm Notes
Aug 1, 2025 · Artificial Intelligence

Unlocking Qwen3-Coder-30B: Features, Fast Start, and Agentic Coding Guide

The article introduces Qwen3‑Coder‑30B‑A3B‑Instruct (aka Qwen3‑Coder‑Flash), detailing its architecture, 256K‑to‑1M token context, agentic coding capabilities, installation steps with Transformers, sample code for tool use, optimal sampling parameters, and deployment tips across various runtimes.

AI coding assistantDeep LearningQwen3
0 likes · 6 min read
Unlocking Qwen3-Coder-30B: Features, Fast Start, and Agentic Coding Guide
Software Engineering 3.0 Era
Software Engineering 3.0 Era
Jul 31, 2025 · Fundamentals

Generating a Software Testing Knowledge Graph with a Large Language Model

The article recounts a 2016 hand‑crafted software testing panorama, then shows how the Claude 4 Sonnet Think model can automatically produce several versions of a software testing knowledge graph, analyzes its entity hierarchy and relationships, critiques gaps, and outlines future plans to store the graph in a database for enhanced testing education.

Claude 4 SonnetKnowledge Graphlarge language model
0 likes · 6 min read
Generating a Software Testing Knowledge Graph with a Large Language Model
AI Algorithm Path
AI Algorithm Path
Jul 29, 2025 · Artificial Intelligence

Why GLM‑4.5 Sets a New Benchmark for Open‑Source Large Language Models

GLM‑4.5 and its lightweight Air variant, featuring a deep‑layered MoE design, grouped‑query attention, and dual inference modes, achieve third‑place overall on 12 hard‑core benchmarks, excel in web‑browsing and tool‑calling with a 90.6 % success rate, and introduce novel training tricks such as the Muon optimizer and Slime RL framework.

AIGLM-4.5MoE
0 likes · 8 min read
Why GLM‑4.5 Sets a New Benchmark for Open‑Source Large Language Models
AntTech
AntTech
Jul 29, 2025 · Artificial Intelligence

How Ant Group’s Agentar‑Fin‑R1 Redefines Financial AI with Expert‑Level Reasoning

Ant Group’s Ant Financial Science released Agentar‑Fin‑R1, a finance‑focused large model that claims expert‑level knowledge, efficient training, and continuous self‑evolution, outperforming open‑source rivals on benchmarks like FinEval1.0, FinanceIQ and Finova, while supporting industry standards through a collaborative AI alliance.

Agentar-Fin-R1Ant GroupFinova benchmark
0 likes · 5 min read
How Ant Group’s Agentar‑Fin‑R1 Redefines Financial AI with Expert‑Level Reasoning
Model Perspective
Model Perspective
Jul 27, 2025 · Artificial Intelligence

Build a Practical AI Agent from Scratch with Coze’s Low‑Code Platform

This guide walks you through creating a functional AI agent using the Coze low‑code platform, covering account setup, goal definition, visual workflow design with large‑model and image‑generation nodes, variable configuration, testing, and publishing the agent to multiple channels.

AI AgentCozePrompt Engineering
0 likes · 10 min read
Build a Practical AI Agent from Scratch with Coze’s Low‑Code Platform
Architecture and Beyond
Architecture and Beyond
Jul 27, 2025 · Artificial Intelligence

What Makes an AI Agent Tick? From Expert Systems to Modern Architectures

This article traces the evolution of AI agents from early expert systems to today’s multimodal, memory‑rich agents, explains their perception, reasoning, memory and action modules, discusses model selection, prompt engineering, RAG techniques, and highlights current limitations such as hallucinations, reliability, cost, and security.

AI AgentFunction CallingMemory Architecture
0 likes · 28 min read
What Makes an AI Agent Tick? From Expert Systems to Modern Architectures
Zhihu Tech Column
Zhihu Tech Column
Jul 25, 2025 · Artificial Intelligence

Boost Creative Writing with Zhi-Create-Qwen3-32B: Training, Eval & Deployment

This article introduces the open‑source Zhi‑Create‑Qwen3‑32B model, detailing its fine‑tuned training on creative‑writing data, the multi‑domain dataset strategy, curriculum‑learning based SFT, evaluation on WritingBench, and practical deployment options across various hardware and inference frameworks.

