Diffusion Transformer has demonstrated powerful capability and scalability in generating high-quality images and videos. Further pursuing the unification of generation and editing tasks has yielded significant progress in the domain of image content creation. However, due to the intrinsic demands for consistency across both temporal and spatial dynamics, achieving a unified approach for video synthesis remains challenging. We introduce VACE, which enables users to perform Video tasks within an All-in-one framework for Creation and Editing. These tasks include reference-to-video generation, video-to-video editing, and masked video-to-video editing. Specifically, we effectively integrate the requirements of various tasks by organizing video task inputs, such as editing, reference, and masking, into a unified interface referred to as the Video Condition Unit (VCU). Furthermore, by utilizing a Context Adapter structure, we inject different task concepts into the model using formalized representations of temporal and spatial dimensions, allowing it to handle arbitrary video synthesis tasks flexibly. Extensive experiments demonstrate that the unified model of VACE achieves performance on par with task-specific models across various subtasks. Simultaneously, it enables diverse applications through versatile task combinations. Project page: https://ali-vilab.github.io/VACE-Page/.

Diffusion models have emerged as a powerful generative technology and have been found to be applicable in various scenarios. Most existing foundational diffusion models are primarily designed for text-guided visual generation and do not support multi-modal conditions, which are essential for many visual editing tasks. This limitation prevents these foundational diffusion models from serving as a unified model in the field of visual generation, like GPT-4 in the natural language processing field. In this work, we propose ACE, an All-round Creator and Editor, which achieves comparable performance compared to those expert models in a wide range of visual generation tasks. To achieve this goal, we first introduce a unified condition format termed Long-context Condition Unit (LCU), and propose a novel Transformer-based diffusion model that uses LCU as input, aiming for joint training across various generation and editing tasks. Furthermore, we propose an efficient data collection approach to address the issue of the absence of available training data. It involves acquiring pairwise images with synthesis-based or clustering-based pipelines and supplying these pairs with accurate textual instructions by leveraging a fine-tuned multi-modal large language model. To comprehensively evaluate the performance of our model, we establish a benchmark of manually annotated pairs data across a variety of visual generation tasks. The extensive experimental results demonstrate the superiority of our model in visual generation fields. Thanks to the all-in-one capabilities of our model, we can easily build a multi-modal chat system that responds to any interactive request for image creation using a single model to serve as the backend, avoiding the cumbersome pipeline typically employed in visual agents.

Inter-network settlement is a critical mechanism for ensuring quality service and sustainable growth in the telecommunications industry. However, existing practices among operators suffer from inefficient, including manual workflows, untrustworthy data foundations, insecure dispute resolution, and insufficient accountability oversight. These challenges lead to prolonged settlement cycles, operational redundancies, and heightened risks of errors or leaks. To address these issues, we propose a blockchain-powered settlement chain framework that integrates business and technical systems to enable intelligent, trusted, and automated cross-operator settlement management. By synergizing consortium blockchain, privacy-preserving computation, and decentralized governance protocols, the framework establishes an end-to-end digital workflow covering data exchange, verification, auditing, and reconciliation. Key innovations include: (1) a multi-operator co-built consortium chain with cross-cloud networking and peer-to-peer governance; (2) a “data-available-but-invisible” auditing mechanism combining blockchain and privacy-preserving computation to ensure secure, compliant interactions; and (3) a dynamic chaincode architecture supporting real-time rule synchronization and adaptive cryptographic controls. The framework achieves full-process traceability, automated reconciliation, and enhanced financial governance while reducing reliance on manual intervention. This work provides a transformative paradigm for modernizing telecommunications settlement systems through digital trust infrastructure.

Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable im-age synthesis. Recent research has introduced tuning meth-ods that make subtle adjustments to the original models, yielding promising results in specific adaptations of foun-dational generative diffusion models. Rather than modi-fying the main backbone of the diffusion model, we delve into the role of skip connection in U-Net and reveal that hi-erarchical features aggregating long-distance information across encoder and decoder make a significant impact on the content and quality of image generation. Based on the observation, we propose an efficient generative tuning framework, dubbed SCEdit, which integrates and edits Skip Connection using a lightweight tuning module named SC-Tuner. Furthermore, the proposed framework allows for straightforward extension to controllable image syn-thesis by injecting different conditions with Controllable SC-Tuner, simplifying and unifying the network design for multi-condition inputs. Our SCEdit substantially reduces training parameters, memory usage, and computational ex-pense due to its lightweight tuners, with backward propa-gation only passing to the decoder blocks. Extensive exper-iments conducted on text-to-image generation and control-lable image synthesis tasks demonstrate the superiority of our method in terms of efficiency and performance. Project page: https://scedit.github.io/

Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models. In this work, we propose the VoP: Text-Video Cooperative Prompt Tuning for efficient tuning on the text-video retrieval task. The proposed VoP is an end-to-end framework with both video & text prompts introducing, which can be regarded as a powerful baseline with only 0.1% trainable parameters. Further, based on the spatiotemporal characteristics of videos, we develop three novel video prompt mechanisms to improve the performance with different scales of trainable parameters. The basic idea of the VoP enhancement is to model the frame position, frame context, and layer function with specific trainable prompts, respectively. Extensive experiments show that compared to full fine-tuning, the enhanced VoP achieves a 1.4% average R@1 gain across five text-video retrieval benchmarks with 6× less parameter overhead. The code will be available at https://github.com/bighuang624/VoP.

Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (e.g., in minutes), temporal grounding in long videos (e.g., in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with one-time network execution. Our pipeline is formulated in a coarse-to-fine manner, where we first extract context knowledge from non-overlapped video clips (i.e., anchors), and then supplement the anchors that highly response to the query with detailed content knowledge. Besides the remarkably high pipeline efficiency, another advantage of our approach is the capability of capturing long-range temporal correlation, thanks to modeling the entire video as a whole, and hence facilitates more accurate grounding. Experimental results suggest that, on the long-form video datasets MAD and Ego4d, our method significantly outperforms state-of-the-arts, and achieves 14.6× / 102.8× higher efficiency respectively. Project can be found at https://github.com/afcedf/SOONet.git.

Testing and evaluation are expensive but critical steps in the development of connected and automated vehicles (CAVs). In this paper, we develop an adaptive sampling framework to efficiently evaluate the accident rate of CAVs, particularly for scenario-based tests where the probability distribution of input parameters is known from the Naturalistic Driving Data. Our framework relies on a surrogate model to approximate the CAV performance and a novel acquisition function to maximize the benefit (information to accident rate) of the next sample formulated through an information-theoretic consideration. In addition to the standard application with only a single high-fidelity model of CAV performance, we also extend our approach to the bi-fidelity context where an additional low-fidelity model can be used at a lower computational cost to approximate the CAV performance. Accordingly, for the second case, our approach is formulated such that it allows the choice of the next sample in terms of both fidelity level (i.e., which model to use) and sampling location to maximize the benefit per cost. Our framework is tested in a widely-considered two-dimensional cut-in problem for CAVs, where Intelligent Driving Model (IDM) with different time resolutions are used to construct the high and low-fidelity models. We show that our single-fidelity method outperforms the existing approach for the same problem, and the bi-fidelity method can further save half of the computational cost to reach a similar accuracy in estimating the accident rate.

Near-duplicate video retrieval (NDVR) aims to find the copies or transformations of the query video from a massive video database. It plays an important role in many video related applications, including copyright protection, tracing, filtering and etc. Video representation and similarity search are crucial to any video retrieval system. To derive effective video representation, most video retrieval systems require a large amount of manually annotated data for training, making it costly inefficient. In addition, most retrieval systems are based on frame-level features for video similarity searching, making it expensive both storage wise and search wise. To address the above issues, we propose a video representation learning (VRL) approach to effectively address the above shortcomings. It first effectively learns video representation from unlabeled videos via contrastive learning to avoid the expensive cost of manual annotation. Then, it exploits transformer structure to aggregate frame-level features into clip-level to reduce both storage space and search complexity. It can learn the complementary and discriminative information from the interactions among clip frames, as well as acquire the frame permutation and missing invariant ability to support more flexible retrieval manners. Comprehensive experiments on two challenging near-duplicate video retrieval datasets, namely FIVR-200K and SVD, verify the effectiveness of our proposed VRL approach, which achieves the best performance of video retrieval on accuracy and efficiency.

The Cyclone Global Navigation Satellite System (CYGNSS) measures GPS signals specularly reflected from Earth's surface to remotely sense ocean surface roughness and wind speed. The mean square slope (mss) is a key physical parameter that relates the ocean surface properties (wave spectra) with the CYGNSS measurement of the normalized bistatic radar cross section (NBRCS). An approach to model the mss for validation with CYGNSS mss data was developed by adding the contribution of a high frequency tail to the IFREMER WAVEWATCH III (WW3) mss. It is demonstrated that the ratio of CYGNSS mss and the modified WW3 mss can be used to diagnose potential calibration errors that exist in the Level 1 calibration algorithm. This approach can help to improve CYGNSS data quality, including the Level 1 NBRCS and Level 2 ocean surface wind speed and roughness.