OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery

Understanding the chemical structure from a graphical representation of a molecule is a challenging image caption task that would greatly benefit molecule-centric scientific discovery. Variations in molecular images and caption subtasks pose a significant challenge in both image representation learning and task modeling. Yet, existing methods only focus on a specific caption task that translates a molecular image into its graph structure, i.e., OCSR. In this paper, we propose the Optical Chemical Structure Understanding (OCSU) task, which extends OCSR to molecular image caption from motif level to molecule level and abstract level. We present two approaches for that, including an OCSR-based method and an end-to-end OCSR-free method. The proposed Double-Check achieves SOTA OCSR performance on real-world patent and journal article scenarios via attentive feature enhancement for local ambiguous atoms. Cascading with SMILES-based molecule understanding methods, it can leverage the power of existing task-specific models for OCSU. While Mol-VL is an end-to-end optimized VLM-based model. An OCSU dataset, Vis-CheBI20, is built based on the widely used CheBI20 dataset for training and evaluation. Extensive experimental results on Vis-CheBI20 demonstrate the effectiveness of the proposed approaches. Improving OCSR capability can lead to a better OCSU performance for OCSR-based approach, and the SOTA performance of Mol-VL demonstrates the great potential of end-to-end approach.

Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning

We demonstrate that generative deep learning can translate galaxy observations across ultraviolet, visible, and infrared photometric bands. Leveraging mock observations from the Illustris simulations, we develop and validate a supervised image-to-image model capable of performing both band interpolation and extrapolation. The resulting trained models exhibit high fidelity in generating outputs, as verified by both general image comparison metrics (MAE, SSIM, PSNR) and specialized astronomical metrics (GINI coefficient, M20). Moreover, we show that our model can be used to predict real-world observations, using data from the DECaLS survey as a case study. These findings highlight the potential of generative learning to augment astronomical datasets, enabling efficient exploration of multi-band information in regions where observations are incomplete. This work opens new pathways for optimizing mission planning, guiding high-resolution follow-ups, and enhancing our understanding of galaxy morphology and evolution.

Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves

We propose a trait-specific image generation method that models forehead creases geometrically using B-spline and B\'ezier curves. This approach ensures the realistic generation of both principal creases and non-prominent crease patterns, effectively constructing detailed and authentic forehead-crease images. These geometrically rendered images serve as visual prompts for a diffusion-based Edge-to-Image translation model, which generates corresponding mated samples. The resulting novel synthetic identities are then used to train a forehead-crease verification network. To enhance intra-subject diversity in the generated samples, we employ two strategies: (a) perturbing the control points of B-splines under defined constraints to maintain label consistency, and (b) applying image-level augmentations to the geometric visual prompts, such as dropout and elastic transformations, specifically tailored to crease patterns. By integrating the proposed synthetic dataset with real-world data, our method significantly improves the performance of forehead-crease verification systems under a cross-database verification protocol.

EfficientVITON: An Efficient Virtual Try-On Model using Optimized Diffusion Process

Would not it be much more convenient for everybody to try on clothes by only looking into a mirror ? The answer to that problem is virtual try-on, enabling users to digitally experiment with outfits. The core challenge lies in realistic image-to-image translation, where clothing must fit diverse human forms, poses, and figures. Early methods, which used 2D transformations, offered speed, but image quality was often disappointing and lacked the nuance of deep learning. Though GAN-based techniques enhanced realism, their dependence on paired data proved limiting. More adaptable methods offered great visuals but demanded significant computing power and time. Recent advances in diffusion models have shown promise for high-fidelity translation, yet the current crop of virtual try-on tools still struggle with detail loss and warping issues. To tackle these challenges, this paper proposes EfficientVITON, a new virtual try-on system leveraging the impressive pre-trained Stable Diffusion model for better images and deployment feasibility. The system includes a spatial encoder to maintain clothings finer details and zero cross-attention blocks to capture the subtleties of how clothes fit a human body. Input images are carefully prepared, and the diffusion process has been tweaked to significantly cut generation time without image quality loss. The training process involves two distinct stages of fine-tuning, carefully incorporating a balance of loss functions to ensure both accurate try-on results and high-quality visuals. Rigorous testing on the VITON-HD dataset, supplemented with real-world examples, has demonstrated that EfficientVITON achieves state-of-the-art results.

Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning

Self-supervised deep learning has accelerated 2D natural image analysis but remains difficult to translate into 3D MRI, where data are scarce and pre-trained 2D backbones cannot capture volumetric context. We present a sequence-invariant self-supervised framework leveraging quantitative MRI (qMRI). By simulating multiple MRI contrasts from a single 3D qMRI scan and enforcing consistent representations across these contrasts, we learn anatomy-centric rather than sequence-specific features. This yields a robust 3D encoder that performs strongly across varied tasks and protocols. Experiments on healthy brain segmentation (IXI), stroke lesion segmentation (ARC), and MRI denoising show significant gains over baseline SSL approaches, especially in low-data settings (up to +8.3% Dice, +4.2 dB PSNR). Our model also generalises effectively to unseen sites, demonstrating potential for more scalable and clinically reliable volumetric analysis. All code and trained models are publicly available.