Evaluationcreative writingdeployment
0 likes · 11 min read
Boost Creative Writing with Zhi-Create-Qwen3-32B: Training, Eval & Deployment
Fun with Large Models
Fun with Large Models
Jul 24, 2025 · Artificial Intelligence

Qwen3‑Coder vs Claude 4: In‑Depth Performance Review and Usage Guide

This article evaluates the open‑source Qwen3‑Coder‑480B‑A35B model, comparing its programming and agentic capabilities to Claude 4 and other leading models, detailing its architecture, token length, reinforcement‑learning‑after‑training technique, ecosystem tools, and real‑world code‑generation case studies.

AI codingQwen3-Coderagent RL
0 likes · 14 min read
Qwen3‑Coder vs Claude 4: In‑Depth Performance Review and Usage Guide
DataFunTalk
DataFunTalk
Jul 23, 2025 · Artificial Intelligence

Qwen3‑Coder: Open‑Source AI Programming Agent That Beats the Competition

Alibaba’s Tongyi team unveiled the open‑source Qwen3‑Coder, a massive 450‑billion‑parameter programming model that outperforms leading closed‑source solutions, supports up to 1 M token context, offers a free CLI tool, and demonstrates impressive code generation capabilities across animations, games, and real‑world tasks.

AI programmingQwen3-CoderYARN
0 likes · 5 min read
Qwen3‑Coder: Open‑Source AI Programming Agent That Beats the Competition
Kuaishou Tech
Kuaishou Tech
Jul 21, 2025 · Artificial Intelligence

Can AI Models Think on Demand? Inside KAT‑V1 AutoThink’s Dynamic Reasoning

The article introduces KAT‑V1 AutoThink, a dual‑mode large language model that automatically switches between thinking and non‑thinking modes based on problem difficulty, details its novel training paradigm, reinforcement‑learning enhancements, performance benchmarks against leading open‑source models, and provides open‑source resources for further research.

auto-thinkknowledge distillationlarge language model
0 likes · 14 min read
Can AI Models Think on Demand? Inside KAT‑V1 AutoThink’s Dynamic Reasoning
Alibaba Cloud Developer
Alibaba Cloud Developer
Jul 21, 2025 · Artificial Intelligence

How Browser‑Use Leverages AI Prompts for Seamless Browser Automation

This article explains how the open‑source browser‑use framework combines carefully designed SystemMessage prompts, structured HumanMessage inputs, and LangChain‑driven tool calls to enable large language models to automate complex web tasks such as shopping, CRM updates, résumé processing, and document generation, while providing concrete code examples and best‑practice tips.

AI automationLangChainPrompt Engineering
0 likes · 21 min read
How Browser‑Use Leverages AI Prompts for Seamless Browser Automation
Architect's Alchemy Furnace
Architect's Alchemy Furnace
Jul 17, 2025 · Artificial Intelligence

Explore the Ultimate Open-Source LLM Catalog: Models, Tools, and Resources

This article compiles a comprehensive, up‑to‑date inventory of open‑source large language models from Chinese and international organizations, detailing each model’s architecture, parameter count, multilingual capabilities, deployment requirements, and associated tools, offering a valuable reference for AI researchers and developers.

AILLMlarge language model
0 likes · 50 min read
Explore the Ultimate Open-Source LLM Catalog: Models, Tools, and Resources
AntTech
AntTech
Jul 17, 2025 · Artificial Intelligence

How M2-Reasoning-7B Achieves State‑of‑the‑Art Spatial Reasoning in Multimodal AI

M2-Reasoning-7B, an open‑source 7B multimodal model from Ant Group, combines a high‑quality data pipeline with dynamic multi‑task training and a novel reward function to deliver state‑of‑the‑art performance on both general and spatial reasoning benchmarks, surpassing many larger competitors.

