相关论文: BLUEX Revisited: Enhancing Benchmark Coverage with…

Most multilingual vision-and-language (V&L) research aims to accomplish multilingual and multimodal capabilities within one model. However, the scarcity of multilingual captions for images has hindered the development. To overcome this…

Large language models (LLMs) have achieved impressive performance across various natural language benchmarks, prompting a continual need to curate more difficult datasets for larger LLMs, which is costly and time-consuming. In this paper,…

This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal…

Video-text retrieval has been stuck in the information mismatch caused by personalized and inadequate textual descriptions of videos. The substantial information gap between the two modalities hinders an effective cross-modal representation…

Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever more detailed and…

We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on static, hand-curated sets of contest or textbook-style problems as proxies for…

Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This…

Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale open source literature…

Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, recommendation, and multi-step agentic inference pipelines. Yet current evaluation practices miss a fundamental question: Can captions…

Multimodal Large Language Models demonstrate strong performance on natural image understanding, yet exhibit limited capability in interpreting scientific images, including but not limited to schematic diagrams, experimental…

We focus on the automatic evaluation of image captions in both reference-based and reference-free settings. Existing metrics based on large language models (LLMs) favor their own generations; therefore, the neutrality is in question. Most…

Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of…

While deep-learning models have been shown to perform well on image-to-text datasets, it is difficult to use them in practice for captioning images. This is because captions traditionally tend to be context-dependent and offer complementary…

Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices…

This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…

Geometric reasoning remains a core challenge for Multimodal Large Language Models (MLLMs). Even the most advanced closed-source systems, such as GPT-O3 and Gemini-2.5-Pro, still struggle to solve geometry problems reliably, despite…

Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is…

The evaluation of machine-generated image captions poses an interesting yet persistent challenge. Effective evaluation measures must consider numerous dimensions of similarity, including semantic relevance, visual structure, object…

Large language models (LLMs) have emerged as powerful general-purpose interfaces for many machine learning problems. Recent work has adapted LLMs to generative visual tasks like image captioning, visual question answering, and visual chat,…

In this work, we present an unsupervised method for enhancing an image captioning model (in our case, BLIP2) using reinforcement learning and vision-language models like CLIP and BLIP2-ITM as reward models. The RL-tuned model is able to…