Many Sign language translation (SLT) systems quietly assume that brief chunks of signing map directly to spoken-language words.That assumption breaks down because signers often create meaning on the fly using context, space, and movement.We revisit SLT and argue that it is mainly a cross-modal reasoning task, not just a straightforward video-to-text conversion.We thus introduce a reasoning-driven SLT framework that uses an ordered sequence of latent thoughts as an explicit middle layer between the video and the generated text.These latent thoughts gradually extract and organize meaning over time.On top of this, we use a planthen-ground decoding method: the model first decides what it wants to say, and then looks back at the video to find the evidence.This separation improves coherence and faithfulness.We also built and released a new large-scale gloss-free SLT dataset with stronger context dependencies and more realistic meanings.Experiments across several benchmarks show consistent gains over existing gloss-free methods.

Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal understanding, but they frequently suffer from hallucination -generating content inconsistent with visual inputs.In this work, we explore a novel perspective on hallucination mitigation by examining the intermediate activations of LVLMs during generation.Our investigation reveals that hallucinated content manifests as distinct, identifiable patterns in the model's hidden state space.Motivated by this finding, we propose Activation Steering Decoding (ASD), a training-free approach that mitigates hallucination through targeted intervention in the model's intermediate activations.ASD operates by first identifying directional patterns of hallucination in the activation space using a small calibration set, then employing a contrast decoding mechanism that computes the difference between positive and negative steering predictions.This approach effectively suppresses hallucination patterns while preserving the model's general capabilities.Extensive experiments demonstrate that our method significantly reduces hallucination across multiple benchmarks while maintaining performance on general visual understanding tasks.Notably, our approach requires no model re-training or architectural modifications, making it readily applicable to existing deployed models.

Topic modeling is a powerful unsupervised tool for knowledge discovery.However, existing work struggles with generating limited-quality topics that are uninformative and incoherent, which hinders interpretable insights from managing textual data.In this paper, we improve the original variational autoencoder framework by incorporating contextual and graph information to address the above issues.First, the encoder utilizes topic fusion techniques to combine contextual and bag-of-words information well, and meanwhile exploits the constraints of topic alignment and topic sharpening to generate informative topics.Second, we develop a simple word co-occurrence graph information fusion strategy that efficiently increases topic coherence.On three benchmark datasets, our new framework generates more coherent and diverse topics compared to various baselines, and achieves strong performance on both automatic and manual evaluations.We make our code available for reproduction 1 .

The isomorphism problem is a key challenge in both graph and hypergraph domains, crucial for applications like protein design, chemical pathways, and community detection. Hypergraph isomorphism, which models high-order relationships in real-world scenarios, remains underexplored compared to the graph isomorphism. Current algorithms for hypergraphs, like the 1-dimensional generalized Weisfeiler-Lehman test (1-GWL), lag behind advancements in graph isomorphism tests, limiting most hypergraph neural networks to 1-GWL's expressive power. To address this, we propose the high-dimensional GWL (k-GWL), generalizing k-WL from graphs to hypergraphs. We prove that k-GWL reduces to k-WL for simple graphs, and thus develop a unified isomorphism method for both graphs and hypergraphs. We also successfully establish a clear and complete understanding of the GWL hierarchy of expressivity, showing that (k+1)-GWL is more expressive than k-GWL with illustrative examples. Based on k-GWL, we develop a hypergraph neural network model named k-HNN with improved expressive power of k-GWL, which achieves superior performance on real-world datasets, including a 6\% accuracy improvement on the Steam-Player dataset over the runner-up. Our code is available at https://github.com/talence-zcq/KGWL.

Bilinear interpolation is widely used in classical signal and image processing. Quantum algorithms have been designed for efficiently realizing bilinear interpolation. However, these quantum algorithms have limitations in circuit width and garbage outputs, which block the quantum algorithms applied to noisy intermediate-scale quantum devices. In addition, the existing quantum bilinear interpolation algorithms cannot keep the consistency between the geometric centers of the original and target images. To save the above questions, we propose quantum bilinear interpolation algorithms based on geometric centers using fault-tolerant implementations of quantum arithmetic operators. Proposed algorithms include the scaling-up and scaling-down for signals (grayscale images) and signals with three channels (color images). Simulation results demonstrate that the proposed bilinear interpolation algorithms obtain the same results as their classical counterparts with an exponential speedup. Performance analysis reveals that the proposed bilinear interpolation algorithms keep the consistency of geometric centers and significantly reduce circuit width and garbage outputs compared to the existing works.

In this paper, we present an optimal frame synchronization scheme for DVB-S2 system. The scheme is based on differential detection and non-threshold peak search algorithm to achieve frame synchronization. By further analyzing the structure of the Physical Layer Header (PLHEADER) that consists of Start of Frame (SOF) and Physical Layer Signalling Code (PLSC), we find some useful properties that can enhance the frame synchronization and reduce the complexity of its implementation. We also introduce some optimizations into the algorithm. Especially, the modifications made on the peak search algorithm improve the overall performance of the frame synchronization. The experimental results show that the optimal frame synchronization can be achieved under large carrier frequency offset (as large as 5MHz at 25MSps) and low SNR threshold of −2.3dB. Compared with previously proposed approaches, the scheme described in this paper takes less time to acquire frame synchronization and seems to be more robust.

Manufacturing Execution Systems (MES), a category of industrial software for the manufacturing environment, is grasping increasing attention, due to its unique ability to improve manufacturing performance, and then to have a positive impact on the financial performance of the company. For many executives, whether to implement MES to improve manufacturing and financial performance is an issue they must encounter. Since what MES brings about are not only benefits and potential opportunities, but also costs and potential risks, a comprehensive and systematic assessment is absolutely necessary before making such a critical investment decision. This paper proposes a decision methodology for MES investment decision making. In addition, a general decision model with respect to Benefits, Opportunities, Costs and Risks merits is provided. The decision methodology and decision model are validated by an undershirt manufacturer in China, by applying Analytic Network Process (ANP) method.

A new scheme is developed for the extraction of local texture features. This scheme, defined as the local spectral mapping (LSM), transforms a textured image into a gray-level one. The power spectrum of a local region is divided into a number of rings and wedges, and local spectral vectors are formed by summing the energy in these rings or wedges as vector elements. Two new texture measures, the linear radial feature enhancement measure (LRFE) and the linear angular feature enhancement measure (LAEF), are designed. A segmentation algorithm is implemented and applied to a set of textured images. Good results are achieved, with more than 92% of the pixel population being correctly classified for each of the test images.