M2-ReasoningMultimodal AIbenchmark
0 likes · 9 min read
How M2-Reasoning-7B Achieves State‑of‑the‑Art Spatial Reasoning in Multimodal AI
Ubiquitous Tech
Ubiquitous Tech
Jul 14, 2025 · Artificial Intelligence

How to Craft Human‑like RAG Prompts for AI Customer Service

This article explains why prompt engineering is essential for turning large‑language‑model‑driven chatbots into empathetic assistants, outlines a 5W1H framework for designing structured prompts, provides concrete travel‑assistant examples, and shares practical techniques and tools such as Prompt Optimizer to improve RAG reliability.

AI Customer ServiceAI toolsPrompt Engineering
0 likes · 25 min read
How to Craft Human‑like RAG Prompts for AI Customer Service
AI Algorithm Path
AI Algorithm Path
Jul 14, 2025 · Artificial Intelligence

The Most Powerful Open‑Source Agent Model: Kimi K2

Kimi K2, an open‑source trillion‑parameter AI model released by Moonshot AI, offers Base and Instruct variants, achieves leading scores on benchmarks such as SWE‑bench, LiveCodeBench and AceBench, and introduces a novel post‑training autonomous‑exploration stage with MuonClip optimization to enable robust tool use and reinforcement‑learning‑driven self‑improvement.

Autonomous AgentsKimi K2benchmark performance
0 likes · 8 min read
The Most Powerful Open‑Source Agent Model: Kimi K2
Architecture and Beyond
Architecture and Beyond
Jul 12, 2025 · Artificial Intelligence

What Exactly Is an AI Agent? History, Architecture, and Future Challenges

This article traces the evolution of AI agents from early expert systems to modern large‑language‑model‑driven assistants, explains their core perception, reasoning, memory, and action modules, compares thinking and execution models, and discusses current limitations such as hallucinations, reliability, cost, and security.

AI AgentMemory ArchitecturePrompt Engineering
0 likes · 20 min read
What Exactly Is an AI Agent? History, Architecture, and Future Challenges
Subtle Storm
Subtle Storm
Jul 10, 2025 · Artificial Intelligence

How User, Assistant, and System Roles Shape Large Language Model Interactions

The article explains the three core roles—user, assistant, and system—in large language model conversations, detailing their definitions, functions, characteristics, and how proper role prompting clarifies dialogue structure, controls AI behavior, and improves task handling, illustrated with JSON examples and a full simulated exchange.

AI conversationPrompt Engineeringlarge language model
0 likes · 6 min read
How User, Assistant, and System Roles Shape Large Language Model Interactions
Data Thinking Notes
Data Thinking Notes
Jul 8, 2025 · Artificial Intelligence

How Xiaohongshu Leverages Large Models to Revolutionize Content Recommendation

This article details Xiaohongshu's multi‑stage recommendation pipeline—using massive multi‑modal pre‑training, long‑sequence modeling, real‑time context features, reinforcement learning and online deep learning—to precisely surface valuable content, address cold‑start challenges, and break information bubbles for billions of users.

large language modelmultimodal learningonline deep learning
0 likes · 16 min read
How Xiaohongshu Leverages Large Models to Revolutionize Content Recommendation
JD Tech Talk
JD Tech Talk
Jul 8, 2025 · Artificial Intelligence

How AI Can Turn a Code Maze into a Knowledge Highway for New Developers

New developer Li Ming’s frustrating onboarding experience highlights hidden business rules, undocumented code, and poor knowledge transfer, prompting him to build an AI‑driven knowledge base that links code changes, requirements, and operational docs, ultimately streamlining troubleshooting, accelerating feature development, and improving knowledge retention across teams.

AIKnowledge ManagementRAG
0 likes · 18 min read
How AI Can Turn a Code Maze into a Knowledge Highway for New Developers
DataFunSummit
DataFunSummit
Jul 6, 2025 · Artificial Intelligence

AI-Driven Knowledge Graphs: Key Insights from Multimodal GraphRAG Research

This article presents a comprehensive overview of cutting‑edge research on integrating large language models with knowledge graphs, covering multimodal GraphRAG, financial AI solutions, traditional Chinese medicine decision support, and industry‑specific knowledge services, guiding readers through emerging paradigms and practical implementations.

