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 %.
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.
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 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.
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.
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.
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.
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.
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.
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.
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.
The article demonstrates how Tencent's Hunyuan large model can generate and iteratively refine Python scripts that automatically compare Excel‑based reports, highlight differences, and handle multiple files, thereby streamlining regression testing and reducing manual effort.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
DeepSeek‑V3.2‑Exp, the latest experimental large‑language model, is open‑sourced with a paper, featuring a million‑token context window, a new sparse attention mechanism, GRPO‑enhanced reasoning, and detailed cost‑analysis showing up to ten‑fold inference savings.
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.
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.
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.
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.
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.
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.
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.
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.
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.
DeepSeek released the V3.1‑Terminus model, fixing the notorious “extreme” character bug, improving language consistency and Agent capabilities, and achieving notable benchmark gains that surpass Gemini 2.5 Pro, while providing download links and hinting at upcoming V4/R2 releases.
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.
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.
This article examines Tencent's large language model deployments across content generation, intelligent customer service, and role‑playing, detailing the underlying SFT, Retrieval‑Augmented Generation, GraphRAG, and Agent technologies that enable smarter, more reliable AI solutions.
DeepSeek‑R1, the first mainstream large language model to pass peer review in Nature, was trained for $294,000 using 648 H800 GPUs, and its RL‑enhanced version, DeepSeek‑R1‑Zero, achieved up to 86.7% pass@1 on AIME 2024, outperforming human averages across math, coding, and science tasks.
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.
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.
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.
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.
This guide walks through deploying a local LLM on Kubernetes using Ollama for model serving and Open-WebUI for a web interface, covering namespace creation, storage setup, GPU support, service exposure, validation, and model download to ensure privacy, low latency, and high availability.
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.
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.
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.
Deploying large‑model AI in customer service can boost efficiency, but without proper boundaries, feedback loops, and emotional handling it often creates costly mistakes, brand damage, and poor user experience, as this article explains the six most frequent traps and how to sidestep them.
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.
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.
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.
Meituan has open‑sourced LongCat‑Flash‑Chat, a 5.6‑trillion‑parameter Mixture‑of‑Experts model that activates only a fraction of its weights per token, delivering mainstream‑level performance, high inference speed, and low cost for complex agent applications.
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.
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.
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.
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.
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.