CSHNet: A Novel Information Asymmetric Image Translation Method

Despite advancements in cross-domain image translation, challenges persist in asymmetric tasks such as SAR-to-Optical and Sketch-to-Instance conversions, which involve transforming data from a less detailed domain into one with richer content. Traditional CNN-based methods are effective at capturing fine details but struggle with global structure, leading to unwanted merging of image regions. To address this, we propose the CNN-Swin Hybrid Network (CSHNet), which combines two key modules: Swin Embedded CNN (SEC) and CNN Embedded Swin (CES), forming the SEC-CES-Bottleneck (SCB). SEC leverages CNN's detailed feature extraction while integrating the Swin Transformer's structural bias. CES, in turn, preserves the Swin Transformer's global integrity, compensating for CNN's lack of focus on structure. Additionally, CSHNet includes two components designed to enhance cross-domain information retention: the Interactive Guided Connection (IGC), which enables dynamic information exchange between SEC and CES, and Adaptive Edge Perception Loss (AEPL), which maintains structural boundaries during translation. Experimental results show that CSHNet outperforms existing methods in both visual quality and performance metrics across scene-level and instance-level datasets. Our code is available at: https://github.com/XduShi/CSHNet.

Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To address this gap, we propose a Simultaneous Learning Knowledge Distillation (SLKD) framework tailored for model compression in image restoration tasks. SLKD employs a dual-teacher, single-student architecture with two distinct learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL), simultaneously. In DRL, the student encoder learns from Teacher A to focus on removing degradation factors, guided by a novel BRISQUE extractor. In IRL, the student decoder learns from Teacher B to reconstruct clean images, with the assistance of a proposed PIQE extractor. These strategies enable the student to learn from degraded and clean images simultaneously, ensuring high-quality compression of image restoration models. Experimental results across five datasets and three tasks demonstrate that SLKD achieves substantial reductions in FLOPs and parameters, exceeding 80\%, while maintaining strong image restoration performance.

Diff-Ensembler: Learning to Ensemble 2D Diffusion Models for Volume-to-Volume Medical Image Translation

Despite success in volume-to-volume translations in medical images, most existing models struggle to effectively capture the inherent volumetric distribution using 3D representations. The current state-of-the-art approach combines multiple 2D-based networks through weighted averaging, thereby neglecting the 3D spatial structures. Directly training 3D models in medical imaging presents significant challenges due to high computational demands and the need for large-scale datasets. To address these challenges, we introduce Diff-Ensembler, a novel hybrid 2D-3D model for efficient and effective volumetric translations by ensembling perpendicularly trained 2D diffusion models with a 3D network in each diffusion step. Moreover, our model can naturally be used to ensemble diffusion models conditioned on different modalities, allowing flexible and accurate fusion of input conditions. Extensive experiments demonstrate that Diff-Ensembler attains superior accuracy and volumetric realism in 3D medical image super-resolution and modality translation. We further demonstrate the strength of our model's volumetric realism using tumor segmentation as a downstream task.

SFC-GAN: A Generative Adversarial Network for Brain Functional and Structural Connectome Translation

Modern brain imaging technologies have enabled the detailed reconstruction of human brain connectomes, capturing structural connectivity (SC) from diffusion MRI and functional connectivity (FC) from functional MRI. Understanding the intricate relationships between SC and FC is vital for gaining deeper insights into the brain's functional and organizational mechanisms. However, obtaining both SC and FC modalities simultaneously remains challenging, hindering comprehensive analyses. Existing deep generative models typically focus on synthesizing a single modality or unidirectional translation between FC and SC, thereby missing the potential benefits of bi-directional translation, especially in scenarios where only one connectome is available. Therefore, we propose Structural-Functional Connectivity GAN (SFC-GAN), a novel framework for bidirectional translation between SC and FC. This approach leverages the CycleGAN architecture, incorporating convolutional layers to effectively capture the spatial structures of brain connectomes. To preserve the topological integrity of these connectomes, we employ a structure-preserving loss that guides the model in capturing both global and local connectome patterns while maintaining symmetry. Our framework demonstrates superior performance in translating between SC and FC, outperforming baseline models in similarity and graph property evaluations compared to ground truth data, each translated modality can be effectively utilized for downstream classification.

MSTS: A Multimodal Safety Test Suite for Vision-Language Models

Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards, however, VLMs may give harmful advice (e.g. how to self-harm) or encourage unsafe behaviours (e.g. to consume drugs). Despite these clear hazards, little work so far has evaluated VLM safety and the novel risks created by multimodal inputs. To address this gap, we introduce MSTS, a Multimodal Safety Test Suite for VLMs. MSTS comprises 400 test prompts across 40 fine-grained hazard categories. Each test prompt consists of a text and an image that only in combination reveal their full unsafe meaning. With MSTS, we find clear safety issues in several open VLMs. We also find some VLMs to be safe by accident, meaning that they are safe because they fail to understand even simple test prompts. We translate MSTS into ten languages, showing non-English prompts to increase the rate of unsafe model responses. We also show models to be safer when tested with text only rather than multimodal prompts. Finally, we explore the automation of VLM safety assessments, finding even the best safety classifiers to be lacking.