AIEnterprise AIKnowledge Graph
0 likes · 2 min read
AI-Driven Knowledge Graphs: Key Insights from Multimodal GraphRAG Research
DataFunTalk
DataFunTalk
Jul 5, 2025 · Artificial Intelligence

DeepSeek R1T2 Chimera: Faster, High‑Performance LLM with Assembly of Experts

The DeepSeek R1T2 Chimera model, an open‑source LLM built with Assembly of Experts technology, delivers up to 200% faster inference than R1‑0528, surpasses R1 on GPQA‑Diamond and AIME‑24 benchmarks, and offers a 671‑billion‑parameter MoE architecture, though it lacks function‑calling support and trails the highest‑end R1‑0528 on the toughest tests.

AIAssembly of ExpertsDeepSeek
0 likes · 5 min read
DeepSeek R1T2 Chimera: Faster, High‑Performance LLM with Assembly of Experts
DataFunTalk
DataFunTalk
Jul 3, 2025 · Artificial Intelligence

Inside xAI’s Grok 4: Massive Funding, Extreme Iteration, and Power Challenges

Elon Musk’s xAI has quietly leaked its upcoming Grok 4 and Grok 4 Code models, skipped Grok 3.5, secured $10 billion in new financing, and is building massive GPU super‑computing facilities, while raising concerns about model bias, data integrity, and unprecedented power‑grid strain.

AI fundingArtificial IntelligenceGPU computing
0 likes · 6 min read
Inside xAI’s Grok 4: Massive Funding, Extreme Iteration, and Power Challenges
DataFunSummit
DataFunSummit
Jul 2, 2025 · Artificial Intelligence

How End-to-End Reinforcement Learning Powers the Kimi Researcher AI Agent

The article explains how Kimi Researcher, an AI Agent built with end‑to‑end reinforcement learning, achieves state‑of‑the‑art performance on the Humanity’s Last Exam benchmark, scales via data‑driven training, and supports diverse research and analysis scenarios.

AI AgentKimi ResearcherResearch Automation
0 likes · 9 min read
How End-to-End Reinforcement Learning Powers the Kimi Researcher AI Agent
Baobao Algorithm Notes
Baobao Algorithm Notes
Jun 30, 2025 · Artificial Intelligence

How End‑to‑End Reinforcement Learning Powers the Kimi‑Researcher AI Agent

The article examines Kimi‑Researcher, an AI research agent built with end‑to‑end reinforcement learning, detailing its technical motivations, advantages over traditional workflow‑based and SFT methods, performance breakthroughs on benchmark exams, and diverse real‑world use cases ranging from literature reviews to legal analysis.

AI AgentEnd-to-End RLKimi Researcher
0 likes · 10 min read
How End‑to‑End Reinforcement Learning Powers the Kimi‑Researcher AI Agent
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jun 29, 2025 · Artificial Intelligence

Multimodal AI Assistant Boosts Network Config: 96.6% Accuracy, 26× Labor Cut

The paper presents NLI2Conf, an intent‑driven network configuration model that fuses configuration files, topology and performance data via a multimodal interface, using large language and graph neural models to align natural‑language intents with forwarding and performance constraints, achieving 96.6% accuracy and a 26‑fold reduction in manual effort.

Graph Neural NetworkMultimodal AINLI2Conf
0 likes · 6 min read
Multimodal AI Assistant Boosts Network Config: 96.6% Accuracy, 26× Labor Cut
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jun 27, 2025 · Artificial Intelligence

Build a Powerful AI Search RAG Application with PAI‑LangStudio, Qwen3 & Elasticsearch

This guide walks you through using the PAI‑LangStudio platform together with the Qwen3 large language model and Elasticsearch to create a full‑stack AI Search RAG solution, covering prerequisites, step‑by‑step configuration of model services, database connections, runtimes, knowledge bases, workflow creation, testing, and deployment for production use.

