Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities—such as time series, system logs, and tabular records—as exemplified by modern IT systems. Effective AD methods in such environments must therefore possess two critical capabilities: (1) the ability to handle heterogeneous data formats within a unified framework, allowing the model to process and detect multiple modalities in a consistent manner during anomalous events; (2) a strong generalization ability to quickly adapt to new scenarios without extensive retraining. However, most existing methods fall short of these requirements, as they typically focus on single modalities and lack the flexibility to generalize across domains. To address this gap, we introduce a novel paradigm: In-Context Anomaly Detection (ICAD), where anomalies are defined by their dissimilarity to a relevant reference set of normal samples. Under this paradigm, we propose ICAD-LLM, a unified AD framework leveraging Large Language Models' in-context learning abilities to process heterogeneous data within a single model. Extensive experiments demonstrate that ICAD-LLM achieves competitive performance with task-specific AD methods and exhibits strong generalization to previously unseen tasks, which substantially reduces deployment costs and enables rapid adaptation to new environments. To the best of our knowledge, ICAD-LLM is the first model capable of handling anomaly detection tasks across diverse domains and modalities.

Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions, thereby enabling scalable video generation with effective motion guidance. Specifically, Tora consists of a Trajectory Extractor (TE), a Spatial-Temporal DiT, and a Motion-guidance Fuser (MGF). The TE encodes arbitrary trajectories into hierarchical spacetime motion patches with a 3D motion compression network. The MGF integrates the motion patches into the DiT blocks to generate consistent videos that accurately follow designated trajectories. Our design aligns seamlessly with DiT’s scalability, allowing precise control of video content’s dynamics with diverse durations, aspect ratios, and resolutions. Extensive experiments demonstrate that Tora excels in achieving high motion fidelity compared to the foundational DiT model, while also accurately simulating the complex movements of the physical world. Code is made available at https://github.com/alibaba/Tora.

Recent developments in Video Diffusion Models (VDMs) have demonstrated remarkable capability to generate high-quality video content. Nonetheless, the potential of VDMs for creating transparent videos remains largely uncharted. In this paper, we introduce TransVDM, the first diffusion-based model specifically designed for transparent video generation. TransVDM integrates a Transparent Variational Autoencoder (TVAE) and a pretrained UNet-based VDM, along with a novel Alpha Motion Constraint Module (AMCM). The TVAE captures the alpha channel transparency of video frames and encodes it into the latent space of the VDMs, facilitating a seamless transition to transparent video diffusion models. To improve the detection of transparent areas, the AMCM integrates motion constraints from the foreground within the VDM, helping to reduce undesirable artifacts. Moreover, we curate a dataset containing 250K transparent frames for training. Experimental results demonstrate the effectiveness of our approach across various benchmarks.

Recent advances in diffusion transformer models for motion-guided video generation, such as Tora, have shown significant progress. In this paper, we present Tora2, an enhanced version of Tora, which introduces several design improvements to expand its capabilities in both appearance and motion customization. Specifically, we introduce a decoupled personalization extractor that generates comprehensive personalization embeddings for multiple open-set entities, better preserving fine-grained visual details compared to previous methods. Building on this, we design a gated self-attention mechanism to integrate trajectory, textual description, and visual information for each entity. This innovation significantly reduces misalignment in multimodal conditioning during training. Moreover, we introduce a contrastive loss that jointly optimizes trajectory dynamics and entity consistency through explicit mapping between motion and personalization embeddings. Tora2 is, to our best knowledge, the first method to achieve simultaneous multi-entity customization of appearance and motion for video generation. Experimental results demonstrate that Tora2 achieves competitive performance with state-of-the-art customization methods while providing advanced motion control capabilities, which marks a critical advancement in multi-condition video generation.

The upcoming satellite-integrated Internet can provide onboard remote sensing image processing and efficient communication to ensure ubiquitous intelligent services. Given the massive volume of remote sensing images, the efficient extraction and transmission of task-oriented information to the corresponding user equipment (UE) remains a critical challenge. To address this challenge, we propose a task-oriented semantic coding and utility-optimal transmission (TUT) framework for satellite-integrated Internet. Specifically, we propose a metric named utility loss of information (UoI) to simultaneously capture the freshness, task updates, and task completion of UEs. Building upon this metric, our TUT framework leverages perceptual-weight maps (PM) generated from the remote sensing images which allowing for variable code rates specific to the tasks of UEs. Besides, the TUT framework can dynamically adjust the numerical distribution of PM to optimize semantic coding tailored to UoI. Considering limited onboard resources, we further model a long-term UoI minimization problem by utilizing the Lyapunov optimization framework and decompose it into a set of single-slot problems, and employ a proximal policy optimization (PPO) algorithm to solve this non-convex UoI minimization problem. Simulation results demonstrate that our TUT framework can achieve minimum long-term average UoI and power consumption compared to the state-of-the-art schemes.

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history. We design a novel decoupled network architecture with the original backbone LLM frozen as a memory encoder and an adaptive residual side-network as a memory retriever and reader. Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness. Enhanced with memory-augmented adaptation training, LongMem can thus memorize long past context and use long-term memory for language modeling. The proposed memory retrieval module can handle unlimited-length context in its memory bank to benefit various downstream tasks. Typically, LongMem can enlarge the long-form memory to 65k tokens and thus cache many-shot extra demonstration examples as long-form memory for in-context learning. Experiments show that our method outperforms strong long-context models on ChapterBreak, a challenging long-context modeling benchmark, and achieves remarkable improvements on memory-augmented in-context learning over LLMs. The results demonstrate that the proposed method is effective in helping language models to memorize and utilize long-form contents.

