Tongyi Lab
@Ali_TongyiLab • 26,027 subscribers
We advance the development of ASI and foster open source collaboration towards a smarter future. Discord: https://t.co/BtsFsAUsvT
Videos
AI excels in the virtual world, but acting in the physical world is a whole different challenge. Why is it so hard to get a robot to fetch an egg without freezing? 🤔 Check out our new explainer video on Embodied Intelligence. We discuss the gap between robot "Thinking" and "Acting,"
Tongyi Lab5,634,584 Aufrufe • vor 3 Monaten
1/6 Introducing Qwen3.5-LiveTranslate: Next-gen real-time interpretation is here. 🌍 We’re breaking down language barriers with 3,500+ language pairs, ultra-low latency, visual context, real-time voice cloning, and hotword customization. Engineered to help you ship native, frictionless real-time translation experiences to a global audience.
Tongyi Lab4,113,995 Aufrufe • vor 5 Monaten
We have officially launched Fun-ASR1.5, a major update to our end-to-end speech recognition model. This release focuses on three core pillars: broader language coverage, language switching, and production-ready text output. Key Features: • Multilingual Support: Supports high-accuracy recognition for 30 languages across Asia, Europe, and the Middle East within a single model. • Language Switching: Handles mixed-language speech (Code-Switching) natively, automatically detecting and transcribing language shifts without the need for manual tagging. • Professional Text Output: Delivers "ready-to-use" text with smart punctuation and automatic formatting for dates, numbers, and currencies. Fun-ASR1.5 bridges the gap between raw audio and professional documentation, providing a reliable engine for global communication.
Tongyi Lab3,917,307 Aufrufe • vor 6 Monaten
How to create digital fireworks on your computer? Choose Qwen3.7-Max and try it out!
Tongyi Lab2,709,095 Aufrufe • vor 4 Monaten
🚀 Qwen-Image-2512: Finer Details, Greater Realism We are thrilled to announce the Qwen-Image-2512 open-source release! This December update pushes the boundaries of our text-to-image foundational model, moving from "AI-generated" looks to true photorealism. What makes 2512 exceptional? · Enhanced Human Realism : We’ve eliminated the artificial "AI look" by capturing intricate facial details—like wrinkles and pores—and ensuring better adherence to body postures. · Finer Natural Detail : Experience notably more detailed rendering of landscapes, misty waterfalls, and animal fur with distinct, individual strands. · Advanced Text Rendering : Achieve professional-grade layout for complex infographics and PPT slides with unprecedented textual accuracy.
Tongyi Lab1,688,620 Aufrufe • vor 9 Monaten
Found a hardcore LoRA workflow! Generate a PLY point cloud --> Adjust angle in editor -->Refine with Qwen-Image-Edit-2511 Gaussian Splash LoRA. It accurately restores complex perspective shifts. As shown in the demo, it handles 3D rotation and can even restore high-def details from blurry close-ups. Within a 45° range, the consistency is unmatched. Huge thanks to 大雄 for this contribution! 🫡
Tongyi Lab1,493,613 Aufrufe • vor 9 Monaten
We released Qwen3-Omni-Flash (2025-12-01 version) API Service. Smarter interaction, more human expression: · A/V Interaction: Significant boost in instruction following. Solves "dumbing down" in casual chats with rock-solid stability. · Precise Control: Enhanced System Prompt adherence for specific personas, styles, and lengths. · Multilingual Mastery: Solved language switching instability. Now supports 119 text languages, 19 for speech understanding, and 10 for speech generation. · Human-like Speech: Adaptive speed and prosody. No more drag—sounds just like a real person.
Tongyi Lab1,637,133 Aufrufe • vor 10 Monaten
Complex instruction following is critical for LLM agents and applications. IOPO with notable improvements is proposed to consider both input and output preference pairs , not only aligning with response preferences but also meticulously exploring the instruction preferences.
Tongyi Lab1,762,969 Aufrufe • vor 1 Jahr
1/4 We’re releasing MAI-UI—a family of foundation GUI agents. It natively integrates MCP tool use, agent user interaction, device–cloud collaboration, and online RL, establishing state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld. To meet real-world deployment constrains, MAI-UI includes a full-spectrum of sizes, including 2B, 8B, 32B and 235B-A22B variants. We are publicly releasing two models: MAI-UI-2B and MAI-UI-8B.
Tongyi Lab855,757 Aufrufe • vor 9 Monaten
Curious about Wan2.5-Preview? Here's everything you need to know in 2 minutes! ⏱️ Wan2.5-Preview natively supports audio-visual synchronization, with massive upgrades to video, image generation, and editing for commercial-grade content. Watch our video below to see it all in action!
Tongyi Lab1,073,009 Aufrufe • vor 1 Jahr
1/4 How to get the most from a few high‑quality, trusted examples—not by piling up data? Tongyi Lab shifts from data‑centric to sample‑centric and presents LPPO, a Progressive Optimization RL framework to break reasoning bottlenecks: master each problem, not just add more.
Tongyi Lab1,081,000 Aufrufe • vor 1 Jahr
Your AI Voice Partner: Smart, Empathetic & Useful Open-sourced now!!! Introducing Fun-Audio-Chat — a new end-to-end voice model, more than just chat. · An empathetic companion that understands tone and emotion. · A productivity helper that follows voice commands to get things done. · Leader in multiple benchmarks (OpenAudioBench, MMAU, etc.). · End-to-end S2S architecture — lower latency, higher efficiency. · Dual-resolution design — reduces GPU cost by ~50% · Supports voice function calling — just speak to complete tasks.
Tongyi Lab256,132 Aufrufe • vor 10 Monaten
1/4Introducing Qwen3-Coder-Next: Our latest open-weights model designed specifically to power the next generation of autonomous Coding Agents. Built on Qwen3-Next, this model is engineered to handle complex, long-horizon programming tasks with unprecedented efficiency. High-performance agentic intelligence is now in your hands.
Tongyi Lab212,645 Aufrufe • vor 8 Monaten
Introducing Tongyi Fun – Alibaba’s enterprise-grade audio foundation model. Powered by Fun-ASR and Fun-CosyVoice it advances voice AI beyond “hearing and speaking” to truly understand context, transcribe with high accuracy, and speak with natural expressiveness—even in complex enterprise environments. ✅ Understands deeply: Trained on tens of millions of hours of real-world audio, with industry-specific terminology across finance, tech, manufacturing, and more. ✅ Transcribes accurately: A context-enhanced architecture with RAG minimizes errors, hallucinations, and cross-language interference. ✅ Speaks expressively: Delivers natural, stable, multilingual speech synthesis with cross-lingual voice cloning.
Tongyi Lab280,542 Aufrufe • vor 1 Jahr