AI SearchElasticsearchPAI‑LangStudio
0 likes · 11 min read
Build a Powerful AI Search RAG Application with PAI‑LangStudio, Qwen3 & Elasticsearch
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 25, 2025 · Cloud Computing

Control Alibaba Cloud Resources with LLMs and MCP Server in Minutes

This article explains how to combine Alibaba Cloud's MCP Server with large language models to enable natural‑language operations on cloud products, covering setup, tool selection, OAuth authentication, code examples, troubleshooting context‑length limits, and future enhancements for more efficient, secure cloud management.

API IntegrationCloud ComputingMCP
0 likes · 20 min read
Control Alibaba Cloud Resources with LLMs and MCP Server in Minutes
Instant Consumer Technology Team
Instant Consumer Technology Team
Jun 23, 2025 · Artificial Intelligence

What Are AI Agents? Architecture, Applications, and Future Trends

AI Agents, autonomous intelligent programs that perceive, reason, and act, are reshaping industries from healthcare to autonomous driving; this article explains their core components, differences from large language models, planning techniques, memory mechanisms, tool use, real‑world applications, current challenges, and future directions.

AI AgentApplicationsMemory
0 likes · 35 min read
What Are AI Agents? Architecture, Applications, and Future Trends
Instant Consumer Technology Team
Instant Consumer Technology Team
Jun 19, 2025 · Artificial Intelligence

Exploring II-Agent: An Open‑Source AI Agent Framework for Multi‑Domain Automation

II-Agent is an open‑source, multi‑domain AI agent framework that leverages powerful large language models, a rich toolset, planning‑and‑reflection mechanisms, and advanced context management to enable autonomous task execution, real‑time interaction, and seamless integration across development, data analysis, and enterprise workflows.

AI AgentAutomationTool integration
0 likes · 21 min read
Exploring II-Agent: An Open‑Source AI Agent Framework for Multi‑Domain Automation
ByteDance Data Platform
ByteDance Data Platform
Jun 18, 2025 · Artificial Intelligence

How Imperfect AI Can Unlock the Hidden 80% of Enterprise Data

Enterprises face a sharp paradox: despite exploding data volumes, only about 20% of structured data is used while the remaining 80% of unstructured data stays frozen, and this talk explores how Data Agent‑powered imperfect AI can awaken that hidden value.

AIData AgentEnterprise AI
0 likes · 16 min read
How Imperfect AI Can Unlock the Hidden 80% of Enterprise Data
JD Tech
JD Tech
Jun 16, 2025 · Artificial Intelligence

How JD Engineers Leverage LLMs and Sparse Models to Boost Search and Ads

This article showcases three JD tech case studies—using large language models for e‑commerce query expansion, applying sparse large models with scaling‑law experiments to improve ad prediction, and building proactive risk‑prevention systems—to illustrate practical AI engineering that drives higher recall, conversion, and system robustness.

AdvertisingE‑commerceQuery Expansion
0 likes · 8 min read
How JD Engineers Leverage LLMs and Sparse Models to Boost Search and Ads
TAL Education Technology
TAL Education Technology
Jun 13, 2025 · Operations

How Large Language Models Are Revolutionizing Fault Localization

This article explores how the rapid rise of large language models and techniques like Retrieval‑Augmented Generation, Chain‑of‑Thought prompting, and multi‑agent architectures can dramatically improve the speed, accuracy, and automation of fault localization in modern operations environments.

Agent ArchitectureCoTFault Localization
0 likes · 14 min read
How Large Language Models Are Revolutionizing Fault Localization
Nightwalker Tech
Nightwalker Tech
Jun 11, 2025 · Artificial Intelligence

Turn Your AI Coding Assistant into a Critical Mentor, Not Just a Tool

This guide explains how to shift AI coding tools like Cursor, Windsurf, and RooCode from simple code generators into proactive mentors that critique, suggest improvements, and adopt multiple specialized modes, while also covering prompt design, multi‑round dialogue, and practical code examples.

AIPrompt Engineeringcoding assistant
0 likes · 15 min read
Turn Your AI Coding Assistant into a Critical Mentor, Not Just a Tool
DataFunSummit
DataFunSummit
Jun 10, 2025 · Artificial Intelligence

How Quwan’s Kaitian Model Tackles Emotional AI for Social Apps – Architecture, Training Tricks, and Safety

Quwan Technology presents its Kaitian social large model, designed for personalized, emotionally rich, multimodal AI interactions, detailing its scene‑specific goals, CPT+SFT+RLHF training pipeline, data desensitization, LoRA fine‑tuning, evaluation methods, pruning, latency trade‑offs, safety mechanisms, and future feedback loops.

