M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA

Venkata Kesav Venna Sai Madhusudan Gunda Jyothi Swaroopa Jinka H. Sagar Anirudh Srinivasan Ravi Kiran Sarvadevabhatla

· 1 citation · 59 references

TL;DR

M3Grounder sets a new state-of-the-art in grounded DocVQA, advancing from coarse boxes to hierarchical, fine-grained and contextually grounded mask evidence.

Semantic Scholar

View source

Similar papers

Improving Scene Text Recognition in Multimodal Large Language Models using Visual Text Grounding

This work introduces three tasks/objectives for reverse localization of text as an instruction-tuning mechanism, where the model is guided to extract textual content based on spatial localization cues, thereby enhancing its spatial grounding ability.

Shashank Krishna Vempati, Chetan Arora · 0 citations

Preprint Aug 2026

ID-VTG: Image-Disambiguated Video Temporal Grounding

The Visually-Guided Disambiguation Aggregation Aggregation (VGD-Agg) framework is proposed, a framework based on a dual-branch fast-slow architecture that enhances discriminability via two learnable tokens and achieves state-of-the-art results on the proposed benchmarks.

Minghang Zheng, Jing Wei, Hong-Yi Yang et al. · 0 citations

Preprint Aug 2026

CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering

CapProbe is introduced, a full-scene dense QA benchmark that turns detailed caption evaluation into region-aligned factual checking and is cost-effective: by converting unconstrained scalar scoring into structured MCQ reading, it reduces open-ended scoring bias while remaining judge-conditioned and yields relatively st...

Mouxiao Huang, Qi Yan, Bo-Rui Jiang et al. · 0 citations

Preprint Jul 2026

TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation

This work proposes a hybrid pipeline coupling T2I generation with context-aware image-to-image (I2I) editing, and introduces VRAIN (Verified Rare-class Augmentation via INstructed editing), a novel I2I editor to strengthen supervision for rare classes.

H. Song, Seokhun Choi, Hoseok Do · 0 citations

Jul 2026

Evidence-Backed Video Question Answering

ST-Evidence is introduced, the first human-verified benchmark for both discriminative and generative pixel-level grounding, and scalable, automated generation pipelines are developed to create ST-Evidence-Instruct, a 160k-scale dataset bridging high-level reasoning with fine-grained grounding.

Shijie Wang, Honglu Zhou, Ziyang Wang et al. · arXiv.org · 0 citations

Preprint Aug 2026

Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing

Modern text-to-image (T2I) models often have similar total scores but different strengths, making practical selection difficult. Fine-grained benchmarks decompose prompts into questions, yet often return them to prompt scores and fixed categories, weakening attribution and ignoring complexity. Related requirements are...

Shao-An Zhao, Fang Zhao, Xueqiang Guo et al. · 0 citations