Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood. In this work, we systematically analyze MAs in representative DiTs and find that they are spatially distributed across image tokens while concentrated in a small set of fixed feature dimensions. We further show that these dimensions are closely aligned with AdaLN residual scaling factors and are primarily modulated by the denoising timestep rather than text conditions. This structure leads to two task-dependent effects: for generation, MAs are critical for fine-grained detail synthesis while having limited influence on global semantics; for understanding, their shared high-magnitude directions make raw DiT features overly similar across spatial tokens and weaken dense feature discrimination. Based on these findings, we introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations (MAs) as a unified modulation signal to improve both generative and representational capabilities of DiTs. For generation, EMA proposes MA-driven Detail G}uidance (DG), which suppresses MA dimensions to construct a detail-deficient counterfactual prediction and guides sampling toward finer visual details. DG further supports efficient partial-forward inference, integration with classifier-free guidance, and token-level Local DG for refining selected image regions. For understanding, EMA introduces MA-modulated REPresentation extraction (MREP), which uses pretrained AdaLN channel-wise modulation to reduce MA directional dominance and concatenates spatially normalized MA maps to preserve useful spatial structure. Extensive experiments demonstrate that EMA consistently improves both the generation quality and representation capability of DiTs.

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

MCA: 2D-3D Retrieval with Noisy Labels via Multi-level Adaptive Correction and Alignment

With the increasing availability of 2D and 3D data, significant advancements have been made in the field of cross-modal retrieval. Nevertheless, the existence of imperfect annotations presents considerable challenges, demanding robust solutions for 2D-3D cross-modal retrieval in the presence of noisy label conditions. Existing methods generally address the issue of noise by dividing samples independently within each modality, making them susceptible to overfitting on corrupted labels. To address these issues, we propose a robust 2D-3D \textbf{M}ulti-level cross-modal adaptive \textbf{C}orrection and \textbf{A}lignment framework (MCA). Specifically, we introduce a Multimodal Joint label Correction (MJC) mechanism that leverages multimodal historical self-predictions to jointly model the modality prediction consistency, enabling reliable label refinement. Additionally, we propose a Multi-level Adaptive Alignment (MAA) strategy to effectively enhance cross-modal feature semantics and discrimination across different levels. Extensive experiments demonstrate the superiority of our method, MCA, which achieves state-of-the-art performance on both conventional and realistic noisy 3D benchmarks, highlighting its generality and effectiveness.

Attention GhostUNet++: Enhanced Segmentation of Adipose Tissue and Liver in CT Images

Accurate segmentation of abdominal adipose tissue, including subcutaneous (SAT) and visceral adipose tissue (VAT), along with liver segmentation, is essential for understanding body composition and associated health risks such as type 2 diabetes and cardiovascular disease. This study proposes Attention GhostUNet++, a novel deep learning model incorporating Channel, Spatial, and Depth Attention mechanisms into the Ghost UNet++ bottleneck for automated, precise segmentation. Evaluated on the AATTCT-IDS and LiTS datasets, the model achieved Dice coefficients of 0.9430 for VAT, 0.9639 for SAT, and 0.9652 for liver segmentation, surpassing baseline models. Despite minor limitations in boundary detail segmentation, the proposed model significantly enhances feature refinement, contextual understanding, and computational efficiency, offering a robust solution for body composition analysis. The implementation of the proposed Attention GhostUNet++ model is available at:https://github.com/MansoorHayat777/Attention-GhostUNetPlusPlus.

An Advanced Features Extraction Module for Remote Sensing Image Super-Resolution

In recent years, convolutional neural networks (CNNs) have achieved remarkable advancement in the field of remote sensing image super-resolution due to the complexity and variability of textures and structures in remote sensing images (RSIs), which often repeat in the same images but differ across others. Current deep learning-based super-resolution models focus less on high-frequency features, which leads to suboptimal performance in capturing contours, textures, and spatial information. State-of-the-art CNN-based methods now focus on the feature extraction of RSIs using attention mechanisms. However, these methods are still incapable of effectively identifying and utilizing key content attention signals in RSIs. To solve this problem, we proposed an advanced feature extraction module called Channel and Spatial Attention Feature Extraction (CSA-FE) for effectively extracting the features by using the channel and spatial attention incorporated with the standard vision transformer (ViT). The proposed method trained over the UCMerced dataset on scales 2, 3, and 4. The experimental results show that our proposed method helps the model focus on the specific channels and spatial locations containing high-frequency information so that the model can focus on relevant features and suppress irrelevant ones, which enhances the quality of super-resolved images. Our model achieved superior performance compared to various existing models.

SEGSRNet for Stereo-Endoscopic Image Super-Resolution and Surgical Instrument Segmentation

SEGSRNet addresses the challenge of precisely identifying surgical instruments in low-resolution stereo endoscopic images, a common issue in medical imaging and robotic surgery. Our innovative framework enhances image clarity and segmentation accuracy by applying state-of-the-art super-resolution techniques before segmentation. This ensures higher-quality inputs for more precise segmentation. SEGSRNet combines advanced feature extraction and attention mechanisms with spatial processing to sharpen image details, which is significant for accurate tool identification in medical images. Our proposed model outperforms current models including Dice, IoU, PSNR, and SSIM, SEGSRNet where it produces clearer and more accurate images for stereo endoscopic surgical imaging. SEGSRNet can provide image resolution and precise segmentation which can significantly enhance surgical accuracy and patient care outcomes.