AI safetyLoRAModel Pruning
0 likes · 13 min read
How Quwan’s Kaitian Model Tackles Emotional AI for Social Apps – Architecture, Training Tricks, and Safety
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Jun 6, 2025 · Artificial Intelligence

How dots.llm1 Sets New Benchmarks for Open‑Source MoE Language Models

dots.llm1, an open‑source 142‑billion‑parameter Mixture‑of‑Experts language model from hi lab, achieves Qwen2.5‑72B‑level performance after training on 11.2 T high‑quality tokens, and the release includes full models, intermediate checkpoints, and detailed training pipelines for the research community.

AI researchMixture of Expertslarge language model
0 likes · 10 min read
How dots.llm1 Sets New Benchmarks for Open‑Source MoE Language Models
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 5, 2025 · Artificial Intelligence

How Deep (Re)Search Transforms Code Search and AI-Powered Knowledge Retrieval

This article systematically explains the concepts of Deep Search and Deep Research, contrasts them with traditional Retrieval‑Augmented Generation, reviews leading commercial and open‑source solutions, details their architecture for code retrieval, and outlines future plans for specialized code‑search agents.

AI researchCode searchDeep Search
0 likes · 13 min read
How Deep (Re)Search Transforms Code Search and AI-Powered Knowledge Retrieval
Java Web Project
Java Web Project
Jun 4, 2025 · Artificial Intelligence

Why DeepSeek V3 Stands Out: Architecture, Performance, and Open‑Source Edge

The article analyzes DeepSeek's rapid adoption, detailing its seven core models, the third‑generation MoE architecture, FP8 mixed‑precision training, 128K context window, benchmark superiority on MMLU/HumanEval/CMMLU, low training cost, and fully open‑source release, while also introducing a companion guide for developers.

AI architectureDeepSeekFP8 training
0 likes · 9 min read
Why DeepSeek V3 Stands Out: Architecture, Performance, and Open‑Source Edge
Kuaishou Tech
Kuaishou Tech
Jun 4, 2025 · Artificial Intelligence

KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning

The KwaiPilot team released the KwaiCoder‑AutoThink‑preview model, which introduces a novel automatic‑thinking training paradigm and a process‑supervised reinforcement‑learning method called Step‑SRPO, enabling the model to dynamically switch between thinking and non‑thinking modes, reduce inference cost, and achieve up to 20‑point gains on code and math benchmarks while handling large‑scale codebases.

AI researchModel Optimizationautomatic thinking
0 likes · 12 min read
KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning
AI Frontier Lectures
AI Frontier Lectures
May 30, 2025 · Artificial Intelligence

Can a 5% Parameter LLM Rival Full‑Scale Models? Inside FairyR1‑32B

The Beijing University team unveils FairyR1‑32B, a 32‑billion‑parameter LLM built on DeepSeek‑R1‑Distill‑Qwen‑32B that uses self‑merging, multi‑teacher cross‑distillation, and lightweight distillation to achieve competitive math and code benchmark scores with only about 5% of the original model’s parameters.

distillationlarge language modelmodel compression
0 likes · 6 min read
Can a 5% Parameter LLM Rival Full‑Scale Models? Inside FairyR1‑32B
Efficient Ops
Efficient Ops
May 29, 2025 · Artificial Intelligence

DeepSeek R1 0528 Update: New Features, Performance Gains Over OpenAI o3

DeepSeek quietly launched the R1 0528 model, which early testers report matches OpenAI’s o3 in benchmarks and style, while adding deeper chain‑of‑thought reasoning, better writing output, and extended thinking windows, and the announcement is followed by a promotion for the GOPS Global Ops Conference.

AI performanceChain-of-ThoughtDeepSeek
0 likes · 3 min read
DeepSeek R1 0528 Update: New Features, Performance Gains Over OpenAI o3