Lumiere

QWEN CHAT GitHub Hugging Face ModelScope Kaggle DEMO DISCORD Introduction Today, we are excited to announce the release of Qwen3, the latest addition to the Qwen family of large language models. Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tier models such as DeepSeek-R1, o1, o3-mini, Grok-3, and Gemini-2.5-Pro. Additionally, the small MoE model, Qwen3-30B-A3B, outcompetes QwQ-32B with 10 times of activated parameters, and even a tiny model like Qwen3-4B can rival the performance of Qwen2.

DESCRIPTION META TAG

Abstract page for arXiv paper 2602.04804: OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

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.

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

LeVo: High-Quality Song Generation with Multi-Preference Alignment

Abstract page for arXiv paper 2601.14251: LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

GITHUB HUGGINGFACE MODELSCOPE SHOWCASE From Chatbot to Autonomous Agent We are proud to present Tongyi DeepResearch, the first fully open‑source Web Agent to achieve performance on par with OpenAI’s DeepResearch across a comprehensive suite of benchmarks. Tongyi DeepResearch demonstrates state‑of‑the‑art results, scoring 32.9 on the academic reasoning task Humanity’s Last Exam (HLE), 43.4 on BrowseComp and 46.7 on BrowseComp‑ZH in extremely complex information‑seeking tasks, and achieving a score of 75 on the user‑centric xbench‑DeepSearch benchmark, systematically outperforming all existing proprietary and open‑source Deep Research agents.