MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning

Text Image Machine Translation (TIMT)-the task of translating textual content embedded in images-is critical for applications in accessibility, cross-lingual information access, and real-world document understanding. However, TIMT remains a complex challenge due to the need for accurate optical character recognition (OCR), robust visual-text reasoning, and high-quality translation, often requiring cascading multi-stage pipelines. Recent advances in large-scale Reinforcement Learning (RL) have improved reasoning in Large Language Models (LLMs) and Multimodal LLMs (MLLMs), but their application to end-to-end TIMT is still underexplored. To bridge this gap, we introduce MT$^{3}$, the first framework to apply Multi-Task RL to MLLMs for end-to-end TIMT. MT$^{3}$ adopts a multi-task optimization paradigm targeting three key sub-skills: text recognition, context-aware reasoning, and translation. It is trained using a novel multi-mixed reward mechanism that adapts rule-based RL strategies to TIMT's intricacies, offering fine-grained, non-binary feedback across tasks. Furthermore, to facilitate the evaluation of TIMT in authentic cross-cultural and real-world social media contexts, we introduced XHSPost, the first social media TIMT benchmark. Our MT$^{3}$-7B-Zero achieves state-of-the-art results on the latest in-domain MIT-10M benchmark, outperforming strong baselines such as Qwen2.5-VL-72B and InternVL2.5-78B by notable margins across multiple metrics. Additionally, the model shows strong generalization to out-of-distribution language pairs and datasets. In-depth analyses reveal how multi-task synergy, reinforcement learning initialization, curriculum design, and reward formulation contribute to advancing MLLM-driven TIMT.

Training Free Stylized Abstraction

Stylized abstraction synthesizes visually exaggerated yet semantically faithful representations of subjects, balancing recognizability with perceptual distortion. Unlike image-to-image translation, which prioritizes structural fidelity, stylized abstraction demands selective retention of identity cues while embracing stylistic divergence, especially challenging for out-of-distribution individuals. We propose a training-free framework that generates stylized abstractions from a single image using inference-time scaling in vision-language models (VLLMs) to extract identity-relevant features, and a novel cross-domain rectified flow inversion strategy that reconstructs structure based on style-dependent priors. Our method adapts structural restoration dynamically through style-aware temporal scheduling, enabling high-fidelity reconstructions that honor both subject and style. It supports multi-round abstraction-aware generation without fine-tuning. To evaluate this task, we introduce StyleBench, a GPT-based human-aligned metric suited for abstract styles where pixel-level similarity fails. Experiments across diverse abstraction (e.g., LEGO, knitted dolls, South Park) show strong generalization to unseen identities and styles in a fully open-source setup.

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation

Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.

PLD: A Choice-Theoretic List-Wise Knowledge Distillation

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation it has become the de facto approach to augment cross-entropy with a distillation term. Typically this term is either a KL divergence-matching marginal probabilities or a correlation-based loss capturing intra- and inter-class relationships but in every case it sits as an add-on to cross-entropy with its own weight that must be carefully tuned. In this paper we adopt a choice-theoretic perspective and recast knowledge distillation under the Plackett-Luce model by interpreting teacher logits as "worth" scores. We introduce Plackett-Luce Distillation (PLD), a weighted list-wise ranking loss in which the teacher model transfers knowledge of its full ranking of classes, weighting each ranked choice by its own confidence. PLD directly optimizes a single teacher-optimal ranking of the true label first, followed by the remaining classes in descending teacher confidence, yielding a convex, translation-invariant surrogate that subsumes weighted cross-entropy. Empirically on standard image classification benchmarks, PLD improves Top-1 accuracy by an average of +0.42% over DIST (arXiv:2205.10536) and +1.04% over KD (arXiv:1503.02531) in homogeneous settings and by +0.48% and +1.09% over DIST and KD, respectively, in heterogeneous settings.

Towards Generating Realistic Underwater Images

This paper explores the use of contrastive learning and generative adversarial networks for generating realistic underwater images from synthetic images with uniform lighting. We investigate the performance of image translation models for generating realistic underwater images using the VAROS dataset. Two key evaluation metrics, Fr\'echet Inception Distance (FID) and Structural Similarity Index Measure (SSIM), provide insights into the trade-offs between perceptual quality and structural preservation. For paired image translation, pix2pix achieves the best FID scores due to its paired supervision and PatchGAN discriminator, while the autoencoder model attains the highest SSIM, suggesting better structural fidelity despite producing blurrier outputs. Among unpaired methods, CycleGAN achieves a competitive FID score by leveraging cycle-consistency loss, whereas CUT, which replaces cycle-consistency with contrastive learning, attains higher SSIM, indicating improved spatial similarity retention. Notably, incorporating depth information into CUT results in the lowest overall FID score, demonstrating that depth cues enhance realism. However, the slight decrease in SSIM suggests that depth-aware learning may introduce structural variations.

