MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifying text and processed by frozen text encoders in pretrained VLMs or LLMs. While this design leverages the strengths of large pretrained models, it only supervises the adapter to produce encoder-compatible tokens that loosely preserve visual semantics. Crucially, it does not directly optimize the composed query representation to capture the full intent of the composition or to align with the target semantics, thereby limiting retrieval performance, particularly in cases involving fine-grained or complex visual transformations. To address this problem, we propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI), a novel approach that leverages a pretrained multimodal large language model (MLLM) to construct two complementary training tasks using only unlabeled images: target text retrieval taskand text-to-image retrieval task. By jointly optimizing these tasks, our method enables the VLM to inherently acquire robust compositional retrieval capabilities, supported by the provided theoretical justifications and empirical validation. Furthermore, during inference, we further prompt the MLLM to generate target texts from composed queries and compute retrieval scores by integrating similarities between (i) the composed query and candidate images, and (ii) the MLLM-generated target text and candidate images. This strategy effectively combines the VLM's semantic alignment strengths with the MLLM's reasoning capabilities.

VORTA: Efficient Video Diffusion via Routing Sparse Attention

Video Diffusion Transformers (VDiTs) have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent attention acceleration methods leverage the sparsity of attention patterns to improve efficiency; however, they often overlook inefficiencies of redundant long-range interactions. To address this problem, we propose \textbf{VORTA}, an acceleration framework with two novel components: 1) a sparse attention mechanism that efficiently captures long-range dependencies, and 2) a routing strategy that adaptively replaces full 3D attention with specialized sparse attention variants throughout the sampling process. It achieves a $1.76\times$ end-to-end speedup without quality loss on VBench. Furthermore, VORTA can seamlessly integrate with various other acceleration methods, such as caching and step distillation, reaching up to $14.41\times$ speedup with negligible performance degradation. VORTA demonstrates its efficiency and enhances the practicality of VDiTs in real-world settings.

Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift

Anomaly detection plays a crucial role in quality control for industrial applications. However, ensuring robustness under unseen domain shifts such as lighting variations or sensor drift remains a significant challenge. Existing methods attempt to address domain shifts by training generalizable models but often rely on prior knowledge of target distributions and can hardly generalise to backbones designed for other data modalities. To overcome these limitations, we build upon memory-bank-based anomaly detection methods, optimizing a robust Sinkhorn distance on limited target training data to enhance generalization to unseen target domains. We evaluate the effectiveness on both 2D and 3D anomaly detection benchmarks with simulated distribution shifts. Our proposed method demonstrates superior results compared with state-of-the-art anomaly detection and domain adaptation methods.

Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion

Multi-camera systems provide richer contextual information for industrial anomaly detection. However, traditional methods process each view independently, disregarding the complementary information across viewpoints. Existing multi-view anomaly detection approaches typically employ data-driven cross-view attention for feature fusion but fail to leverage the unique geometric properties of multi-camera setups. In this work, we introduce an epipolar geometry-constrained attention module to guide cross-view fusion, ensuring more effective information aggregation. To further enhance the potential of cross-view attention, we propose a pretraining strategy inspired by memory bank-based anomaly detection. This approach encourages normal feature representations to form multiple local clusters and incorporate multi-view aware negative sample synthesis to regularize pretraining. We demonstrate that our epipolar guided multi-view anomaly detection framework outperforms existing methods on the state-of-the-art multi-view anomaly detection dataset.

Ambient Backscatter Communication in LTE Uplink Sounding Reference Signal

Ambient Internet of Things (AIoT), recently standardized by the 3rd Generation Partnership Project (3GPP), demands a low-power wide-area communication solution that operates several orders of magnitude below the power requirements of existing 3GPP specifications. Ambient backscatter communication (AmBC) is considered as a competitive potential technique by harvesting energy from the ambient RF signal. This paper considers a symbiotic AmBC into Long Term Evolution (LTE) cellular system uplink. Leveraging by LTE uplink channel estimation ability, AIoT conveys its own message to Base Station (BS) by modulating backscatter path. We explore the detector design, analyze the error performance of the proposed scheme, provide exact expression and its Guassian approximation for the error probability. We corroborate the receiver error performance by Monte Carlo simulation. Analysis of communication range reveals AmBC achieves a reasonable BER of order of magnitude $10^{-2}$ within four times wavelength reading distance. In addition, a AmBC prototype in LTE uplink confirms the its feasibility. The over-the-air experiment results validate theoretical analysis. Hence, the proposed AmBC approach enables AIoT deployment with minimal changes to the LTE system.

