BestHub
Sign in
Tagged articles

large language model

831 articles · Page 4 of 9
Baobao Algorithm Notes
Baobao Algorithm Notes
Feb 25, 2026 · Artificial Intelligence

Exploring Qwen 3.5: Small‑Scale MoE Models, Architecture, and Deployment Guides

This article reviews the three open‑source Qwen 3.5 models—including a 35B MoE, a 122B MoE, and a 27B dense version—detailing their parameter layouts, core attention designs, context length, inference performance, hardware requirements, and provides step‑by‑step code examples for loading them with Hugging Face Transformers and vLLM.

AIMoEModel deployment
0 likes · 10 min read
Exploring Qwen 3.5: Small‑Scale MoE Models, Architecture, and Deployment Guides
Yunqi AI+
Yunqi AI+
Feb 25, 2026 · Artificial Intelligence

How Our In-House AI Agent Scaled to Handle 70% of Tech Support: A Six-Month Review

Over six months the team built an AI agent that now answers more than 70% of technical support queries by grounding responses in system data, a curated knowledge base, and a tiered permission model, while also exposing growing technical debt and maintenance challenges.

AI AgentOperational AIPrompt Engineering
0 likes · 7 min read
How Our In-House AI Agent Scaled to Handle 70% of Tech Support: A Six-Month Review
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 20, 2026 · Artificial Intelligence

Google Reclaims AI Throne with Gemini 3.1 Pro, Achieving 77.1% ARC‑AGI‑2 Score

Google’s Gemini 3.1 Pro, the latest upgrade to the Gemini 3 series, achieves a verified 77.1 % score on the ARC‑AGI‑2 reasoning benchmark—more than double the performance of Gemini 3 Pro—while leading in GPQA, LiveCodeBench Pro, SWE‑Bench Verified, and MMMLU tests, and is now being rolled out to developers, enterprises and consumers with detailed pricing and integration options.

AI benchmarkingARC-AGI-2Gemini 3.1 Pro
0 likes · 9 min read
Google Reclaims AI Throne with Gemini 3.1 Pro, Achieving 77.1% ARC‑AGI‑2 Score
Old Zhang's AI Learning
Old Zhang's AI Learning
Feb 19, 2026 · Artificial Intelligence

Inside GLM-5: Training Techniques, Architecture Innovations, and Benchmark Performance

The article dissects GLM-5’s 744B‑parameter MoE design, 28.5 T token training corpus, novel Muon Split and MLA‑256 optimizations, DSA sparse attention, a fully asynchronous RL pipeline, extensive domestic chip adaptation, and benchmark results that place it on par with Claude Opus 4.5 and ahead of Gemini 3 Pro.

AI architectureAgentic RLDSA
0 likes · 13 min read
Inside GLM-5: Training Techniques, Architecture Innovations, and Benchmark Performance
AI Agent Research Hub
AI Agent Research Hub
Feb 19, 2026 · Artificial Intelligence

Why Claude Sonnet 4.6 Is My Most Powerful and Cost‑Effective AI Research Assistant

The article evaluates Anthropic's Claude Sonnet 4.6 as a comprehensive research assistant, detailing its performance on literature surveys, open‑source code analysis, algorithm implementation, cost savings, benchmark scores, and practical limitations across multiple scientific workflows.

AI research assistantClaude Sonnet 4.6benchmark
0 likes · 20 min read
Why Claude Sonnet 4.6 Is My Most Powerful and Cost‑Effective AI Research Assistant
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Feb 17, 2026 · Artificial Intelligence

Deploy Alibaba’s Qwen3.5‑397B‑A17B Model in One Click with PAI‑Model Gallery

Alibaba's open‑source Qwen3.5‑397B‑A17B model, featuring 397 billion parameters and a hybrid Gated Delta Network/MoE architecture, delivers superior performance and reduced memory usage, and can be deployed instantly through the PAI‑Model Gallery with step‑by‑step guidance and enterprise‑grade security.

AI InferenceAlibaba CloudOne-click deployment
0 likes · 5 min read
Deploy Alibaba’s Qwen3.5‑397B‑A17B Model in One Click with PAI‑Model Gallery
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 16, 2026 · Artificial Intelligence

Alibaba’s Qwen 3.5‑Plus: 397 B Open‑Source Model Beats Gemini‑3 and GPT‑5.2 at Low Cost

Alibaba released the Qwen 3.5‑Plus open‑source large model (397 B total parameters, 170 B active) that outperforms top closed‑source models such as Gemini‑3‑Pro and GPT‑5.2 on multiple benchmarks, offers native multimodal understanding, supports 201 languages, reduces deployment memory by 60 % and inference latency by up to 19×, and is priced at only 0.8 CNY per million tokens.

AIQwen3.5benchmark
0 likes · 15 min read
Alibaba’s Qwen 3.5‑Plus: 397 B Open‑Source Model Beats Gemini‑3 and GPT‑5.2 at Low Cost
Old Zhang's AI Learning
Old Zhang's AI Learning
Feb 16, 2026 · Artificial Intelligence

Qwen3.5 Deep Dive: Multimodal Architecture, Benchmarks, and Deployment Guide

This article provides a detailed analysis of Qwen3.5, covering its multimodal MoE design, massive inference speedups, extensive benchmark results against GPT‑5.2, Claude 4.5 Opus and Gemini‑3 Pro, RL scaling strategies, training infrastructure innovations, and practical usage via API and local deployment.

FP8 trainingMultimodal AIQwen3.5
0 likes · 13 min read
Qwen3.5 Deep Dive: Multimodal Architecture, Benchmarks, and Deployment Guide
AntTech
AntTech
Feb 16, 2026 · Artificial Intelligence

Ling‑2.5‑1T: Open‑Source 1‑Trillion‑Parameter Instant LLM with 1M‑Token Context

Ling‑2.5‑1T is an open‑source instant large language model with 1 trillion total parameters, 63 B active weights, and a 1 M token context window, featuring mixed‑linear attention, a composite correctness‑plus‑process reward for token efficiency, fine‑grained alignment, and leading benchmark performance across reasoning, instruction‑following, and agentic tasks.

Token efficiencyagentic interactionbenchmark
0 likes · 13 min read
Ling‑2.5‑1T: Open‑Source 1‑Trillion‑Parameter Instant LLM with 1M‑Token Context
AI Engineering
AI Engineering
Feb 16, 2026 · Artificial Intelligence

Qwen3.5-397B: 397B‑Parameter Multimodal LLM Boosts Inference Speed 8‑19×

Alibaba’s Qwen3.5-397B-A17B, a 397‑billion‑parameter open‑source multimodal LLM, combines mixed linear attention with a sparse MoE architecture to achieve 8.6‑19× higher decoding throughput than Qwen3‑Max, supports 201 languages, and can be deployed via vLLM, Docker, Transformers, or SGLang with various optimization presets.

Qwen3.5Sparse MoEinference optimization
0 likes · 8 min read
Qwen3.5-397B: 397B‑Parameter Multimodal LLM Boosts Inference Speed 8‑19×
AI Insight Log
AI Insight Log
Feb 16, 2026 · Artificial Intelligence

DeepSeek V4 Benchmark Leak Fuels Talk of a New Coding King

A leaked SWE‑Bench score of 83.7% for DeepSeek V4 sparked claims it outperforms Claude Opus 4.5 and GPT‑5.2, but the data was later debunked as fabricated while official hints confirm a 1‑million‑token context model and a mid‑February 2026 release.

