Connecting text and visual modalities plays an essential role in generative intelligence. For
this reason, inspired by the success of large language models, significant research efforts …

Current universal segmentation methods demonstrate strong capabilities in pixel-level
image and video understanding. However, they lack reasoning abilities and cannot be …

Abstract Generalized Referring Expression Segmentation (GRES) extends the scope of
classic RES to refer to multiple objects in one expression or identify the empty targets absent …

While Ferret seamlessly integrates regional understanding into the Large Language Model
(LLM) to facilitate its referring and grounding capability, it poses certain limitations …

Hierarchical segmentation entails creating segmentations at varying levels of granularity.
We introduce the first hierarchical semantic segmentation dataset with subpart annotations …

Recent advancements have empowered Large Language Models for Vision (vLLMs) to
generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless …

Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by
allowing them to abstain from answering when uncertain. However, when deploying a vision …

Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on
$\texttt {< SEG>} $ token as a text prompt to jointly optimize the vision-language model (eg …

Image editing technologies are tools used to transform, adjust, remove, or otherwise alter
images. Recent research has significantly improved the capabilities of image editing tools …

We present SegLLM, a novel multi-round interactive reasoning segmentation model that
enhances LLM-based segmentation by exploiting conversational memory of both visual and …