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

Video Diffusion Transformers (DiTs) have demonstrated significant potential for generating high-fidelity videos but are computationally intensive. Existing acceleration methods include distillation, which requires costly retraining, and feature caching, which is highly sensitive to network architecture. Recent token reduction methods are training-free and architecture-agnostic, offering greater flexibility and wider applicability. However, they enforce the same sequence length across different components, constraining their acceleration potential. We observe that intra-sequence redundancy in video DiTs varies across features, blocks, and denoising timesteps. Building on this observation, we propose Asymmetric Reduction and Restoration (AsymRnR), a training-free approach to accelerate video DiTs. It offers a flexible and adaptive strategy that reduces the number of tokens based on their redundancy to enhance both acceleration and generation quality. We further propose matching cache to facilitate faster processing. Integrated into state-of-the-art video DiTs, AsymRnR achieves a superior speedup without compromising the quality.

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing

While open-source video generation and editing models have made significant progress, individual models are typically limited to specific tasks, failing to meet the diverse needs of users. Effectively coordinating these models can unlock a wide range of video generation and editing capabilities. However, manual coordination is complex and time-consuming, requiring users to deeply understand task requirements and possess comprehensive knowledge of each model's performance, applicability, and limitations, thereby increasing the barrier to entry. To address these challenges, we propose a novel video generation and editing system powered by our Semantic Planning Agent (SPAgent). SPAgent bridges the gap between diverse user intents and the effective utilization of existing generative models, enhancing the adaptability, efficiency, and overall quality of video generation and editing. Specifically, the SPAgent assembles a tool library integrating state-of-the-art open-source image and video generation and editing models as tools. After fine-tuning on our manually annotated dataset, SPAgent can automatically coordinate the tools for video generation and editing, through our novelly designed three-step framework: (1) decoupled intent recognition, (2) principle-guided route planning, and (3) capability-based execution model selection. Additionally, we enhance the SPAgent's video quality evaluation capability, enabling it to autonomously assess and incorporate new video generation and editing models into its tool library without human intervention. Experimental results demonstrate that the SPAgent effectively coordinates models to generate or edit videos, highlighting its versatility and adaptability across various video tasks.

Diffusion Model-Based Video Editing: A Survey

The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editing has gained substantial attention and seen a swift rise in research activity, necessitating a comprehensive and systematic review of the existing literature. This paper reviews diffusion model-based video editing techniques, including theoretical foundations and practical applications. We begin by overviewing the mathematical formulation and image domain's key methods. Subsequently, we categorize video editing approaches by the inherent connections of their core technologies, depicting evolutionary trajectory. This paper also dives into novel applications, including point-based editing and pose-guided human video editing. Additionally, we present a comprehensive comparison using our newly introduced V2VBench. Building on the progress achieved to date, the paper concludes with ongoing challenges and potential directions for future research.

COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection

Existing approaches towards anomaly detection~(AD) often rely on a substantial amount of anomaly-free data to train representation and density models. However, large anomaly-free datasets may not always be available before the inference stage; in which case an anomaly detection model must be trained with only a handful of normal samples, a.k.a. few-shot anomaly detection (FSAD). In this paper, we propose a novel methodology to address the challenge of FSAD which incorporates two important techniques. Firstly, we employ a model pre-trained on a large source dataset to initialize model weights. Secondly, to ameliorate the covariate shift between source and target domains, we adopt contrastive training to fine-tune on the few-shot target domain data. To learn suitable representations for the downstream AD task, we additionally incorporate cross-instance positive pairs to encourage a tight cluster of the normal samples, and negative pairs for better separation between normal and synthesized negative samples. We evaluate few-shot anomaly detection on on 3 controlled AD tasks and 4 real-world AD tasks to demonstrate the effectiveness of the proposed method.

Coded Backscattering Communication with LTE Pilots as Ambient Signal

The 3GPP has recently conducted a study on the Ambient Internet of Things (AIoT), with a particular emphasis on examining backscatter communications as one of the primary techniques under consideration. Previous investigations into Ambient Backscatter Communications (AmBC) within the long term evolution (LTE) downlink have shown that it is feasible to utilize the user equipment channel estimator as a receiver for demodulating frequency shift keyed (FSK) messages transmitted by the backscatter devices. In practical deployment scenarios, the backscattered link often experiences a low signal-to-noise ratio, leading to subpar bit error rate (BER) performance in the case of uncoded transmissions. In this paper, we propose the adoption of the same convolutional coding methodology for backscatter links that is already employed for LTE downlink control signals. This approach facilitates the reuse of identical demodulation functions at the modem for both control signals and backscattered AIoT messages. To assess the performance of the proposed scheme, we conducted experiments utilizing real LTE downlink signals generated by a mobile operator within an office environment. When compared to uncoded FSK, convolutional channel coding delivers a notable gain of approximately 6 dB at a BER of $10^{-3}$. Consequently, the AmBC system demonstrates a high level of reliability, achieving a BER of $10^{-3}$ at a Signal-to-Noise Ratio (SNR) of 5 dB.