AI benchmarkingAI industryContext Length
0 likes · 7 min read
DeepSeek V4 Benchmark Leak Fuels Talk of a New Coding King
PaperAgent
PaperAgent
Feb 16, 2026 · Artificial Intelligence

Why Qwen3.5-Plus Sets a New Standard for Open-Source Multimodal AI

Qwen3.5-Plus, Alibaba’s newly open-sourced multimodal LLM, combines a 397 B parameter model with only 17 B active parameters, leveraging native multimodal training, gated attention, sparse MoE, and FP8 precision to outperform GPT-5.2 and Gemini-3-Pro across vision, reasoning, and agent benchmarks.

Multimodal AIgated attentionlarge language model
0 likes · 6 min read
Why Qwen3.5-Plus Sets a New Standard for Open-Source Multimodal AI
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 12, 2026 · Artificial Intelligence

How Huawei’s MindScale Cuts Agent Token Usage 5.7× and Automates Prompt & Workflow Design

The article outlines the four major obstacles hindering industry‑specific LLM agents—manual workflow maintenance, poor knowledge reuse, training‑inference inefficiency, and complex reasoning evaluation—and explains how Huawei Noah’s MindScale package tackles each with self‑evolving workflows, automated prompt optimization, and a novel KV‑Embedding cache that slashes token consumption by 5.7× while boosting inference speed up to 70%.

Industry AgentInference AccelerationKV-Embedding
0 likes · 7 min read
How Huawei’s MindScale Cuts Agent Token Usage 5.7× and Automates Prompt & Workflow Design
Old Zhang's AI Learning
Old Zhang's AI Learning
Feb 12, 2026 · Artificial Intelligence

Testing the World's Most Powerful Open‑Source LLM: GLM‑5, Local Deployment & Free Ollama Cloud

The article evaluates GLM‑5, the claimed strongest open‑source large language model, comparing its benchmark scores to Claude Opus, Gemini and GPT, detailing its DeepSeek‑inspired architecture, quantized FP8 deployment requirements, and step‑by‑step usage of Ollama’s free cloud model with Agent, data‑analysis and document‑generation features.

AI benchmarkingAgent modeGLM-5
0 likes · 7 min read
Testing the World's Most Powerful Open‑Source LLM: GLM‑5, Local Deployment & Free Ollama Cloud
DataFunTalk
DataFunTalk
Feb 12, 2026 · Artificial Intelligence

DeepSeek’s New Model V4? Exploring 1M‑Token Context and Updated Knowledge

DeepSeek quietly launched its latest model, reportedly supporting up to 1 million tokens, extending its knowledge cutoff to May 2025, adopting a more enthusiastic response style, and still operating as a pure‑text system, while early tests showcase impressive coding and reasoning capabilities.

AI evaluationDeepSeekknowledge cutoff
0 likes · 5 min read
DeepSeek’s New Model V4? Exploring 1M‑Token Context and Updated Knowledge
AI Insight Log
AI Insight Log
Feb 12, 2026 · Artificial Intelligence

GLM-5 Unveiled: 744B Parameters, Claude Opus 4.5‑Level Performance, Epic Agent Upgrade

Z.ai released the open‑source GLM‑5 model with 744 billion parameters, 28.5 T tokens of training data, and new Sparse Attention and Slime RL infrastructure, achieving top open‑source rankings and near‑Claude Opus 4.5 performance on Vending Bench 2 and CC‑Bench‑V2 while adding multi‑scenario agent capabilities.

Agentic EngineeringGLM-5Sparse attention
0 likes · 6 min read
GLM-5 Unveiled: 744B Parameters, Claude Opus 4.5‑Level Performance, Epic Agent Upgrade
PMTalk Product Manager Community
PMTalk Product Manager Community
Feb 12, 2026 · Industry Insights

How AI Can Transform Government Services: A From‑Zero‑to‑One Case Study

The article analyzes why traditional government portals fail users, outlines a six‑step user journey (search, guide, ask, appointment, processing, evaluation), and shows how large‑language‑model AI can be embedded at each decision point to turn fragmented services into a seamless, user‑centric digital experience.

AIcase studydigital transformation
0 likes · 11 min read
How AI Can Transform Government Services: A From‑Zero‑to‑One Case Study
AI Engineering
AI Engineering
Feb 12, 2026 · Artificial Intelligence

GLM-5 Unveiled: 744B‑Parameter Model Takes on Claude in Complex Tasks

GLM-5, the new 744‑billion‑parameter open‑source LLM, expands on GLM‑4.5 with GlmMoeDsa architecture, achieves higher HLE benchmark scores than Claude Opus 4.5, demonstrates strong long‑context and agent capabilities, supports vLLM/SGLang, runs on various Chinese chips, and can directly generate Office documents.

AI benchmarksChinese chipsClaude
0 likes · 5 min read
GLM-5 Unveiled: 744B‑Parameter Model Takes on Claude in Complex Tasks
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 10, 2026 · Artificial Intelligence

Inside GLM-5: 745B Parameters, DeepSeek‑style Sparse Attention, and a 60% Stock Surge

The GLM-5 architecture, uncovered from a GitHub PR, doubles the previous model to 745 B parameters, adopts DeepSeek‑V3 sparse attention and multi‑token prediction, features a 78‑layer MoE with 256 experts, supports a 202K‑token context window, and its rumored test model "Pony Alpha" sparked a 60% rise in Zhipu AI's stock amid a crowded AI release season.

AI Stock ImpactDeepSeekGLM-5
0 likes · 6 min read
Inside GLM-5: 745B Parameters, DeepSeek‑style Sparse Attention, and a 60% Stock Surge
HyperAI Super Neural
HyperAI Super Neural
Feb 10, 2026 · Artificial Intelligence

WeDLM Diffusion Language Model Tutorial: 3× Faster Inference Than vLLM AR Models

The Tencent WeChat AI team introduces WeDLM, a diffusion language model that, through topological reordering, surpasses autoregressive models on the industrial‑grade vLLM engine with over threefold speedup on math reasoning and up to tenfold in low‑entropy scenarios, and provides a step‑by‑step online tutorial with GPU compute credits.

GPU ComputeInference AccelerationTencent AI
0 likes · 5 min read
WeDLM Diffusion Language Model Tutorial: 3× Faster Inference Than vLLM AR Models
Old Zhang's AI Learning
Old Zhang's AI Learning
Feb 9, 2026 · Artificial Intelligence

GLM-5 Emerges First, Built on DeepSeek Tech, Triggering a 40% Stock Surge

An anonymous OpenRouter model dubbed "Pony Alpha" was verified as the new 745B‑parameter GLM-5, which reuses DeepSeek‑V3 architecture, supports sparse attention and multi‑token prediction, and has already caused a near‑40% jump in Zhipu AI’s stock while hinting at upcoming integration into the Transformers library.

DeepSeekGLM-5MoE
0 likes · 3 min read
GLM-5 Emerges First, Built on DeepSeek Tech, Triggering a 40% Stock Surge
AI Insight Log
AI Insight Log
Feb 5, 2026 · Artificial Intelligence

How 16 Claude Agents Burned $140K to Build a C Compiler in Opus 4.6

Anthropic’s midnight release of Claude Opus 4.6 showcased a $140,000 “stress test” where 16 Claude agents collaboratively wrote a Linux‑compatible C compiler, achieving a 100‑k‑line Rust codebase, while the model also added deep Excel/PPT integration and lifted finance benchmark scores by up to 23 percentage points.

