The paper investigates how to best integrate large language model (LLM) guidance into visual question answering (VQA) systems. By prompting the 70‑billion‑parameter Llama 3.3 model to identify visual concepts, distractors, and external facts for each question, the authors inject this guidance into a frozen Vision Transformer (ViT) and a T5 text‑to‑text model via two methods: decision‑level late fusion and attention‑matrix injection. On the OK‑VQA benchmark, the shallow late‑fusion approach outperforms the deeper attention injection, achieving 39.4% exact match versus 31.8%, and a paraphrasing pipeline further expands the training set tenfold, indicating that the depth of integration should match the data regime.
By Aneerban Saha, Vijay Kumar, Sameer Madhav D., Priyam Srivastava, Dhruv Bansal
MEVL-STP introduces a two‑stage pipeline for spotting arbitrarily shaped scene text. The detection stage fuses features from six frozen vision encoders via a hierarchical Feature Pyramid Network and a Progressive Scale Expansion network to produce precise polygon masks. The recognition stage then crops these masks and feeds them to a fine‑tuned Qwen3‑VL‑8B‑Instruct model, achieving state‑of‑the‑art detection and end‑to‑end performance on CTW1500, Total‑Text, and ICDAR 2015 without synthetic pretraining.
By Aman Anand, Partha Pratim Roy, Shivakumara Palaiahnakote
The paper introduces a controlled benchmark for evaluating large language models (LLMs) on key‑value pair extraction from documents with varying levels of OCR noise. It tests 136 configurations across five instruction‑tuned open‑weight LLMs, three datasets, and four text‑quality conditions, using deterministic decoding to generate 17,688 document‑level inferences. The study finds that clean‑text performance does not reliably predict real‑world robustness, model rankings can reverse under noisy conditions, and few‑shot demonstrations do not always improve accuracy, highlighting reliability risks in OCR‑to‑LLM pipelines.
By Zahra Anvari
LensVLM is an inference framework and post‑training recipe that lets Vision‑Language Models (VLMs) process compressed images of text by selectively expanding only the relevant parts back to full resolution. Using Qwen3.5‑9B‑Base, LensVLM achieves accuracy comparable to full‑text models at 4.3× compression and outperforms other compression baselines up to 10.1× across seven text QA benchmarks, while also improving performance on multimodal document and code tasks as compression increases.
By Roy Xie, Dan Friedman, Donghan Yu, Bowen Pan, Christopher Fifty, Jang-Hyun Kim, Xianzhi Du, Zhe Gan, Vivek Rathod, Bhuwan Dhingra
arXiv:2602. 00593v4 Announce Type: replace-cross Abstract: Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation.
By Yifan Jiang, Cong Zhang, Bofei Zhang, Qiaofeng Zheng, Yifan Yang, Bingzhang Wang, Yew-Soon Ong
arXiv:2605. 16409v3 Announce Type: replace-cross Abstract: Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images containing small or degraded text, cluttered layouts, occlusion, handwriting, and complex typography.
By Qinwu Xu, Yifan Jiang, Haoyu Ren
arXiv:2606. 00435v1 Announce Type: cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question.
By Sayeed Shafayet Chowdhury, Md. Shaown Miah
We present HunyuanOCR-1. 5, a lightweight end-to-end OCR-specialized vision-language model.
The paper presents ChatNDE Figure to Caption, an AI system that automates the interpretation of nondestructive evaluation (NDE) images. It combines a Vision‑and‑Language Pretraining (VLP) approach using ResNet50 for visual feature extraction and GPT‑2 for natural‑language captioning, evaluated with BLEU scores. Additionally, a Visual Question Answering (VQA) model is integrated to answer specific queries about the images, enhancing interactivity for field inspectors.
By Mehrdad Shafiei Dizaji, Hoda Azari
arXiv:2608.28707v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with quest...
By Anoop Senthil
arXiv:2608. 20122v1 Announce Type: new Abstract: Large multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to adversarial visual text that is readable to humans but challenging for models to localize and recognize.
By Linhan Cao, Siyuan Li, Jun Lan, Liangbo He, Guannan Li, Xiaolei Huang, Jun Jia, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Wei Sun
arXiv:2609.15640v1 Announce Type: cross
Abstract: Long-text image--text congruence scoring is increasingly important for vision-language systems that must evaluate whether detailed textual descriptio...
By Alessandro Gambetti, Qiwei Han