OpenAI's GPT-5.4 launch introduces three model tiers, a 1 million‑token context window, native computer‑use abilities, higher factual accuracy and a new Tool Search feature, reshaping enterprise AI capabilities and intensifying competition with Anthropic and Google.
OpenAI announced GPT‑5.4 at 2 a.m., skipping GPT‑5.3 and claiming integrated coding and reasoning abilities; the model tops five of eight benchmark categories, introduces native computer operation, tool‑search and interruptible thinking, while users debate its trustworthiness and pricing changes.
The article argues that Software Engineering 3.0 is fundamentally a continuous entropy‑reduction process, using information theory to explain how large language models turn ambiguous human intent into precise executable code, why knowledge graphs outperform documents, and how multi‑agent systems improve quality assurance.
The article analyzes the limitations of traditional ID‑based and vector recall, proposes a generative Semantic‑ID‑based recall framework (ASGR), details a series of inference‑time optimizations—including a custom SDPA‑enabled optimizer, novel beam search, static‑cache compilation, tree‑aware attention, sliding‑window attention, quantization, ONNX/Optimum conversion, and TensorRT‑LLM integration—and reports concrete latency and throughput gains that enable large‑scale, low‑latency recommendation serving.
Alibaba has released three new Qwen3.5 models (35B‑A3B, 122B‑A10B, 27B) that, thanks to hybrid attention and high‑sparse MoE architecture, achieve record performance for mid‑size LLMs, support up to 1 M token context, and can be deployed on consumer‑grade GPUs with low inference cost.
This article provides a detailed side‑by‑side analysis of the open‑source ASR tools FunASR and Qwen3‑ASR, covering team origins, model architectures, language coverage, speed, deployment requirements, and ideal use‑cases so readers can decide which solution fits their projects best.
DeerFlow 2.0, an open‑source super‑agent framework from ByteDance, lets developers automate multi‑step, minutes‑to‑hours‑long workflows by orchestrating sub‑agents with memory, sandboxed execution, and extensible skills, and has surged to over 2.4 k GitHub stars.
The author reviews the Qwen3.5 model family, showing that the 27‑billion‑parameter dense Qwen3.5-27B offers the best balance of size, stability, low‑cost local deployment, and comprehensive capabilities, making it the default pick for most users.
This article walks through creating a Telegram bot that leverages OpenCode's Server API to provide full AI coding assistance, covering setup, multi‑model integration, core architecture, common pitfalls, and extensible features, all with under 900 lines of Python code.
Recent reports indicate that DeepSeek's unreleased V4 Lite model, featuring a 1‑million‑token context window and native multimodal reasoning, has been leaked online, with Huawei gaining early access while Nvidia is excluded, and the model demonstrates impressive spatial reasoning in generated SVG examples.
This guide reviews the Qwen3.5 model lineup, explains mixed‑inference and MoE architecture, presents benchmark comparisons with GPT‑5.2, Claude 4.5 and Gemini‑3 Pro, evaluates 4‑bit and 3‑bit quantization loss, outlines hardware requirements, and provides step‑by‑step deployment options using llama.cpp or llama‑server.
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.
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.
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.
This article explains the technical distinction between intelligent speech— a toolbox of ASR, TTS, NLU, and NLG technologies— and Voice Agent, an end‑to‑end conversational system built on those tools and large‑model reasoning, illustrating their layered relationship, functional gaps, and typical use cases.
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.
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.
The latest Ollama 0.16.1 release lets users switch models and tools instantly, use Claude Code, Codex, and OpenClaw without extra configuration, and enables Subagents and built‑in web search directly via simple commands.
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.
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.
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.
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.
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.
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.
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.
This guide walks through building a resilient Python client for locally hosted Ollama models, covering retry decorators, health checks, monitored sessions, utility functions for code extraction and caching, prompt formatting, and a complete Docker deployment with configuration examples.
This article presents a two‑stage, cache‑enabled pipeline that extracts text blocks from a PDF with PyMuPDF, translates them via a large‑language‑model API, and re‑renders each page as an image with Chinese text overlaid to keep the original layout, along with full Python code and usage instructions.
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%.
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.
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.
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.
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.
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.
GLM-5, a new large language model with 744 B parameters and 28.5 T tokens of training data, introduces DeepSeek sparse attention and an asynchronous RL system called slime, delivering strong benchmark gains on complex system engineering, long‑horizon agent tasks, and surpassing many open‑source competitors.
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.
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.
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.
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.
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.
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.
The article details how Aliexpress built an AI‑driven recruitment agent that combines NL2SQL smart filtering, a dual‑Agent voice interaction framework, low‑latency serverless deployment, and real‑time quality inspection, achieving sub‑second response times and a ten‑percent boost in intent rates.
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.
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.
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.
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.
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.
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.
This tutorial explains the OpenAI‑style request and response schema, demonstrates low‑level API calls with the requests library, compares them to the high‑level openai package, and walks through building a streaming multi‑turn chatbot that interacts with a locally hosted large language model.
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.
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.
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.
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.
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.
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.
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.
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.
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.
GLM-4.7 scores 68 points to rank sixth worldwide and first among open‑source models, surpassing Claude 4.5 Sonnet, with strong reasoning performance, fast generation speed, but higher cost and weaker code‑generation and math abilities compared to rivals.
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.
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 %.
The article examines Postal Savings Bank's transition from fragmented, low‑quality requirement documents to a standardized, AI‑enhanced demand knowledge base, detailing the challenges, the three‑dimensional collaboration and closed‑loop iteration framework, technical standards, core modules, and measurable improvements in document generation, duplicate detection, and semantic retrieval.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
The Postal Savings Bank built a domain‑specific legal large model using a fine‑tuned base LLM, RAG‑enhanced retrieval and LoRA incremental pre‑training, cutting contract‑review time by more than 50%, standardising opinions and enabling a scalable intelligent compliance platform for the banking industry.
