BestHub
Sign in
Meituan Technology Team
Author

Meituan Technology Team

Over 10,000 engineers powering China’s leading lifestyle services e‑commerce platform. Supporting hundreds of millions of consumers, millions of merchants across 2,000+ industries. This is the public channel for the tech teams behind Meituan, Dianping, Meituan Waimai, Meituan Select, and related services.

658
Articles
0
Likes
2.2k
Views
0
Comments
Recent Articles

Latest from Meituan Technology Team

100 recent articles max
Meituan Technology Team
Meituan Technology Team
May 14, 2026 · Artificial Intelligence

General 365: Meituan LongCat’s Open‑Source Benchmark Redefines LLM Reasoning Evaluation

The General 365 benchmark, built from 365 original seed questions and 1,095 variants across eight reasoning challenges, reveals that most mainstream large language models struggle with everyday logical tasks, achieving at most 62.8% accuracy and requiring far more tokens than on traditional subject‑specific tests.

AI reasoningGeneral 365LLM evaluation
0 likes · 9 min read
General 365: Meituan LongCat’s Open‑Source Benchmark Redefines LLM Reasoning Evaluation
Meituan Technology Team
Meituan Technology Team
May 7, 2026 · R&D Management

Managing AI‑Generated Code with Agent‑Based Evaluation: Refactoring 310K Lines of Code

When over 90% of a codebase is produced by AI, system quality hinges on constraining AI rather than speed, and this article details how a team used an agent‑based evaluation framework, unified standards, and incremental refactoring to turn 310,000 lines of AI‑written code into a maintainable, low‑debt system.

AI GovernanceAI codingR&D management
0 likes · 21 min read
Managing AI‑Generated Code with Agent‑Based Evaluation: Refactoring 310K Lines of Code
Meituan Technology Team
Meituan Technology Team
Apr 23, 2026 · Artificial Intelligence

LARYBench Introduces an ImageNet‑Style Benchmark for Embodied Action Representations Learned from Human Video

LARYBench (Latent Action Representation Yielding Benchmark) provides the first systematic, ImageNet‑scale evaluation for implicit action representations derived from large‑scale human video, decoupling representation quality from downstream control, and shows that general‑purpose vision models outperform specialized embodied models in both action generalization and control precision across diverse robot morphologies and environments.

Vision-Language-Actionaction representationbenchmark
0 likes · 13 min read
LARYBench Introduces an ImageNet‑Style Benchmark for Embodied Action Representations Learned from Human Video
Meituan Technology Team
Meituan Technology Team
Apr 16, 2026 · Artificial Intelligence

Can End-to-End Diffusion TTS Beat Traditional Pipelines? Inside LongCat-AudioDiT

LongCat-AudioDiT introduces a wave‑VAE plus diffusion Transformer architecture that eliminates intermediate spectrograms, solves training‑inference mismatch with dual constraints, replaces classifier‑free guidance with adaptive projection guidance, and achieves state‑of‑the‑art zero‑shot voice cloning performance on multiple benchmarks.

AI researchText-to-Speechaudio generation
0 likes · 12 min read
Can End-to-End Diffusion TTS Beat Traditional Pipelines? Inside LongCat-AudioDiT
Meituan Technology Team
Meituan Technology Team
Apr 2, 2026 · Artificial Intelligence

Can AI Really Prove Math? Inside LongCat‑Flash‑Prover’s Breakthrough

LongCat‑Flash‑Prover, an open‑source AI model that decomposes theorem proving into auto‑formalization, sketching, and proving with tool‑integrated reasoning, achieves SOTA results on MiniF2F‑Test (97.1% with only 72 inference steps) and strong performance on MathOlympiad‑Bench and PutnamBench, demonstrating that AI can move from guessing answers to rigorous, verifiable mathematical proofs.

AI theorem provingLean4formal verification
0 likes · 14 min read
Can AI Really Prove Math? Inside LongCat‑Flash‑Prover’s Breakthrough
Meituan Technology Team
Meituan Technology Team
Mar 12, 2026 · Frontend Development

How Qwik.js Resumability Supercharged Meituan‑Dianping’s M‑Site Performance

The article details how Meituan‑Dianping’s growth team rebuilt its high‑traffic M‑site using Qwik.js, replacing a legacy Vue‑based stack with a resumable SSR architecture that eliminates hydration overhead, dramatically reduces first‑screen JS size, and boosts conversion metrics across weak‑network and low‑end devices.

QwikResumabilitySSR
0 likes · 40 min read
How Qwik.js Resumability Supercharged Meituan‑Dianping’s M‑Site Performance
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 ExpansionLarge Language Model
0 likes · 14 min read
How LongCat‑Flash‑Thinking‑2601 Achieves Real‑World Generalization for Agents
Meituan Technology Team
Meituan Technology Team
Jan 23, 2026 · Artificial Intelligence

How EvoCUA Set a New Open‑Source SOTA for Computer‑Use Agents with Evolutionary Learning

EvoCUA, a native computer‑use agent from Meituan, combines a verifiable data‑synthesis engine, a ten‑thousand‑level sandbox infrastructure, and an experience‑driven learning paradigm to overcome data‑scaling and feedback challenges, achieving a 56.7% success rate on the OSWorld benchmark and surpassing previous open‑source models.

AI agentData SynthesisOSWorld
0 likes · 27 min read
How EvoCUA Set a New Open‑Source SOTA for Computer‑Use Agents with Evolutionary Learning
Meituan Technology Team
Meituan Technology Team
Jan 8, 2026 · Artificial Intelligence

Must‑Read AAAI 2026 Papers: Efficient Reasoning, Annealing, Multimodal Diffusion & More

This article curates eight AAAI 2026 papers authored by the Meituan research team, covering verifiable stepwise rewards for LLM reasoning, annealing strategies in large‑scale training, process reward models, competence‑difficulty sampling, high‑fidelity visual text rendering, counterfactual fusion, compress‑then‑rank reranking, and cross‑modal quantization for generative recommendation, with direct PDF links for each work.

AAAI2026LLMcounterfactual
0 likes · 14 min read
Must‑Read AAAI 2026 Papers: Efficient Reasoning, Annealing, Multimodal Diffusion & More