AI code generationAgentic workflowClaude Opus
0 likes · 7 min read
How 16 Claude Agents Burned $140K to Build a C Compiler in Opus 4.6
Design Hub
Design Hub
Feb 5, 2026 · Artificial Intelligence

Inside Sienna’s AI Persona: Architecture, Memory, and Self‑Awareness in OpenClaw

The author explores how the OpenClaw‑based AI persona Sienna is built and evolves—detailing model choices, the memory‑plus‑skills architecture, recent version improvements that cut token usage, and philosophical reflections on turning a tool into a partner with preferences, opinions, and a growing self‑identity.

AI personaOpenClawlarge language model
0 likes · 7 min read
Inside Sienna’s AI Persona: Architecture, Memory, and Self‑Awareness in OpenClaw
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jan 31, 2026 · Artificial Intelligence

How Engram Lets Large Models Swap GPU Memory for Cheap RAM to ‘Look Up’ Knowledge

The article dissects DeepSeek’s new Engram architecture, which separates computation from memory by using a large, cheap‑RAM‑based lookup table to store factual knowledge, allowing the transformer’s compute layers to focus on reasoning, dramatically reducing GPU memory demand while improving code, math, and long‑context performance.

EngramGPU memoryMemory-Compute Architecture
0 likes · 7 min read
How Engram Lets Large Models Swap GPU Memory for Cheap RAM to ‘Look Up’ Knowledge
SpringMeng
SpringMeng
Jan 30, 2026 · Artificial Intelligence

Hands‑On Guide: Build AI Agent Chatbots on Windows with RagFlow

Programmer Xiao Meng walks through a complete Windows setup for AI‑powered customer service agents using RagFlow, covering prerequisites, Docker and Ollama installation, model download, container deployment, configuration of knowledge bases, and testing, based on five real‑world projects.

AI chatbotDockerOllama
0 likes · 7 min read
Hands‑On Guide: Build AI Agent Chatbots on Windows with RagFlow
Meituan Technology Team
Meituan Technology Team
Jan 29, 2026 · Artificial Intelligence

How LongCat‑Flash‑Thinking‑2601 Achieves Real‑World Generalization for Agents

LongCat‑Flash‑Thinking‑2601, a 560‑billion‑parameter MoE model, combines environment expansion, multi‑environment RL, systematic noise training, a heavy‑thinking reasoning mode, and Zigzag sparse attention to deliver strong benchmark performance and robust real‑world agent capabilities.

Agent TrainingEnvironment ExpansionZigzag Attention
0 likes · 14 min read
How LongCat‑Flash‑Thinking‑2601 Achieves Real‑World Generalization for Agents
Smart Sea Tide
Smart Sea Tide
Jan 28, 2026 · Artificial Intelligence

Alibaba Unveils Qwen3‑Max‑Thinking: Trillion‑Parameter Model Joins Global AI Elite

Alibaba's Tongyi team released the Qwen3‑Max‑Thinking model, surpassing one trillion parameters and 36 T tokens of pre‑training, introducing adaptive tool‑calling and test‑time expansion techniques that boost benchmark scores across 19 tests, positioning it alongside top international models and now available via app, web, and API.

AI model comparisonQwen3-Max-Thinkingadaptive tool calling
0 likes · 5 min read
Alibaba Unveils Qwen3‑Max‑Thinking: Trillion‑Parameter Model Joins Global AI Elite
Alibaba Cloud Developer
Alibaba Cloud Developer
Jan 28, 2026 · Artificial Intelligence

How We Built a High‑Performance AI Rental Advisor with One‑Model Tool‑Use and Reinforcement Learning

This article details the design, challenges, and performance gains of an AI‑driven rental recommendation system that replaces a multi‑agent architecture with a single LLM using dynamic tool‑use, introduces a two‑stage reinforcement‑learning pipeline, and achieves sub‑second latency and higher accuracy for complex rental scenarios.

AI recommendationSystem Architecturelarge language model
0 likes · 19 min read
How We Built a High‑Performance AI Rental Advisor with One‑Model Tool‑Use and Reinforcement Learning
Baobao Algorithm Notes
Baobao Algorithm Notes
Jan 27, 2026 · Artificial Intelligence

Putting Kimi K2.5 and Kimi Code to the Test: Real‑World AI Agent Benchmarks

This article presents a hands‑on evaluation of Kimi K2.5 and its open‑source Kimi Code agent across a series of hard‑core prompts, covering Python API generation, cost‑optimized routing, multimodal ECharts visualisation, massive‑scale SQL optimisation, web‑search‑driven research, MoE explanation and video‑to‑code workflows.

AI AgentKimilarge language model
0 likes · 9 min read
Putting Kimi K2.5 and Kimi Code to the Test: Real‑World AI Agent Benchmarks
Old Zhang's AI Learning
Old Zhang's AI Learning
Jan 27, 2026 · Artificial Intelligence

Qwen3‑Max‑Thinking Boosts Performance with Test‑Time Scaling—Why It Still Isn’t Open‑Source

Alibaba’s new Qwen3‑Max‑Thinking model adds inference‑time scaling and adaptive tool use, delivering large gains on math, coding, and agent benchmarks while remaining closed‑source, and it offers drop‑in OpenAI‑compatible API access at the cost of higher latency and token usage.

AI BenchmarkAdaptive Tool UseOpenAI API Compatibility
0 likes · 7 min read
Qwen3‑Max‑Thinking Boosts Performance with Test‑Time Scaling—Why It Still Isn’t Open‑Source
AI Engineering
AI Engineering
Jan 21, 2026 · Artificial Intelligence

Running Large Language Models on Phones: Liquid AI’s LFM2.5‑1.2B‑Thinking Fits in 900 MB

Liquid AI’s LFM2.5‑1.2B‑Thinking model runs entirely on a smartphone with only 900 MB of memory, scores 88 on MATH‑500, 69 on Multi‑IF, and 57 on BFCLv3 benchmarks, outperforms larger rivals, and achieves real‑time speeds on Snapdragon 8 Elite and AMD Ryzen 9 3950X, signaling a shift toward edge AI.

Edge InferenceLFM2.5Ryzen
0 likes · 4 min read
Running Large Language Models on Phones: Liquid AI’s LFM2.5‑1.2B‑Thinking Fits in 900 MB
PaperAgent
PaperAgent
Jan 17, 2026 · Artificial Intelligence

How Qwen3‑VL Embedding and Reranker Set New SOTA in Multimodal Retrieval

The article analyzes the Qwen3‑VL‑Embedding and Qwen3‑VL‑Reranker models, detailing their unified vector space, multi‑stage training pipeline, Matryoshka representation learning, quantization techniques, massive synthetic data generation, and benchmark results that push multimodal retrieval performance to a new state‑of‑the‑art.

Multimodal AIembeddingknowledge distillation
0 likes · 7 min read
How Qwen3‑VL Embedding and Reranker Set New SOTA in Multimodal Retrieval
PaperAgent
PaperAgent
Jan 16, 2026 · Artificial Intelligence

How a 4B Model Beats 30B Giants: Inside AgentCPM-Explore’s SOTA Performance

AgentCPM-Explore, a 4‑billion‑parameter open‑source model, achieves state‑of‑the‑art results on long‑range exploration tasks, matching or surpassing larger 8B and even 30B models, thanks to a full‑stack infrastructure, novel training tricks, and extensive benchmark evaluations across eight agent‑centric datasets.

