Augini Documentation

Hunyuan-GameCraft

We present a simple yet effective technique to estimate lighting in a single input image. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.

DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance.

GITHUB HUGGING FACE MODELSCOPE DISCORD Today, we’re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we’re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.

Abstract page for arXiv paper 2602.07120: Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

Abstract page for arXiv paper 2601.14232: KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

Project landing page for WeDLM

Kimi K2 Thinking, Moonshot's best open-source thinking model.