arXiv:2608. 07570v1 Announce Type: cross Abstract: Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred.
The paper introduces a new task called compositional layout understanding, focusing on interpreting complex, multi‑layer document and UI designs. It presents CoDeLayout, a VQA dataset of about 20,000 real‑world layouts annotated with compositional element pairs and design intent. The authors identify semantic drift and structural ambiguity as key challenges for vision‑language models and propose MASON, a post‑training approach that combines multimodal alignment and structural perception to improve performance, achieving 91.66% accuracy with only 30% of the training data.
The paper introduces InterIL, a joint generative model that simultaneously produces a background image and a layout of foreground elements for graphic design templates, addressing the limitations of sequential generation approaches. InterIL connects pretrained image and layout diffusion backbones via a learnable communication module, freezing the backbones to preserve prior knowledge while training only the interaction module. The model also offers a test‑time guidance strategy, enabling users to impose preferences without retraining, and demonstrates superior image, layout, and harmonization quality compared to previous methods.
arXiv:2503. 09399v4 Announce Type: replace-cross Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context.
arXiv:2510. 05740v2 Announce Type: replace-cross Abstract: The rapid development of generative models has made it increasingly crucial to develop detectors that can reliably detect synthetic images.
The paper introduces a new task called compositional layout understanding, focusing on interpreting complex, multi-layer document and UI layouts that involve hierarchical relationships among visually entangled elements. It presents CoDeLayout, a VQA dataset of about 20,000 real-world layouts annotated with compositional element pairs and design intent, and identifies two main challenges for current vision‑language models: semantic drift between textual metadata and visual content, and structural ambiguity in hierarchical inter‑element relationships. To address these, the authors propose MASON, a post‑training paradigm that combines multimodal alignment and structural perception, achieving a 91.66% accuracy on CoDeLayout and outperforming full‑data direct fine‑tuning with only 30% of the training data.
arXiv:2607. 01303v1 Announce Type: cross Abstract: Presentation Attack Detection (PAD) serves as a crucial safeguard for face recognition systems against presentation attacks such as printed photos, replayed videos, and 3D masks.
arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.
The MSU team presents a modular approach to the Explainable Deepfake Detection Challenge, combining multiple DINOv3 backbones with Mesorch manipulation-localization features for real/fake classification. They incorporate a Grounding-DINO-based pseudo-mask pipeline to generate artifact evidence maps and a local contrastive objective to separate artifact from authenticity cues. For explanations, class-conditional Qwen3-VL models produce complex descriptions, which are then simplified by a GRPO-optimized text model, achieving high detection and explanation scores on the XPlainVerse dataset.
arXiv:2509. 12046v2 Announce Type: replace-cross Abstract: Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement.
The paper introduces Relative Patch Response Learning (PRL) to detect AI‑generated images by comparing patch responses across two mixed views of aligned real‑generated image pairs. PRL uses a relative response objective, a reference coherence objective, and an area ranking objective to address contextual shifts caused by self‑attention, providing precise supervision for patch‑level detection. Experiments show PRL outperforms prior methods by 4.3% and 5.9% in average balanced accuracy on standard and in‑the‑wild benchmarks.
ES‑VP introduces Energy‑Shaped Visual Prompting, a method that generates image‑specific prompts through low‑rank initialization and energy‑guided dynamic adaptation. It achieves higher performance than existing single‑prompt and diverse‑prompt approaches while using far fewer parameters. Experiments on five architectures and fifteen datasets show consistent superiority, including a 2.6% accuracy gain over DAM‑VP on CLIP with 590× fewer prompt parameters.