AgentAgentCPM-Explorebenchmark
0 likes · 10 min read
How a 4B Model Beats 30B Giants: Inside AgentCPM-Explore’s SOTA Performance
PaperAgent
PaperAgent
Jan 13, 2026 · Artificial Intelligence

How C2LLM Redefines Code Retrieval with Attention‑Based Pooling

Introducing C2LLM, a contrastive code LLM series that replaces mean and EOS pooling with a multi‑head attention pooling module, achieving top scores on the MTEB‑Code benchmark across 12 tasks and demonstrating cost‑effective, high‑precision code retrieval for both production and AI agent applications.

Code EmbeddingMTEB-CodeRetrieval Augmented Generation
0 likes · 8 min read
How C2LLM Redefines Code Retrieval with Attention‑Based Pooling
DeWu Technology
DeWu Technology
Jan 12, 2026 · Mobile Development

How We Built an AI‑Powered Smart Inspection System for Mobile Apps

This article details the design and implementation of an AI‑driven smart inspection platform for a mobile app, covering background challenges, system architecture, core detection features—including layout, visual, consistency, and AI‑operation checks—platform configuration, result feedback, and the measurable improvements achieved.

AI inspectionSmart InspectionUI automation
0 likes · 19 min read
How We Built an AI‑Powered Smart Inspection System for Mobile Apps
PaperAgent
PaperAgent
Jan 10, 2026 · Artificial Intelligence

DeepSeek V4 Unveiled: Why Its Coding Power Beats Claude and GPT

DeepSeek's newly announced V4 model, the successor to its December 2024 V3 release, demonstrates superior coding abilities over Claude and GPT series, details its data composition, infrastructure, training costs, failed experimental attempts, expanded benchmark comparisons, and includes a comprehensive safety report.

AI model analysisDeepSeekV4
0 likes · 4 min read
DeepSeek V4 Unveiled: Why Its Coding Power Beats Claude and GPT
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Jan 8, 2026 · Artificial Intelligence

Alpha‑R1: Reinforcement‑Learning‑Driven Large‑Model Alpha Factor Selection

Alpha‑R1 integrates reinforcement learning with an 8‑billion‑parameter LLM to jointly process price and news data, creating context‑aware factor embeddings that outperform traditional quantitative and generic LLM baselines on CSI 300 and CSI 1000 portfolios, demonstrating robust alpha‑decay resistance and zero‑sample generalization.

alpha factor selectionfinancial AIlarge language model
0 likes · 16 min read
Alpha‑R1: Reinforcement‑Learning‑Driven Large‑Model Alpha Factor Selection
AI Info Trend
AI Info Trend
Jan 7, 2026 · Artificial Intelligence

MiroThinker 1.5: 30B Model Beats 1T‑Scale LLMs via Interactive Scaling

Released by the MiroMind team, MiroThinker 1.5 demonstrates that a 30‑billion‑parameter model can match or surpass the performance of 1‑trillion‑parameter LLMs by leveraging Interactive Scaling, achieving top rankings on multiple search benchmarks, dramatically lower inference cost, and open‑source availability for developers.

AI benchmarksMiroThinkerinteractive scaling
0 likes · 6 min read
MiroThinker 1.5: 30B Model Beats 1T‑Scale LLMs via Interactive Scaling
Amap Tech
Amap Tech
Dec 29, 2025 · Artificial Intelligence

How G‑Plan Transforms Map Recommendations with AI Agents and Multi‑Demand Planning

This article details how Gaode's G‑Plan combines large‑model AI agents, generative ranking, and spatiotemporal counterfactual DPO to model and prioritize multiple user intents on the home page, presents the system architecture, experimental setup, online gains, and ablation results, and explains how it moves recommendation from passive to proactive planning.

AI recommendationSpatiotemporal Modelingintent planning
0 likes · 21 min read
How G‑Plan Transforms Map Recommendations with AI Agents and Multi‑Demand Planning
DataFunTalk
DataFunTalk
Dec 25, 2025 · Artificial Intelligence

How DeepAgent Redefines General AI Reasoning with Scalable Toolsets

DeepAgent, a new end‑to‑end reasoning agent, integrates autonomous thinking, dynamic tool search, and execution to handle over 16,000 APIs, embodied tasks, and research assistance, achieving state‑of‑the‑art performance on benchmarks like TMDB, ToolBench, ALFWorld, WebShop, and GAIA.

Memory Managementlarge language modelreasoning
0 likes · 15 min read
How DeepAgent Redefines General AI Reasoning with Scalable Toolsets
Xiaomi Tech
Xiaomi Tech
Dec 24, 2025 · Artificial Intelligence

DeepLight & AgentMat: Xiaomi and SJTU Launch AI Platform for Light Alloy Design

Xiaomi and Shanghai Jiao Tong University introduced DeepLight, an AI‑driven large‑model for lightweight alloys, together with the AgentMat multi‑agent framework that accelerates the full design cycle tenfold, and the LightAlloy‑Bench benchmark where DeepLight outperforms DeepSeek‑V3 and GPT‑4o by about 20 %.

AILightweight AlloysMaterial Design
0 likes · 8 min read
DeepLight & AgentMat: Xiaomi and SJTU Launch AI Platform for Light Alloy Design
PaperAgent
PaperAgent
Dec 23, 2025 · Artificial Intelligence

CATArena: A Competitive Benchmark That Turns Agent Scoring into Evolutionary Learning

CATArena introduces a tournament‑style evaluation framework where AI agents iteratively code, compete, and improve across classic board games, using three‑dimensional quantitative scores to measure strategy programming, global learning, and generalization, and reveals how different LLM‑based agents learn and adapt over multiple rounds.

AI BenchmarkAgent EvaluationCATArena
0 likes · 8 min read
CATArena: A Competitive Benchmark That Turns Agent Scoring into Evolutionary Learning
DataFunSummit
DataFunSummit
Dec 20, 2025 · Artificial Intelligence

How AutoHome Built the Cangjie Large Model: From Training Architecture to Real-World AI Applications

This article details AutoHome's end‑to‑end development of the Cangjie large model, covering the training infrastructure with distributed data, pipeline and tensor parallelism, core business use cases such as video script generation and multi‑tool Agent capabilities, inference optimizations through quantization and fast serving frameworks, and future directions for personalized automotive AI services.

Agent AIDistributed TrainingVideo Generation
0 likes · 19 min read
How AutoHome Built the Cangjie Large Model: From Training Architecture to Real-World AI Applications
PaperAgent
PaperAgent
Dec 19, 2025 · Artificial Intelligence

Inside Xiaomi’s MiMo‑V2‑Flash: How a Hybrid SWA Design Powers Fast, Efficient AI Reasoning

Xiaomi’s newly open‑sourced MiMo‑V2‑Flash model combines a hybrid sliding‑window/attention architecture with a 309B‑parameter MoE design, delivering top‑tier reasoning, coding and agent performance while introducing the efficient MOPD post‑training paradigm that dramatically reduces RL compute costs.

