Author

Xiaomi Tech

Chat about technology with Xiaomi and change life together.

Articles

Likes

115

Views

Comments

Latest from Xiaomi Tech

43 recent articles

Xiaomi Tech

Jul 2, 2026 · Artificial Intelligence

One‑Step Face Video Restoration and 15.7× Faster Streaming Video Models – Xiaomi Papers at ECCV 2026

Xiaomi's AI team showcased twelve ECCV 2026 papers that advance visual understanding and generation, including a single‑step high‑quality face‑video restoration method, a streaming VideoLLM that thinks while watching with a 15.7× speed boost, relative aesthetic scoring, GUI agents, in‑image translation, multimodal retrieval, and several autonomous‑driving world‑model breakthroughs.

Large Language Modelsautonomous drivingcomputer vision

0 likes · 21 min read

One‑Step Face Video Restoration and 15.7× Faster Streaming Video Models – Xiaomi Papers at ECCV 2026

Xiaomi Tech

Jun 26, 2026 · Industry Insights

How Xiaomi’s WPC Qi Plugfest Accelerates Chinese Wireless Charging into Global Standards

The June 2026 WPC Qi Off‑cycle Meeting in Beijing, hosted by Xiaomi, gathered over 20 industry players to discuss, test and verify the upcoming Qi 50 W standard, highlighting the challenges and strategic push for Chinese small‑inductance, low‑voltage, high‑power wireless‑charging solutions to enter global standards.

50WChinaIndustry Standards

0 likes · 11 min read

How Xiaomi’s WPC Qi Plugfest Accelerates Chinese Wireless Charging into Global Standards

Xiaomi Tech

Jun 18, 2026 · Artificial Intelligence

What Xiaomi Miloco 2.0 Can Do: A Deep Dive into the New AI Home Assistant

Xiaomi’s Miloco 2.0 transforms whole‑home smart devices from simple command executors into an AI‑driven household manager that can see, hear, remember habits, handle long‑term tasks, and act proactively, while remaining open‑source and privacy‑focused.

AIHome AutomationMiMo

0 likes · 10 min read

What Xiaomi Miloco 2.0 Can Do: A Deep Dive into the New AI Home Assistant

Xiaomi Tech

Jun 12, 2026 · Artificial Intelligence

Building a Universal Sound Model: Xiaomi Dasheng’s 8‑GPU AI Engineering Journey

This article details Xiaomi Dasheng’s end‑to‑end approach to creating a universal sound representation model, from choosing a Masked Autoencoder pre‑training framework and scaling up to 1.2 B parameters on 300 TB of diverse audio, to six‑dimensional annotation, unified understanding‑generation architecture, and future audio‑scene generation.

Xiaomi Dashengaudio generationaudio representation

0 likes · 13 min read

Building a Universal Sound Model: Xiaomi Dasheng’s 8‑GPU AI Engineering Journey

Xiaomi Tech

Jun 11, 2026 · Artificial Intelligence

MiMo Code 0.1.0 Released: Model‑Agent Collaboration Drives Self‑Evolving AI Coding

MiMo Code 0.1.0, an open‑source terminal AI coding assistant built on OpenCode, introduces a persistent memory system, a Compose mode that orchestrates design‑to‑test workflows, voice input, and benchmark‑proven superiority over Claude Code on SWE‑Bench and Terminal Bench, while supporting multiple large‑model APIs.

AI coding assistantCompose modeOpen Source

0 likes · 7 min read

MiMo Code 0.1.0 Released: Model‑Agent Collaboration Drives Self‑Evolving AI Coding

Xiaomi Tech

Jun 9, 2026 · Artificial Intelligence

What 1000 tokens/s Really Means: Inside Xiaomi MiMo’s UltraSpeed Breakthrough

The article explains how Xiaomi’s MiMo‑V2.5‑Pro‑UltraSpeed mode achieves a record‑breaking 1000 tokens per second inference speed, why such ultra‑fast performance matters for real‑time AI applications, and the FP4 quantization, DFlash decoding and TileRT inference technologies that make it possible without sacrificing model quality.

DFlashFP4InferenceSpeed

0 likes · 10 min read

What 1000 tokens/s Really Means: Inside Xiaomi MiMo’s UltraSpeed Breakthrough

Xiaomi Tech

Jun 9, 2026 · Artificial Intelligence

How Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed Achieves 1000 TPS on a 1‑Trillion‑Parameter Model

Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed mode breaks the 1000 tokens‑per‑second barrier for a 1‑trillion‑parameter model by combining FP4 expert‑only quantization, DFlash block‑masked speculative decoding, and TileRT’s ultra‑low‑latency GPU system, and the API is now available through a limited‑time trial.

AI inferenceDFlashFP4 Quantization

0 likes · 13 min read

How Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed Achieves 1000 TPS on a 1‑Trillion‑Parameter Model

Xiaomi Tech

May 30, 2026 · Artificial Intelligence

How Xiaomi’s MiMo V2.5 Achieves 99% API Price Cut with Full‑Stack Inference Optimizations

The MiMo‑V2.5 series combines Hybrid Sliding‑Window Attention, Mixture‑of‑Experts and multimodal support with a complete redesign of KVCache management, tiered caching, prefix‑tree logic and scheduling, compressing KVCache to about one‑seventh of full‑attention models and delivering up to 40% faster Prefill, 30% lower TTFT and dramatically reduced inference costs that enable a 99% API price reduction.

Hybrid SWAKVCacheMiMo V2.5

0 likes · 12 min read

How Xiaomi’s MiMo V2.5 Achieves 99% API Price Cut with Full‑Stack Inference Optimizations

Xiaomi Tech

May 29, 2026 · Artificial Intelligence

ControlFoley: An Open‑Source Model for Fully Controllable Video Sound Generation

ControlFoley, released by Xiaomi's large‑model team, is an open‑source framework that lets creators generate video‑aligned sound effects while explicitly controlling content, style, and timing through text prompts, video dubbing, or reference audio, achieving SOTA performance on multiple benchmarks.

ControlFoleyOpen Sourceaudio synthesis

0 likes · 15 min read

ControlFoley: An Open‑Source Model for Fully Controllable Video Sound Generation

Xiaomi Tech

May 28, 2026 · Artificial Intelligence

Scaling AI Coding from Individuals to Teams: Xiaomi’s Engineering Practices

The article analyzes how Xiaomi’s AI coding initiative boosted individual developer speed but exposed organizational bottlenecks, and describes a three‑layer engineering solution—Unified Workflow (VAF), Code Knowledge Index (VKF), and Collaborative Workbench (eight‑claw)—that lowers entry barriers, builds searchable code knowledge, enables parallel task execution, and preserves team‑wide knowledge for sustainable productivity gains.

AI codingSoftware Engineeringcode knowledge base

0 likes · 19 min read

Scaling AI Coding from Individuals to Teams: Xiaomi’s Engineering Practices