Xiaomi-Lens-0 技術報告
Xiaomi-Lens-0 Technical Report
Xiaomi-Lens-0 是基於 Qwen3.5 構建的 4B 多模態模型,透過自身視覺表徵預測遮罩,以改善細粒度區域推理和指代理解。在 RefCOCO、RefCOCO+ 和 RefCOCOg 的全部八個 split 中,其指代理解平均較 Qwen3.5 高 5.6 分,並在所比較模型中取得最高分割 cIoU;它亦在所有感知基準上勝過 Qwen3.5。
Published on Oct 16
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
Xiaomi-Lens-0 is a 4B multimodal model that predicts masks from internal visual representations to improve fine-grained region reasoning and referring comprehension.
Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding. A key reason is that text-only supervision never specifies which regions support an answer. To close this gap, we present Xiaomi-Lens-0, a 4B MLLM built on Qwen3.5 that predicts masks from its own visual representations. Specifically, a lightweight decoder combines vision-encoder patch features with visual latents, the language model's mask-token states, so mask supervision reaches the shared backbone without an additional segmentation encoder. Because each latent decodes to a mask, the model can interleave reasoning with region-specific latents and thus think with visual latents, while grounded reasoning traces supervise the regions it visits during chain-of-thought. As a result, across all eight RefCOCO, RefCOCO+, and RefCOCOg splits, Xiaomi-Lens-0 gains 5.6 points on average over Qwen3.5 in referring comprehension and achieves the highest segmentation cIoU among compared models. Moreover, it surpasses Qwen3.5 across all perception benchmarks. Homepage: https://seerray-lab.github.io/Xiaomi-Lens-0{this https URL}
View arXiv page View PDF Project page GitHub 10 Add to collection
Get this paper in your agent:
hf papers read 2610.23279
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Image-Text-to-Text • 5B • Updated 25 minutes ago • 10 • 1SeerRay-Lab/Xiaomi-Lens-0
Datasets citing this paper 1
SeerRay-Lab/LensBench
Viewer • Updated about 7 hours ago • 4.8k
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.23279 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co