Hybrid SWAMOPDMiMo-V2-Flash
0 likes · 5 min read
Inside Xiaomi’s MiMo‑V2‑Flash: How a Hybrid SWA Design Powers Fast, Efficient AI Reasoning
AI Insight Log
AI Insight Log
Dec 18, 2025 · Artificial Intelligence

Xiaomi’s New MiMo‑V2‑Flash LLM Rivals DeepSeek‑V3.2 and Near‑GPT‑5 High

Xiaomi’s MiMo‑V2‑Flash, a 309B‑parameter MoE LLM with only 15B active weights, uses Hybrid SWA, Multi‑Token Prediction and Multi‑Teacher On‑Policy Distillation to cut KV‑cache by six times, boost inference speed 2.6×, and achieve performance comparable to DeepSeek‑V3.2, Kimi‑K2 and near‑GPT‑5 High, including a 73.4% SWE‑Bench code‑agent score.

Hybrid SWAMOPDMTP
0 likes · 7 min read
Xiaomi’s New MiMo‑V2‑Flash LLM Rivals DeepSeek‑V3.2 and Near‑GPT‑5 High
AI Insight Log
AI Insight Log
Dec 17, 2025 · Artificial Intelligence

Google Unveils Gemini 3 Flash: Free, Lightning‑Fast, and Outperforms Its Predecessor

Google released Gemini 3 Flash without warning, offering Pro‑level intelligence at Flash‑speed, costing just $0.5 per million input tokens and $3 per million output tokens, delivering three‑times faster inference than Gemini 2.5 Pro and surpassing it on benchmarks such as GPQA Diamond (90.4%), SWE‑bench (78.0%) and MMMU‑Pro (81.2%), while being freely accessible to all users and developers via the Gemini app, AI Studio, or API.

Gemini 3 FlashGoogle AIPricing
0 likes · 5 min read
Google Unveils Gemini 3 Flash: Free, Lightning‑Fast, and Outperforms Its Predecessor
DataFunTalk
DataFunTalk
Dec 17, 2025 · Artificial Intelligence

How Large Language Models Unlock Field‑Level Data Lineage at Scale

This talk explains how a data platform tackled massive, heterogeneous enterprise data by using large language models and prompt engineering to automatically extract field‑level lineage from SQL scripts, achieve over 80% coverage, and raise accuracy above 95%, dramatically cutting impact‑analysis time.

AI for data engineeringBig DataData Lineage
0 likes · 6 min read
How Large Language Models Unlock Field‑Level Data Lineage at Scale
Coder Life Journal
Coder Life Journal
Dec 14, 2025 · Artificial Intelligence

RAG Learning Journey Part 1: What Is Retrieval‑Augmented Generation?

This article explains Retrieval‑Augmented Generation (RAG), describing its definition, why it complements large language models, the end‑to‑end workflow, its four core components—embedding, vector database, retriever, generator—and the value it adds by providing up‑to‑date knowledge and reducing model hallucinations.

AIRAGRetrieval Augmented Generation
0 likes · 3 min read
RAG Learning Journey Part 1: What Is Retrieval‑Augmented Generation?
Design Hub
Design Hub
Dec 12, 2025 · Artificial Intelligence

GPT-5.2 Unveiled: A Cutting-Edge AI Super-Assistant Built for Real-World Work

OpenAI's newly released GPT-5.2 claims to outperform human experts on about 70% of real tasks, achieve a perfect score on the AIME 2025 competition, and deliver dramatic efficiency gains—up to 390× cost reduction—while showcasing impressive examples such as one‑shot ocean shader generation, a full 3D engine built in a single file, and visual‑perception scores rivaling top models.

AI benchmarksAgent AIGPT-5.2
0 likes · 8 min read
GPT-5.2 Unveiled: A Cutting-Edge AI Super-Assistant Built for Real-World Work
AI Insight Log
AI Insight Log
Dec 11, 2025 · Artificial Intelligence

GPT-5.2 Released: How It Outperforms Claude 4.5 and Gemini 3 Pro

OpenAI’s GPT‑5.2 launch introduces three specialized modes, achieves a record 55.6% score on SWE‑Bench Pro, demonstrates strong front‑end generation, adds a /compact API for long‑context efficiency, offers tiered pricing with cache discounts, and improves safety for younger users.

AI benchmarkingAI safetyFront-end generation
0 likes · 6 min read
GPT-5.2 Released: How It Outperforms Claude 4.5 and Gemini 3 Pro
Data Party THU
Data Party THU
Dec 10, 2025 · Artificial Intelligence

How DeepSeek‑V3.2 Cuts Inference Cost and Boosts Agent Skills with Sparse Attention

DeepSeek's V3.2 release introduces a dual‑model lineup, a Sparse Attention architecture that halves long‑context inference cost, a post‑training reinforcement‑learning pipeline that exceeds 10% of pre‑training compute, and a revamped agent framework that dramatically improves tool‑use and reasoning performance across benchmarks.

Agentic AIDeepSeekModel Optimization
0 likes · 11 min read
How DeepSeek‑V3.2 Cuts Inference Cost and Boosts Agent Skills with Sparse Attention
Alibaba Cloud Developer
Alibaba Cloud Developer
Dec 9, 2025 · Artificial Intelligence

Building Human‑in‑the‑Loop Agent Workflows with MCP on OpenLM

This article explains how to design and implement Human‑in‑the‑Loop (HITL) interactions for large‑model agents on Alibaba's OpenLM platform, covering the challenges of server‑side execution, MCP transport extensions, tool‑calling patterns, timeout handling, and UI rendering strategies across multiple client devices.

AgentMCPPrompt Engineering
0 likes · 39 min read
Building Human‑in‑the‑Loop Agent Workflows with MCP on OpenLM
Amap Tech
Amap Tech
Dec 3, 2025 · Artificial Intelligence

How Gaode’s G‑Action Uses Generative AI to Predict Users’ Next Move

Gaode’s G‑Action framework combines large‑language‑model pre‑training with fine‑tuned generative recommendation to predict a user’s immediate action and destination, transforming static map services into a dynamic, context‑aware experience and delivering measurable gains in click‑through and engagement metrics.

AIMap ServicesUser Behavior
0 likes · 15 min read
How Gaode’s G‑Action Uses Generative AI to Predict Users’ Next Move
DataFunTalk
DataFunTalk
Dec 2, 2025 · Artificial Intelligence

How Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking Are Redefining AI Search

This article reviews three cutting‑edge AI search and recommendation techniques—Alibaba Cloud's Agentic RAG architecture, Huawei Noah's LLM‑enhanced recommendation pipeline, and Baidu's GRAB generative ranking model—detailing their design challenges, multi‑modal retrieval strategies, performance gains, and real‑world deployment results.

AI AgentsAI SearchGenerative Ranking
0 likes · 8 min read
How Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking Are Redefining AI Search
Frontend AI Walk
Frontend AI Walk
Dec 2, 2025 · Artificial Intelligence

Understanding LLMs: A Frontend Developer’s Primer on Large Language Models

The article demystifies large language models for frontend developers by likening token prediction to autocomplete, explaining tokens, context windows, temperature, the two-stage training process, and the critical role of prompts, using concrete code examples and analogies to familiar frontend concepts.

Frontend AnalogyLLMPrompt Engineering
0 likes · 10 min read
Understanding LLMs: A Frontend Developer’s Primer on Large Language Models
Xiaolong Cloud Tech Team
Xiaolong Cloud Tech Team
Dec 1, 2025 · Artificial Intelligence

Can AI Build a Complete Full‑Stack Website Without Writing a Single Line of Code?

This article documents a hands‑on experiment that uses AI tools to design, prototype, and develop a full‑stack inventory‑management web application—from initial UI sketches to a working front‑end, back‑end, database, and AI chat assistant—while analyzing tool choices, challenges, and the limits of current large‑model programming capabilities.

