Related papers: Scaling Text-Rich Image Understanding via Code-Gui…

Multimodal large language models (MLLMs) are increasingly deployed in real-world, agentic settings where outputs must not only be correct, but also conform to predefined data schemas. Despite recent progress in structured generation in…

Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and…

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsistencies, and mode collapse when tasked with structured…

Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for…

We develop ImageNet-Think, a multimodal reasoning dataset designed to aid the development of Vision Language Models (VLMs) with explicit reasoning capabilities. Our dataset is built on 250,000 images from ImageNet21k dataset, providing…

The ability of large language models (LLMs) to interpret visual representations of data is crucial for advancing their application in data analysis and decision-making processes. This paper presents a novel synthetic dataset designed to…

Fine-tuning Vision-Language Models (VLMs) is a common strategy to improve performance following an ad-hoc data collection and annotation of real-world scenes. However, this process is often prone to biases, errors, and distribution…

The scarcity of domain-specific dialogue datasets limits the development of dialogue systems across applications. Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. To…

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

Vision-Language Models (VLMs) have shown strong performance in zero-shot image classification tasks. However, existing methods, including Contrastive Language-Image Pre-training (CLIP), all rely on annotated text-to-image pairs for aligning…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scarce scenarios. Recently, DMs have opened up the possibility…

Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities…

Vision language models (VLMs) are expected to perform effective multimodal reasoning and make logically coherent decisions, which is critical to tasks such as diagram understanding and spatial problem solving. However, current VLM reasoning…

Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. In parallel, the problem of data scarcity has brought a growing interest in employing AIGC technology for high-quality…

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…

Recent advancements in Large Language Models (LLMs) have led to high-quality Machine-Generated Text (MGT), giving rise to countless new use cases and applications. However, easy access to LLMs is posing new challenges due to misuse. To…

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine…