An Australian film that was digitally altered to change a same-sex couple to a heterosexual one has drawn backlash from moviegoers in China. Together, a horror film starring Dave Franco and Alison Brie, was shown in selected Chinese cinemas in advance screenings on 12 September. Cinemagoers later realised some scenes had been modified after screenshots showing the original scenes went viral online. The film was due to be publicly released on 19 September - but as of Thursday has yet to be aired in cinemas. The film's global distributor, Neon, later condemned the edit, saying they did not approve of [this] unauthorised edit... and demand they ceased distribution, according to reports.

Can Ukraine restore its pre-war borders? How is Russia replenishing its military? At least two people were killed by a daytime Ukrainian drone attack on the Russian city of Novorossiysk on Wednesday, according to The Moscow Times. Among those injured were employees of a Russian-Kazakh oil project. Russia's Ministry of Defence on Wednesday said 1,495 Ukrainian troops were killed in the past 24 hours of fighting, according to Russia's state news agency TASS.

Denmark's Aalborg airport in the country's north has been closed after unauthorised drones were seen in its airspace, according to local authorities. Three other smaller airports in the country's southern region - Esbjerg, Sønderborg and Skrydstrup - also reported drone activity, but were not closed. The incident comes after the country's Copenhagen airport was forced to close earlier this week due to a drone incursion, which the prime minister described as the most severe attack on Danish infrastructure so far. Police said the devices could be seen from the ground, adding they couldn't rule out the activity being a prank. They were investigating who was controlling them and their motive.

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile edge computing (MEC) systems. Therefore, we propose an FA-assisted MEC offloading framework to minimize system delay. This framework faces two severe challenges, which are the complexity of channel estimation due to dynamic port configuration and the inherent non-convexity of the joint optimization problem. Firstly, we propose Information Bottleneck Metric-enhanced Channel Compressed Sensing (IBM-CCS), which advances FA channel estimation by integrating information relevance into the sensing process and capturing key features of FA channels effectively. Secondly, to address the non-convex and high-dimensional optimization problem in FA-assisted MEC systems, which includes FA port selection, beamforming, power control, and resource allocation, we propose a game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm (HiTDMA) based offloading scheme, where the hierarchical structure effectively decouples and coordinates the optimization tasks between the user side and the base station side. Crucially, the game theory effectively reduces the dimensionality of power control variables, allowing deep reinforcement learning (DRL) agents to achieve improved optimization efficiency. Numerical results confirm that the proposed scheme significantly reduces system delay and enhances offloading performance, outperforming benchmarks. Additionally, the IBM-CCS channel estimation demonstrates superior accuracy and robustness under varying port densities, contributing to efficient communication under imperfect CSI.

Tensor decompositions have emerged as powerful analytical tools across diverse fields including signal/image processing [1, 2, 3, 4, 5, 6], chemometrics [7], geophysics [8, 9], and neuroscience [10, 11, 12, 13]. Their effectiveness stems from their ability to approximate high-dimensional tensors with low-rank decompositions, offering efficient dimensionality reduction while preserving essential structural information. For example, tensor decomposition techniques [14, 15, 16] are applied in hyperspectral image (HSI) analysis to extract low-rank structures for dimensionality reduction [9], and used in electroencephalogram (EEG) analysis to capture latent patterns across multiple dimensions [10]. Over the past decade, tensor regression (TR) models have received attention, with numerous approaches proposed in the literature, including Tucker tensor regression [17], low-rank orthogonally decomposable tensor regression [18], Bayesian Kruskal tensor regression (KTR) [19], Bayesian low rank tensor ring completion [20], graph-regularized tensor regression [21], and tensor regression network [22].

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading architecture, achieving state-of-the-art results across a range of language modeling tasks. However, Mamba's performance significantly deteriorates when applied to contexts longer than those seen during pre-training, revealing a sharp sensitivity to context length extension. Through detailed analysis, we attribute this limitation to the out-of-distribution behaviour of its state-space dynamics, particularly within the parameterization of the state transition matrix $\mathbf{A}$. Unlike recent works which attribute this sensitivity to the vanished accumulation of discretization time steps, $\exp(-\sum_{t=1}^NΔ_t)$, we establish a connection between state convergence behavior as the input length approaches infinity and the spectrum of the transition matrix $\mathbf{A}$, offering a well-founded explanation of its role in length extension. Next, to overcome this challenge, we propose an approach that applies spectrum scaling to pre-trained Mamba models to enable robust long-context generalization by selectively modulating the spectrum of $\mathbf{A}$ matrices in each layer. We show that this can significantly improve performance in settings where simply modulating $Δ_t$ fails, validating our insights and providing avenues for better length generalization of state-space models with structured transition matrices.

Ge'ez is an ancient Semitic language renowned for its unique alphabet. It serves as the script for numerous languages, including Tigrinya and Amharic, and played a pivotal role in Ethiopia's cultural and religious development during the Aksumite kingdom era. Ge'ez remains significant as a liturgical language in Ethiopia and Eritrea, with much of the national identity documentation recorded in Ge'ez. These written materials are invaluable primary sources for studying Ethiopian and Eritrean philosophy, creativity, knowledge, and civilization. Ge'ez has a complex morphological structure with rich inflectional and derivational morphology, and no usable NLP has been developed and published until now due to the scarcity of annotated linguistic data, corpora, labeled datasets, and lexicons. Therefore, we propose a rule-based Ge'ez morphological synthesizer to generate surface words from root words according to the morphological structures of the language. We used 1,102 sample verbs, representing all verb morphological structures, to test and evaluate the system. The system achieves a performance of 97.4%, outperforming the baseline model and suggesting that future work should build a comprehensive system considering morphological variations of the language. Keywords: Ge'ez, NLP, morphology, morphological synthesizer, rule-based

Traffic accidents remain a major global concern, with lane-change maneuvers recognized as one of the significant contributors to collision risk. Anticipating these maneuvers has become an important research focus, supporting both traffic safety and the safe integration of autonomous and assisted driving technologies. Over the past decade, numerous models have been developed for lane-change prediction. However, most existing works have been designed and validated using simulation environments or pre-recorded datasets. While these settings allow for benchmarking and controlled evaluation, they often rely on simplified assumptions about sensing, communication, and vehicle behavior that do not fully capture the complexity of real-world operation. Real-world deployments of lane-change prediction systems are relatively rare, and when they are reported, their practical challenges, limitations, and insights remain under-documented. To illustrate the setting more concretely, consider the left lane change scenario shown in Figure 1. The Ego Vehicle (EV) is driving in the left lane, while the Target Vehicle (TV) is moving in the right lane behind a Preceding Vehicle (PV). When the PV suddenly brakes, the TV must change lanes to avoid a collision.

Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related to various factors (e.g., data size, economic and social factors) whose impact, however, turns out to be inconsistent. In this work, we investigate factors impacting the model performance more directly: we correlate Tokenization Parity (TP) and Information Parity (IP), as measures of representational biases in pre-trained multilingual models, with the downstream performance. We compare state-of-the-art decoder-only LLMs with encoder-based models across three tasks: dialect classification, topic classification, and extractive question answering, controlling for varying scripts (Latin vs. non-Latin) and resource availability (high vs. low). Our analysis reveals that TP is a better predictor of the performance on tasks reliant on syntactic and morphological cues (e.g., extractive QA), while IP better predicts performance in semantic tasks (e.g., topic classification). Complementary analyses, including tokenizer behavior, vocabulary coverage, and qualitative insights, reveal that the language support claims of LLMs often might mask deeper mismatches at the script or token level.

Edge intelligence has emerged as a promising strategy to deliver low-latency and ubiquitous services for mobile devices. Recent advances in fine-tuning mechanisms of foundation models have enabled edge intelligence by integrating low-rank adaptation (LoRA) with federated learning. However, in wireless networks, the device heterogeneity and resource constraints on edge devices pose great threats to the performance of federated fine-tuning. To tackle these issues, we propose to optimize federated fine-tuning in heterogenous wireless networks via online learning. First, the framework of switching-based federated fine-tuning in wireless networks is provided. The edge devices switches to LoRA modules dynamically for federated fine-tuning with base station to jointly mitigate the impact of device heterogeneity and transmission unreliability. Second, a tractable upper bound on the inference risk gap is derived based on theoretical analysis. To improve the generalization capability, we formulate a non-convex mixed-integer programming problem with long-term constraints, and decouple it into model switching, transmit power control, and bandwidth allocation subproblems. An online optimization algorithm is developed to solve the problems with polynomial computational complexity. Finally, the simulation results on the SST-2 and QNLI data sets demonstrate the performance gains in test accuracy and energy efficiency.