Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically treated in isolation. This separation reveals a fundamental issue: image manipulation methods overlook how actions unfold over time, while video prediction models often ignore the intended outcomes. To this end, we propose ShowMe, a unified framework that enables both tasks by selectively activating the spatial and temporal components of video diffusion models. In addition, we introduce structure and motion consistency rewards to improve structural fidelity and temporal coherence. Notably, this unification brings dual benefits: the spatial knowledge gained through video pretraining enhances contextual consistency and realism in non-rigid image edits, while the instruction-guided manipulation stage equips the model with stronger goal-oriented reasoning for video prediction. Experiments on diverse benchmarks demonstrate that our method outperforms expert models in both instructional image and video generation, highlighting the strength of video diffusion models as a unified action-object state transformer. Our code will be available at https://yujiangpu20.github.io/showme/.

Energy forecasting is vital for grid reliability and operational efficiency. Although recent advances in time series forecasting have led to progress, existing benchmarks remain limited in spatial and temporal scope and lack multi-energy features. This raises concerns about their reliability and applicability in real-world deployment. To address this, we present the Real-E dataset, covering over 74 power stations across 30+ European countries over a 10-year span with rich metadata. Using Real- E, we conduct an extensive data analysis and benchmark over 20 baselines across various model types. We introduce a new metric to quantify shifts in correlation structures and show that existing methods struggle on our dataset, which exhibits more complex and non-stationary correlation dynamics. Our findings highlight key limitations of current methods and offer a strong empirical basis for building more robust forecasting models

In this paper, we propose H-MoRe, a novel pipeline for learning precise human-centric motion representation. Our approach dynamically preserves relevant human motion while filtering out background movement. Notably, unlike previous methods relying on fully supervised learning from synthetic data, H-MoRe learns directly from real-world scenarios in a self-supervised manner, incorporating both human pose and body shape information. Inspired by kinematics, H-MoRe represents absolute and relative movements of each body point in a matrix format that captures nuanced motion details, termed world-local flows. H-MoRe offers refined insights into human motion, which can be integrated seamlessly into various action-related applications. Experimental results demonstrate that H-MoRe brings substantial improvements across various downstream tasks, including gait recognition (CL@R1: 16.01%↑), action recognition (Acc@1: 8.92%↑), and video generation (FVD: 67.07%↓). Additionally, H-MoRe exhibits high inference efficiency (34 fps), making it suitable for most real-time scenarios. Models and code is available at https://github.com/haku-huang/h-more.

Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code are available at https://github.com/ShiqiYu/OpenGait/.

This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network. The fusion network with one generator and dual discriminators seeks commons while learning from differences, which preserves structural information of targets from the infrared and textural details from the visible. Furthermore, we build a synchronized imaging system with calibrated infrared and optical sensors, and collect currently the most comprehensive benchmark covering a wide range of scenarios. Extensive experiments on several public datasets and our benchmark demonstrate that our method outputs not only visually appealing fusion but also higher detection mAP than the state-of-the-art approaches. The source code and benchmark are available at https://github.com/dlut-dimt/TarDAL.

Nowadays, driven by the high demand for autonomous driving and surveillance, infrared and visible image fusion (IVIF) has attracted significant attention from both the industry and research community. Existing learning-based IVIF methods tried to design various architectures to extract features. Still, these hand-crafted designed architectures cannot adequately represent the typical features of different modalities, resulting in undesirable artifacts on the fused results. To alleviate this issue, we propose a Neural Architecture Search (NAS)-based deep learning network to realize the IVIF task, which can automatically discover the modality-oriented feature representation. Our network is accomplished through two modality-oriented encoders and a unified decoder, in addition to a self-visual saliency weight module (SvSW). The two modality-oriented encoders target to learn different intrinsic feature representations automatically from infrared-/visible- modality images. Subsequently, these intermediate features are merged via the SvSW module. Finally, the fused image is recovered by a unified decoder. Extensive experiments demonstrate that our method outperforms the state-of-the-art approaches by a large margin, especially in generating distinct targets and abundant details.