We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO

Constant memory long CoT is here!

MiMo-VL technical report, models, and evaluation suite are out! 🤗 Models: huggingface.co/XiaomiMiMo/MiM… (or RL) Report: arxiv.org/abs/2506.03569 Evaluation Suite: github.com/XiaomiMiMo/lmm… Looking back, it's incredible that we delivered such compact yet powerful vision-language

🔬 The HKU team presents ParallelComp: a training-free technique for efficient context length extrapolation in LLMs—from 8K up to 128K tokens—on a single A100 GPU, with minimal performance loss. 📄 Paper: arxiv.org/abs/2502.14317 💻 Code: github.com/menik1126/Para…

The RL recipe from us, with everything fully open! hkunlp.github.io/blog/2025/Pola…

Huge milestone from the team! A blazing-fast diffusion LLM built for chat, delivering real-time performance at commercial scale. If you liked Mercury Coder for code, you'll love this for conversation.

Thanks for sharing our work!!!🙏Code release is in progress😺

Fun especially considering this is a shiba :)

🤖Can diffusion models write code competitively? Excited to share our latest 7B coding diffusion LLM!!💻 With DiffuCoder, we explore how they decode, why temperature🔥 matters, and how to improve them via coupled-GRPO that speaks diffusion!!📈 Code: github.com/apple/ml-diffu… 🧵

🌳TreeSynth: Synthesizing large-scale diverse data from scratch! Struggling with repetition and space collapse in data synthesis? 🤔 Our latest research mitigates this challenge through innovative tree-guided subspace partitioning. ✨Introducing TreeSynth—a novel framework

We present DreamOn: a simple yet effective method for variable-length generation in diffusion language models. Our approach boosts code infilling performance significantly and even catches up with oracle results.

🚀 Thrilled to announce Dream-Coder 7B — the most powerful open diffusion code  LLM to date.

📢 Update: Announcing Dream's next-phase development. - Dream-Coder 7B: A fully open diffusion LLM for code delivering strong performance, trained exclusively on public data. - DreamOn: targeting the variable-length generation problem in dLLM!

Xinyu Yang from CMU will be giving a talk titled "Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation" at Friday July 25 11am HKT (Thursday July 24 8pm PDT). Link to talk: hku.zoom.us/j/92651812689?…

🚀 MiMo‑VL 2508 is live! Same size, much smarter. We’ve upgraded performance, thinking control, and overall user experience. 📈 Benchmark gains across image + video: MMMU 70.6, VideoMME 70.8. Consistent improvements across the board. 🤖 Thinking Control: toggle reasoning with

Jinjie Ni Jinjie Ni from NUS will be giving a talk titled "Diffusion Language Models are Super Data Learners" at Friday Aug 22 11am HKT. link to talk: hku.zoom.us/j/94293996114?…