相关论文: TextPecker: Rewarding Structural Anomaly Quantific…

Visual captioning requires models to capture visual content faithfully while minimizing both omission and hallucination. As the dominant paradigm for captioning, MLLMs have achieved strong performance through scaling and high-quality data.…

Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider…

We present an architecture that generates medical texts while learning an informative, continuous representation with discriminative features. During training the input to the system is a dataset of captions for medical X-Rays. The acquired…

This paper addresses the performance bottlenecks of existing text-driven image generation methods in terms of semantic alignment accuracy and structural consistency. A high-fidelity image generation method is proposed by integrating…

We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual representations, which we apply to text recognition. To account for the sequence-to-sequence structure, each feature map is divided into different…

Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a representational bottleneck: contrastive 3D CT embeddings encode…

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though…

Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of…

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…

Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer:…

With the increasing integration of multimodal AI systems in creative workflows, understanding information loss in vision-language-vision pipelines has become important for evaluating system limitations. However, the degradation that occurs…

Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…

Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing…

Vector-quantized based models have recently demonstrated strong potential for visual prior modeling. However, existing VQ-based methods simply encode visual features with nearest codebook items and train index predictor with code-level…

Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this…

Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…

Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process…

Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent efforts have been made to tackle this issue by pruning visual…

With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has primarily focused on…

Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant improvements in image quality when text is used as a prior.…