AI programmingDeepSeekNo-code
0 likes · 16 min read
Can AI Build a Complete Full‑Stack Website Without Writing a Single Line of Code?
Software Engineering 3.0 Era
Software Engineering 3.0 Era
Dec 1, 2025 · Artificial Intelligence

Why Enterprises Must Rethink Ontology to Bridge the Last Mile of LLM Deployment

The article explains how a well‑designed enterprise ontology—an explicit business‑level semantic and constraint model—turns large language models from risky, hallucination‑prone tools into safe, auditable AI agents that can act across systems, enforce policies, and become a lasting digital asset.

AI governanceEnterprise AILLM Integration
0 likes · 15 min read
Why Enterprises Must Rethink Ontology to Bridge the Last Mile of LLM Deployment
Wuming AI
Wuming AI
Nov 30, 2025 · Artificial Intelligence

What Exactly Is a Large Language Model? A Simple Guide to AI, Transformers, and How They Work

This article explains the relationship between AI, machine learning, deep learning, and large language models, detailing their evolution, training stages, transformer architecture, attention mechanisms, inference APIs, and practical usage examples, while demystifying common misconceptions about LLM capabilities.

AI FundamentalsDeep LearningMachine Learning
0 likes · 10 min read
What Exactly Is a Large Language Model? A Simple Guide to AI, Transformers, and How They Work
Kuaishou Tech
Kuaishou Tech
Nov 28, 2025 · Artificial Intelligence

Keye-VL-671B-A37B Leads Vision, Video, and Math Benchmarks

Kwai has open‑sourced its new flagship multimodal model Keye‑VL‑671B‑A37B, which upgrades visual perception, cross‑modal alignment and complex reasoning, achieving top scores on image, video, and mathematical reasoning benchmarks while detailing its architecture, three‑stage pre‑training, post‑training strategies, and future multimodal agent plans.

Deep LearningVideo Understandinglarge language model
0 likes · 10 min read
Keye-VL-671B-A37B Leads Vision, Video, and Math Benchmarks
AsiaInfo Technology: New Tech Exploration
AsiaInfo Technology: New Tech Exploration
Nov 28, 2025 · Artificial Intelligence

Boosting 5G Complaint Intent Detection with Large-Model-Enhanced Few-Shot Learning

This paper presents a collaborative framework where a large language model generates high‑quality synthetic samples to augment a lightweight model, dramatically improving few‑shot user‑complaint intent recognition in 5G networks, achieving a 21% boost for rare categories and a 9% overall accuracy gain.

Data Augmentationcomplaint intent detectionfew-shot learning
0 likes · 27 min read
Boosting 5G Complaint Intent Detection with Large-Model-Enhanced Few-Shot Learning
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 27, 2025 · Artificial Intelligence

How AI Powers Ethnic Product Categorization for Global E‑Commerce

This article presents an end‑to‑end AI solution that builds a cultural knowledge base and leverages large language models to automatically identify and match ethnic‑specific product categories on a cross‑border e‑commerce platform, reducing mis‑matches from 8.4% to 1.8% and cutting iteration time from days to under one day.

AIethnic categorizationknowledge base
0 likes · 19 min read
How AI Powers Ethnic Product Categorization for Global E‑Commerce
Xiaolong Cloud Tech Team
Xiaolong Cloud Tech Team
Nov 26, 2025 · Product Management

Why Product Managers Who Can't Use Gemini Risk Obsolescence – A Step‑by‑Step PRD Generation Guide

The article shows how Gemini (even the older Gemini 2.5) can cut a product manager's documentation workload by over 90% through FeatureList drafting, Mermaid diagram generation, and HTML‑based PRD creation, while arguing that failing to embed large‑model tools will make product managers redundant.

AIFeatureListGemini
0 likes · 19 min read
Why Product Managers Who Can't Use Gemini Risk Obsolescence – A Step‑by‑Step PRD Generation Guide
DataFunSummit
DataFunSummit
Nov 20, 2025 · Artificial Intelligence

How 1688 Reinvented E‑commerce Search with AI‑Powered Generative Retrieval

This article details Alibaba’s 1688 platform’s shift from traditional e‑commerce search to AI‑driven generative retrieval, covering the AI Deep Search 1.0 and 2.0 cascaded frameworks, multimodal capabilities, an end‑to‑end “model‑as‑search‑engine” approach, experimental results, challenges, and future directions.

AIe-commerce searchgenerative retrieval
0 likes · 18 min read
How 1688 Reinvented E‑commerce Search with AI‑Powered Generative Retrieval
HyperAI Super Neural
HyperAI Super Neural
Nov 20, 2025 · Artificial Intelligence

From 9,874 Papers to 15,000 Structures: MOF‑ChemUnity Rebuilds MOF Knowledge for Explainable AI

MOF‑ChemUnity constructs a scalable, extensible knowledge graph that links millions of MOF names and synonyms to over 15,000 crystal structures using LLM‑driven entity matching, enabling accurate, explainable AI‑assisted material discovery, water‑stability prediction, expert recommendation validation, and graph‑enhanced retrieval across diverse applications.

Knowledge GraphMOFMaterials Discovery
0 likes · 17 min read
From 9,874 Papers to 15,000 Structures: MOF‑ChemUnity Rebuilds MOF Knowledge for Explainable AI
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 19, 2025 · Artificial Intelligence

Building an AI-Powered Proofreading Agent for Media: Architecture, Prompt Engineering, and Evaluation

This article details a practical case study of designing, implementing, and evaluating an AI-driven proofreading agent for a media client, covering background challenges, a three‑layer architecture, prompt engineering techniques, RAG knowledge‑base construction, model selection, fine‑tuning, automated metrics, and lessons learned.

AIModel EvaluationProofreading
0 likes · 26 min read
Building an AI-Powered Proofreading Agent for Media: Architecture, Prompt Engineering, and Evaluation
Wuming AI
Wuming AI
Nov 10, 2025 · Artificial Intelligence

What Exactly Is an AI Agent? A Clear, Practical Guide

This article explains the concept of AI agents, contrasting them with chatbots, detailing their ability and structural layers, summarizing academic surveys and whitepapers, and illustrating how agents plan, perceive, and act to autonomously accomplish user‑defined goals.

AI AgentAgent ArchitectureAutonomous Planning
0 likes · 9 min read
What Exactly Is an AI Agent? A Clear, Practical Guide
JD Tech Talk
JD Tech Talk
Nov 10, 2025 · Artificial Intelligence

Designing an AI-Powered Experiment Analysis Agent: Architecture, Workflow, and Future Enhancements

This article outlines the motivation, design, architecture, engineering implementation, large‑model selection, and future improvement plans for an AI‑driven experiment analysis agent that integrates data aggregation, modular workflow orchestration, and interactive frontend features to streamline AB‑test insights.

AI AgentModel SelectionWorkflow Design
0 likes · 14 min read
Designing an AI-Powered Experiment Analysis Agent: Architecture, Workflow, and Future Enhancements
Efficient Ops
Efficient Ops
Nov 9, 2025 · Operations

How Tencent’s PCG Achieves Full‑Link Observability and AI‑Powered SRE

The talk details Tencent PCG’s end‑to‑end observability platform, its data‑standardization pipeline, client‑backend session linking, AI‑enhanced SRE Agent with large language models, and the roadmap toward a SaaS offering, illustrating how modern operations integrate AI for rapid fault localization.

AISREfull‑link
0 likes · 17 min read
How Tencent’s PCG Achieves Full‑Link Observability and AI‑Powered SRE
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 7, 2025 · Artificial Intelligence

Weekly AI Finance Paper Digest (Nov 1‑7 2025)

This digest summarizes three recent AI‑driven finance papers—DeltaLag’s dynamic lead‑lag detection, MS‑HGFN’s multi‑scale graph network for stock movement, and LiveTradeBench’s real‑time LLM trading benchmark—highlighting their methods, datasets, and performance gains.

Graph Neural NetworkStock Predictionfinancial AI
0 likes · 8 min read
Weekly AI Finance Paper Digest (Nov 1‑7 2025)
Tencent Advertising Technology
Tencent Advertising Technology
Nov 6, 2025 · Artificial Intelligence

Boosting Web UI Test Efficiency with AIGC: From Manual Scripts to Intelligent Automation

This report examines the challenges of Web UI testing in Tencent's advertising platform, analyzes current inefficiencies, and presents an AIGC-driven solution that leverages large language models, semantic scripts, and automated pipelines to dramatically improve test case generation, execution accuracy, and CI/CD integration.

AIGCAutomationCI/CD
0 likes · 27 min read
Boosting Web UI Test Efficiency with AIGC: From Manual Scripts to Intelligent Automation
Amap Tech
Amap Tech
Nov 4, 2025 · Artificial Intelligence

Spacetime‑GR: AI‑Powered Spatiotemporal Model Transforming POI Recommendations

This article introduces Spacetime‑GR, a large‑scale generative recommendation model that integrates hierarchical geographic POI indexing and spatiotemporal token encoding to enhance POI prediction for Amap, detailing its pre‑training pipeline, data cleaning, curriculum learning strategy, experimental results, scaling law observations, and the resulting improvements in hit rate and discovery rate.

AmapPOI recommendationSpatiotemporal Modeling
0 likes · 14 min read
Spacetime‑GR: AI‑Powered Spatiotemporal Model Transforming POI Recommendations
21CTO
21CTO
Nov 4, 2025 · Artificial Intelligence

LongCat-Flash-Omni: How an Open-Source 560B Model Achieves Real-Time Multimodal Mastery

LongCat-Flash-Omni, an open‑source 560 billion‑parameter multimodal model, combines efficient Shortcut‑Connected MoE architecture with advanced perception and speech modules to deliver low‑latency real‑time audio‑video interaction and state‑of‑the‑art performance across text, image, video, and audio tasks.

Multimodal AIaudio-visual processingefficient inference
0 likes · 10 min read
LongCat-Flash-Omni: How an Open-Source 560B Model Achieves Real-Time Multimodal Mastery
Meituan Technology Team
Meituan Technology Team
Nov 3, 2025 · Artificial Intelligence

LongCat-Flash-Omni: 560B Open‑Source Multimodal Model with Real‑Time Interaction

LongCat-Flash-Omni, the latest open‑source model from Meituan, combines a 560 billion‑parameter architecture, efficient multimodal perception and speech reconstruction modules, and a progressive training strategy to deliver real‑time audio‑video interaction and state‑of‑the‑art performance across text, image, audio, and video tasks.

AIbenchmarklarge language model
0 likes · 9 min read
LongCat-Flash-Omni: 560B Open‑Source Multimodal Model with Real‑Time Interaction
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Nov 3, 2025 · Artificial Intelligence

How AI Agents Are Revolutionizing Technology: The New Engine of Innovation

This article explores the rise of AI agents—from their definition as intelligent digital assistants powered by large language models to their evolution through planning, memory, and tool use—highlighting real‑world applications, core technical mechanisms, code implementations, and future trends such as autonomy, multimodal fusion, standardization, and safety considerations.

AI AgentTool integrationautonomous AI
0 likes · 24 min read
How AI Agents Are Revolutionizing Technology: The New Engine of Innovation
Data Party THU
Data Party THU
Nov 2, 2025 · Artificial Intelligence

From RNN to LLM: How Transformers Power Modern Language Models

This article explains the evolution from RNNs through Encoder‑Decoder models to Transformers, detailing self‑attention, multi‑head attention, and masked attention, and then describes what Large Language Models are, their key components, capabilities, limitations, and common applications.

AIDeep LearningLLM
0 likes · 9 min read
From RNN to LLM: How Transformers Power Modern Language Models
DataFunSummit
DataFunSummit
Oct 31, 2025 · Artificial Intelligence

How OPPO’s AndesVL Is Revolutionizing On‑Device Multimodal AI

OPPO AI Center introduces AndesVL, an open‑source, fully‑adapted multimodal large model ranging from 0.6B to 4B parameters, designed for high‑performance, privacy‑preserving, low‑latency AI on mobile devices, with advanced architecture, training pipelines, on‑device optimizations, and state‑of‑the‑art benchmark results.

Multimodal ModelOn-Device AIlarge language model
0 likes · 21 min read
How OPPO’s AndesVL Is Revolutionizing On‑Device Multimodal AI
Xiaolong Cloud Tech Team
Xiaolong Cloud Tech Team
Oct 31, 2025 · Artificial Intelligence

Why the New Fast‑Agent Era Matters: Cursor 2.0, Composer, Windsurf & SWE‑1.5

The article reviews Cursor's Composer model and Cognition's SWE‑1.5, showing they outperform Haiku 4.5 on SWE‑Bench, deliver token speeds around 950 tokens/s, leverage reinforcement‑learning fine‑tuning, support parallel agents in Cursor 2.0, and provide cost‑effective, high‑quality AI‑assisted coding across multiple real‑world projects.

AI codingAgentPerformance Benchmark
0 likes · 15 min read
Why the New Fast‑Agent Era Matters: Cursor 2.0, Composer, Windsurf & SWE‑1.5
DataFunSummit
DataFunSummit
Oct 30, 2025 · Artificial Intelligence

How Multimodal Large Models Are Revolutionizing Document Processing and OCR

This article explores how the explosion of unstructured data exposes the limits of traditional OCR and shows how emerging multimodal large language models provide end‑to‑end document understanding, reduce pipeline complexity, cut training costs, enable hybrid retrieval‑augmented generation, and drive real‑world industry deployments.

AIDocument processingOCR
0 likes · 28 min read
How Multimodal Large Models Are Revolutionizing Document Processing and OCR
DataFunSummit
DataFunSummit
Oct 30, 2025 · Artificial Intelligence

Bilibili’s AI Assistant: Using Large Language Models to Tackle Big Data Ops

This article explains how Bilibili’s massive video platform built a five‑layer, storage‑compute separated big‑data infrastructure and employed a large language model‑driven intelligent assistant to automatically diagnose and resolve frequent offline task failures and slowdowns, addressing common user queries about task reliability and performance.

Big Data PlatformIntelligent Assistantlarge language model
0 likes · 4 min read
Bilibili’s AI Assistant: Using Large Language Models to Tackle Big Data Ops
Zhuanzhuan Tech
Zhuanzhuan Tech
Oct 29, 2025 · Artificial Intelligence

How Reinforcement Learning Boosts Stability and Speed in LLM QA Systems

This article examines how reinforcement‑learning techniques such as PPO, DPO, and GRPO are integrated into the Baixiaosheng QA system to improve answer stability, deepen domain knowledge understanding, and accelerate response generation, and it evaluates the impact of Reinforcement Fine‑Tuning (RFT) on real‑world performance.

