Image Captioning

Gender bias in large vision-language models (LVLMs) undermines their fairness and reliability, compromising output trustworthiness. Current mitigation methods rely on training-phase adjustments or post-hoc calibration, b…

Visual Grounding Image Captioning Text Generation

SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation

2026-09-15 · Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang 외 arxiv

Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in …

Visual Question Answering Reinforcement Learning Visual Grounding Image Captioning

FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation

2026-09-15 · Guangyu Sun, Shlok Kumar Mishra, Wentao Bao, Robert Zhenheng Yang 외 arxiv

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks g…

Representation Learning Cross-Modal Retrieval Image Captioning

A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss

2026-09-01 · Suryaansh Jain, Rahasya Barkur, Vishal G, Ryan Rossi 외 hf

An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss the attributes, counts, textures, materia…

Image Captioning

Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding

2026-08-27 · Gabriel Pirlogeanu, Dan Oneata, Horia Cucu, Herman Kamper arxiv

In many low-resource settings, even just eliciting speech for data collection is difficult. One promising approach has been to ask speakers to describe images. But how do we build models from such visually grounded speec…

Visual Grounding Image Captioning Keyword Spotting

Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models

2026-08-26 · Raúl Vázquez, Aman Sinha, Chuyuan Li, Claudio Savelli 외 arxiv

In 2026, we held the fourth iteration of the SHROOM Shared Task series: SHROOM-Visions (\textbf{S}hared-task on \textbf{H}allucinations and \textbf{R}elated \textbf{O}bservable \textbf{O}vergeneration \textbf{M}istakes i…

Image Captioning Text Generation

전체 2,089편 보기 →