Diffusion Technology Achieves 10x Faster Text Generation

Inception Labs has introduced the Mercury diffusion language model family, a new approach to speed up text generation. Unlike traditional sequential (autoregressive) language models, Mercury uses diffusion technology, promising significant improvements in speed and efficiency. While currently focused on code generation, this technology could transform the entire field of text generation.

How Diffusion Models Work

Diffusion models gradually recover clean, meaningful information from noisy data. The process has two steps:

  • Forward Process: Noise is added step by step to real data until it becomes random noise.

  • Reverse Process: The model learns to remove the noise, eventually producing high-quality data.

Based on principles from non-equilibrium thermodynamics, diffusion models offer advantages like more stable training, easier parallel processing, and flexible design. This helps them outperform traditional GANs or autoregressive models in tasks like generation.

Inception Labs’ Mercury Models

Unlike traditional models (which generate text left-to-right), Mercury uses a “coarse-to-fine” approach. Starting with pure noise, it refines the output over multiple steps.

Its main application today is code generation. Mercury Coder provides an interactive preview of generated code, improving developers’ workflows by showing how random characters evolve into functional code. The model can generate thousands of tokens per second—up to 10 times faster than traditional methods. Mercury is also available in downloadable versions, making it easy for businesses to integrate into their systems.

Potential Impact of Diffusion Technology

  • Speed & Efficiency: Runs on standard GPUs, speeding up development cycles and application response times.

  • Lower Cost: Works with existing infrastructure, reducing the need for specialized hardware.

  • New Research Opportunities: Combining diffusion and autoregressive models could advance tasks requiring structured logic, like coding or math problem-solving. 

Share this post
Apple’s AI Doctor Plans
Apple is developing an AI-powered health coach, codenamed “Project Mulberry,” designed to give personalized advice for everyday life. The new feature is expected to be included in a future iOS 19.4 update—likely in spring or summer 2026—and will first launch in the US.
 Credit-based Windows Notepad usage with Copilot integration
Microsoft is introducing a new feature in Windows Notepad that allows you to use Microsoft Copilot, an artificial intelligence to improve your writing in Notepad. The feature allows you to rephrase your writing, generate a summary, or make other text tweaks such as adjusting the tone or style of text.
TxGemma - New Open Model for Drug Development
One of the biggest challenges in drug development is finding lead compounds beyond the clinical phase, as 90% of candidates fail in the initial trial phase. In this context, TxGemma—an open model collection developed on top of Google's DeepMind Gemma and its family of modern, lightweight open models—represents a breakthrough. TxGemma aims to harness the power of large language models to improve the efficiency of therapeutic discovery, from identifying promising targets to predicting clinical trial outcomes.
Artificial Intelligence in Practice: An Innovative Collaboration between NVIDIA and Boston Dynamics
Modern robotics has grown hand in hand with artificial intelligence and simulation technologies. NVIDIA’s Isaac™ GR00T research project aims to speed up the development of humanoid robots with new basic models. Meanwhile, Boston Dynamics uses its long experience and modern computing platforms to create robots that move in a natural, lifelike way. Their partnership is a new milestone in humanoid robotics, as it combines simulation, learning, and real-world testing to create adaptive, real-time robotic solutions.