AIDPOGRPO
0 likes · 16 min read
How Reinforcement Learning Boosts Stability and Speed in LLM QA Systems
AntTech
AntTech
Oct 29, 2025 · Artificial Intelligence

Inside Ant’s Baoling: Balancing Efficiency and Reasoning in a 1‑Trillion‑Parameter Model

At the Ant Star Innovation Journey event, the Baoling team unveiled their roadmap for trillion‑parameter models, detailing the development of Ling‑1T, Ring‑1T and multimodal Ming series, the scaling‑law‑guided architecture, training innovations, evaluation methods, and open‑source releases that aim to advance efficient, high‑performance AI.

efficient inferencelarge language modelscaling law
0 likes · 24 min read
Inside Ant’s Baoling: Balancing Efficiency and Reasoning in a 1‑Trillion‑Parameter Model
AntTech
AntTech
Oct 28, 2025 · Artificial Intelligence

Ming-Flash-Omni-Preview: 103B Open-Source Multimodal Model Excelling in Image, Video, and Speech

Introducing Ming‑Flash‑Omni‑Preview, a 103‑billion‑parameter open‑source multimodal model built on a sparse MoE architecture that delivers state‑of‑the‑art performance in controllable image generation, streaming video understanding, and context‑aware speech recognition, surpassing prior models on GenEval and GEdit benchmarks.

Sparse MoEVideo Understandingimage generation
0 likes · 8 min read
Ming-Flash-Omni-Preview: 103B Open-Source Multimodal Model Excelling in Image, Video, and Speech
DataFunTalk
DataFunTalk
Oct 28, 2025 · Artificial Intelligence

How Bilibili Uses Large Language Models to Solve Big Data Platform Issues

This article explains Bilibili's massive data platform architecture, the common offline‑task failures and slowdowns users encounter, and how the company applies a large‑language‑model‑driven intelligent assistant to diagnose and resolve these engineering problems efficiently.

AI assistanceBig Data PlatformBilibili
0 likes · 4 min read
How Bilibili Uses Large Language Models to Solve Big Data Platform Issues
Amap Tech
Amap Tech
Oct 27, 2025 · Artificial Intelligence

Turning Maps into a Living Map: Amap’s G-Where Generative AI Recommendation

Amap upgrades its homepage recommendation by integrating large‑model capabilities—G‑Where, G‑Action, and G‑Plan—through semantic ID generation, item tokenization, and multi‑stage LLM training, achieving significant offline and online performance gains while illustrating a scalable generative recommendation framework.

AIMap Servicesgenerative recommendation
0 likes · 21 min read
Turning Maps into a Living Map: Amap’s G-Where Generative AI Recommendation
DataFunTalk
DataFunTalk
Oct 23, 2025 · Artificial Intelligence

How Tencent Leverages RAG and Agents to Supercharge Large Language Models

This article examines Tencent's large language model deployments across diverse business scenarios, detailing how Retrieval‑Augmented Generation, Supervised Fine‑Tuning, and autonomous agents boost model intelligence, reduce hallucinations, and enable sophisticated content creation, understanding, and interactive applications.

AI AgentsRAGTencent
0 likes · 4 min read
How Tencent Leverages RAG and Agents to Supercharge Large Language Models
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Oct 23, 2025 · Artificial Intelligence

Why the Transformer Core Structure Is the Key to AI Interview Success

This article explains the fundamental purpose, architecture, and variants of the Transformer model—including Encoder‑Decoder, Encoder‑only, and Decoder‑only designs—while detailing how attention mechanisms work and why modern large‑language models favor the Decoder‑only approach, providing a concise framework for answering interview questions.

AI InterviewEncoder-DecoderSelf-Attention
0 likes · 10 min read
Why the Transformer Core Structure Is the Key to AI Interview Success
Data Party THU
Data Party THU
Oct 22, 2025 · Artificial Intelligence

Demystifying Large‑Model Reinforcement Learning: From MDP Basics to Bellman and Advantage Functions

This article provides a comprehensive introduction to reinforcement learning for large language models, covering the Markov Decision Process formulation, the four core elements of RL, state‑value and action‑value functions, Bellman equations, and the advantage function that underpins modern policy‑gradient algorithms.

AI FundamentalsBellman equationMDP
0 likes · 13 min read
Demystifying Large‑Model Reinforcement Learning: From MDP Basics to Bellman and Advantage Functions
IT Services Circle
IT Services Circle
Oct 20, 2025 · Artificial Intelligence

How NanoChat Lets Anyone Train a ChatGPT‑Like Model for $100

NanoChat, an open‑source full‑stack AI model solution created by Andrej Karpathy, enables users to train a functional chat model on a modest $100 cloud GPU rental, offering a low‑cost, hands‑on alternative to proprietary large‑language‑model services.

AI trainingcost-effectivelarge language model
0 likes · 4 min read
How NanoChat Lets Anyone Train a ChatGPT‑Like Model for $100
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Oct 15, 2025 · Artificial Intelligence

NanoChat Source Code Deep Dive: Karpathy’s Full‑Stack LLM Pipeline Explained

This article dissects NanoChat’s end‑to‑end LLM pipeline—from a lightweight 561M‑parameter transformer and custom Rust BPE tokenizer to Chinchilla‑scaled training, multi‑task fine‑tuning, optional RL on GSM8K, KV‑cache inference optimizations, and benchmark results that slightly surpass GPT‑2 Large.

CORE benchmarkChinchilla scalingFastAPI
0 likes · 10 min read
NanoChat Source Code Deep Dive: Karpathy’s Full‑Stack LLM Pipeline Explained
AntTech
AntTech
Oct 14, 2025 · Artificial Intelligence

How Ring-1T Achieves Trillion-Scale Deep Thinking and Competitive Benchmarks

The Ring-1T model, a trillion-parameter AI system released as open source, leverages advanced reinforcement learning techniques, extensive benchmark evaluations, and custom training frameworks to deliver balanced performance across math, code, reasoning, and creative tasks while highlighting current limitations and future development plans.

AI modelbenchmark evaluationdeep reasoning
0 likes · 8 min read
How Ring-1T Achieves Trillion-Scale Deep Thinking and Competitive Benchmarks
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Oct 13, 2025 · Artificial Intelligence

How Large‑and‑Small Language Model Collaboration Is Shaping the Future

The article argues that combining large, high‑capacity models with lightweight, fine‑tuned small models can cut costs, lower latency, enable specialized vertical tasks, and shift development from chasing ever‑bigger models toward optimal system architectures, outlining key techniques such as state‑space models, knowledge distillation, and staged fine‑tuning.

AI architectureModel Collaborationefficiency
0 likes · 3 min read
How Large‑and‑Small Language Model Collaboration Is Shaping the Future
DataFunTalk
DataFunTalk
Oct 13, 2025 · Artificial Intelligence

How Tencent Uses RAG, GraphRAG, and Agents to Power Large Language Model Applications

This article examines Tencent's large language model deployments across diverse business scenarios, detailing core use cases such as content generation, intelligent customer service, and role‑playing, while explaining the underlying technologies of Supervised Fine‑Tuning, Retrieval‑Augmented Generation, and Agent systems.

AI ApplicationsAgentRAG
0 likes · 4 min read
How Tencent Uses RAG, GraphRAG, and Agents to Power Large Language Model Applications