ImplicitStainer: Data-Efficient Medical Image Translation for Virtual Antibody-based Tissue Staining Using Local Implicit Functions

Hematoxylin and eosin (H&E) staining is a gold standard for microscopic diagnosis in pathology. However, H&E staining does not capture all the diagnostic information that may be needed. To obtain additional molecular information, immunohistochemical (IHC) stains highlight proteins that mark specific cell types, such as CD3 for T-cells or CK8/18 for epithelial cells. While IHC stains are vital for prognosis and treatment guidance, they are typically only available at specialized centers and time consuming to acquire, leading to treatment delays for patients. Virtual staining, enabled by deep learning-based image translation models, provides a promising alternative by computationally generating IHC stains from H&E stained images. Although many GAN and diffusion based image to image (I2I) translation methods have been used for virtual staining, these models treat image patches as independent data points, which results in increased and more diverse data requirements for effective generation. We present ImplicitStainer, a novel approach that leverages local implicit functions to improve image translation, specifically virtual staining performance, by focusing on pixel-level predictions. This method enhances robustness to variations in dataset sizes, delivering high-quality results even with limited data. We validate our approach on two datasets using a comprehensive set of metrics and benchmark it against over fifteen state-of-the-art GAN- and diffusion based models. Full Code and models trained will be released publicly via Github upon acceptance.

A Deep Learning Framework for Two-Dimensional, Multi-Frequency Propagation Factor Estimation

Accurately estimating the refractive environment over multiple frequencies within the marine atmospheric boundary layer is crucial for the effective deployment of radar technologies. Traditional parabolic equation simulations, while effective, can be computationally expensive and time-intensive, limiting their practical application. This communication explores a novel approach using deep neural networks to estimate the pattern propagation factor, a critical parameter for characterizing environmental impacts on signal propagation. Image-to-image translation generators designed to ingest modified refractivity data and generate predictions of pattern propagation factors over the same domain were developed. Findings demonstrate that deep neural networks can be trained to analyze multiple frequencies and reasonably predict the pattern propagation factor, offering an alternative to traditional methods.

MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications

Accessibility remains a critical concern in today's society, as many technologies are not developed to support the full range of user needs. Existing multi-agent systems (MAS) often cannot provide comprehensive assistance for users in need due to the lack of customization stemming from closed-source designs. Consequently, individuals with disabilities frequently encounter significant barriers when attempting to interact with digital environments. We introduce MATE, a multimodal accessibility MAS, which performs the modality conversions based on the user's needs. The system is useful for assisting people with disabilities by ensuring that data will be converted to an understandable format. For instance, if the user cannot see well and receives an image, the system converts this image to its audio description. MATE can be applied to a wide range of domains, industries, and areas, such as healthcare, and can become a useful assistant for various groups of users. The system supports multiple types of models, ranging from LLM API calling to using custom machine learning (ML) classifiers. This flexibility ensures that the system can be adapted to various needs and is compatible with a wide variety of hardware. Since the system is expected to run locally, it ensures the privacy and security of sensitive information. In addition, the framework can be effectively integrated with institutional technologies (e.g., digital healthcare service) for real-time user assistance. Furthermore, we introduce ModCon-Task-Identifier, a model that is capable of extracting the precise modality conversion task from the user input. Numerous experiments show that ModCon-Task-Identifier consistently outperforms other LLMs and statistical models on our custom data. Our code and data are publicly available at https://github.com/AlgazinovAleksandr/Multi-Agent-MATE.

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

Cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural context in multimodal translation. We introduce CaMMT, a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. Using this dataset, we evaluate five Vision Language Models (VLMs) in text-only and text+image settings. Through automatic and human evaluations, we find that visual context generally improves translation quality, especially in handling Culturally-Specific Items (CSIs), disambiguation, and correct gender usage. By releasing CaMMT, we aim to support broader efforts in building and evaluating multimodal translation systems that are better aligned with cultural nuance and regional variation.

Rotation-Equivariant Self-Supervised Method in Image Denoising

Self-supervised image denoising methods have garnered significant research attention in recent years, for this kind of method reduces the requirement of large training datasets. Compared to supervised methods, self-supervised methods rely more on the prior embedded in deep networks themselves. As a result, most of the self-supervised methods are designed with Convolution Neural Networks (CNNs) architectures, which well capture one of the most important image prior, translation equivariant prior. Inspired by the great success achieved by the introduction of translational equivariance, in this paper, we explore the way to further incorporate another important image prior. Specifically, we first apply high-accuracy rotation equivariant convolution to self-supervised image denoising. Through rigorous theoretical analysis, we have proved that simply replacing all the convolution layers with rotation equivariant convolution layers would modify the network into its rotation equivariant version. To the best of our knowledge, this is the first time that rotation equivariant image prior is introduced to self-supervised image denoising at the network architecture level with a comprehensive theoretical analysis of equivariance errors, which offers a new perspective to the field of self-supervised image denoising. Moreover, to further improve the performance, we design a new mask mechanism to fusion the output of rotation equivariant network and vanilla CNN-based network, and construct an adaptive rotation equivariant framework. Through extensive experiments on three typical methods, we have demonstrated the effectiveness of the proposed method.