End-to-end speech-to-text translation (E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the triplet training corpus〈speech, transcription, translation〉, the conventional high-quality E2E-ST system leverages the〈speech, transcription〉pair to pre-train the model and then utilizes the〈speech, translation〉pair to optimize it further. However, this process only involves two-tuple data at each stage, and this loose coupling fails to fully exploit the association between triplet data. In this paper, we attempt to model the joint probability of transcription and translation based on the speech input to directly leverage such triplet data. Based on that, we propose a novel regularization method for model training to improve the agreement of dual-path decomposition within triplet data, which should be equal in theory. To achieve this goal, we introduce two Kullback-Leibler divergence regularization terms into the model training objective to reduce the mismatch between output probabilities of dual-path. Then the well-trained model can be naturally transformed as the E2E-ST models by a pre-defined early stop tag. Experiments on the MuST-C benchmark demonstrate that our proposed approach significantly outperforms state-of-the-art E2E-ST baselines on all 8 language pairs while achieving better performance in the automatic speech recognition task.

The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters.However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet data is scarce or nonexistent.In this paper, we propose a novel nonparametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems.To this end, we first incorporate an additional encoder into the pre-trained E2E-ST model to realize text translation modeling, based on which the decoder's output representations for text and speech translation tasks are unified by reducing the correspondent representation mismatch in available triplet training data.During domain adaptation, a k-nearest-neighbor (kNN) classifier is introduced to produce the final translation distribution using the external datastore built by the domain-specific text translation corpus, while the universal output representation is adopted to perform a similarity search.Experiments on the Europarl-ST benchmark demonstrate that when in-domain text translation data is involved only, our proposed approach significantly improves baseline by 12.82 BLEU on average in all translation directions, even outperforming the strong in-domain fine-tuning strategy.

In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing. However, directly applying this method heavily suffers from the dialogue entity inconsistency caused by the removal of delexicalized tokens, as well as the catastrophic forgetting problem of the pre-trained model during fine-tuning, leading to unsatisfactory performance. To alleviate these problems, we design a novel GPT-Adapter-CopyNet network, which incorporates the lightweight adapter and CopyNet modules into GPT-2 to achieve better performance on transfer learning and dialogue entity generation. Experimental results conducted on the DSTC8 Track 1 benchmark and MultiWOZ dataset demonstrate that our proposed approach significantly outperforms baseline models with a remarkable performance on automatic and human evaluations.

In this paper, a two-dimensional weighted fractional Fourier transform (2DWFRFT) based secure spatial modulation (SM) scheme is proposed to enhance the physical layer security (PLS) of the wireless communication system. In the proposed scheme, 2DWFRFT is implemented as the security kernel for PLS provision. The invertibility and uniqueness of the 2DWFRFT effectively protect the confidential messages from being intercepted by the eavesdroppers while imposing no performance degradation on the legitimate receiver. Both the signal generation strategy and the ergodic secrecy rate analysis under discrete-input continuous-output memoryless (DCMC) channel have been elaborated to depict the security mechanism of the proposed scheme. The maximum likelihood (ML) detector and the separate detection (SD) algorithm are formulated to correctly recover the received signal of our system. Simulation results demonstrate that the proposed scheme can achieve a much higher secrecy capacity than artificial noise schemes without requiring additional jamming power consumption.

Space information network (SIN) is regarded as an effective solution to enable ubiquitous connectivity in a global coverage and a cost-effective manner for massive machine type communications (mMTC) in the future internet of things (IoT). In this paper, we study an uplink code-domain non-orthogonal multiple access (CD-NOMA) mMTCs system for SINs, and introduce an uncoordinated code-domain NOMA protocol. Considering the dominant traffic in uplink mMTC communications is short packet, where the fixed length control overhead becomes inefficient due to the short length of payload. To address this challenge, superimposed pilots (SP) scheme is adopted for synchronization and channel estimation. Moreover, we utilize successive interference cancellation (SIC) and successive joint decoding (SJD) to recover the signals in collisions under the shadowed-Rician fading and path loss satellite-ground channel, and the expressions of the outage probability and maximum system throughput of SP with SIC and SJD decoding methods are derived, respectively. Simulation results validate our analytical results and show that the maximum system throughput of SP with SJD can outperform that of SIC in SIN for a short packet transmission.

Internet of Vehicle (IoV) is a promising Internet of Thing (IoT) application, where roadside unit (RSU) plays an important role to transmit traffic information to cloud server through internet. However, there exists redundancy among the data collected with a data collection period by a single vehicle, which may cause network congestion and waste the storage of cloud. In this paper, we propose to equip each RSU with a mobile edge computing (MEC) server, and differential compress data at edge node, for saving the transmission time and storage space. First, we present a new cost model for COPY/ADD class, then a metric to measure a differential compression algorithm is given. we propose a Maximal Length of COPYs (MLOC) algorithm that can construct a good delta encoding based on our cost model and evaluation. Theoretical analysis proves that the proposed MLOC algorithm constructs a delta encoding with minimal amount of COPYs on the premise of maximal total length of data segments copied. Numerical results show that MLOC algorithm can get better performance in constructing a good delta encoding between two data compared with Simple Greedy algorithm and Hash Suffix Array Delta (Hsadelta) algorithm.