Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts between robotic action data, primarily due to substantial numerical variations in action commands across diverse robotic platforms and tasks, hindering the effective transfer of pretrained knowledge. To address this limitation, we propose a semantically grounded linguistic representation to normalize actions for efficient pretraining. Unlike conventional discretized action representations that are sensitive to numerical scales, the motion representation specifically disregards numeric scale effects, emphasizing directionality instead. This abstraction mitigates distribution shifts, yielding a more generalizable pretraining representation. Moreover, using the motion representation narrows the feature distance between action tokens and standard vocabulary tokens, mitigating modality gaps. Multi-task experiments on two benchmarks demonstrate that the proposed method significantly improves generalization performance and transferability in robotic manipulation tasks.

The Chat Generative Pre-trained Transformer (ChatGPT), a prominent example of Artificial Intelligence Generated Content (AIGC) technology, has garnered considerable attention from educational researchers and is increasingly employed in education. Learners' attitudes toward tools like ChatGPT are crucial for maximising their educational effectiveness. Previous research has overlooked the multidimensional structure of learners' attitudes toward emerging technologies, encompassing both positive and negative emotional and rational dimensions. This study aimed to develop and validate a scale, the Learners' Attitudes Toward ChatGPT Scale (LATCS), for assessing university students' attitudes toward ChatGPT. First, initial scale items were generated. A rigorous stratified random sampling method was employed, recruiting a total sample of 850 university students from seven universities across four administrative regions in mainland China. Following psychometric procedures, the total sample was split into two subsamples: an exploratory sample and a validation sample. The exploratory sample, consisting of 425 participants, was used to conduct exploratory and confirmatory factor analyses to develop the preliminary LATCS, comprising 16 items. The validation sample, with an independent sample of 425 participants (115 males), was used to validate the LATCS's reliability and validity through confirmatory factor analysis. These findings offer a scientific tool for further exploring individuals' attitudes toward ChatGPT.

Task-oriented dialogue systems have become overwhelmingly popular in recent researches. Spoken Language Understanding (SLU) is widely used to extract the semantics frame of user queries and comprehend users’ intent/emotion/dialogue state in task-oriented dialogue systems. Most previous works on such discriminative tasks only model current query or historical conversations. Even if the entire conversation flow is modeled in some work, it is not suitable for real-world task-oriented dialogue systems, where future contexts are not visible until a response is given based on the current dialogue state. In this paper, we propose to jointly model historical and future information using knowledge distillation methods to address the discrepancy between offline and online information in dialogue understanding. More specifically, by modeling the current utterance and past contexts as student, and the entire dialogue flow as teacher, we optimize the "distance" between these two networks to regularize our student model in both online and offline ways. Our experiments on two dialogue datasets validate the effectiveness of our proposed method, achieving superior results compared with all baseline models.

A long-standing goal in the field of sensory substitution is enabling sound perception for deaf and hard of hearing (DHH) people by visualizing audio content. Different from existing models that translate to hand sign language, between speech and text, or text and images, we target immediate and low-level audio to video translation that applies to generic environment sounds as well as human speech. Since such a substitution is artificial, with-out labels for supervised learning, our core contribution is to build a mapping from audio to video that learns from unpaired examples via high-level constraints. For speech, we additionally disentangle content from style, such as gender and dialect. Qualitative and quantitative results, including a human study, demonstrate that our unpaired translation approach maintains important audio features in the generated video and that videos of faces and numbers are well suited for visualizing high-dimensional audio features that can be parsed by humans to match and distinguish between sounds and words. Project website: https://chunjinsong.github.io/audioviewer

Task-oriented chatbots have been drawing a major demand in industry. In this demo, we present FinBot, a Chinese intelligent financial assistant, which is designed to help customers solve various financial investment problems with good expertise. Our FinBot may automatically understand user queries and respond with proper information accordingly in a dialogue session. To solve the difficulties of modeling financial dialogue histories, we adopt a multi-task model jointly capturing the intent and slots, in which the memory from previous dialogue turns and external user behaviors are exploited to further promote the performance of the dialogue response for better interpretability and user experience. The presented FinBot has been deployed in a mobile application that serves hundreds of millions of users.

Community Question Answering (CQA) is a well-defined task that can be used in many scenarios, such as E-Commerce and online user community for special interests. In these communities, users can post articles, give comment, raise a question and answer it. These data form the heterogeneous information sources where each information source have their own special structure and context (comments attached to an article or related question with answers). Most of the CQA methods only incorporate articles or Wikipedia to extract knowledge and answer the user's question. However, various types of information sources in the community are not fully explored by these CQA methods and these multiple information sources (MIS) can provide more related knowledge to user's questions. Thus, we propose a question-aware heterogeneous graph transformer to incorporate the MIS in the user community to automatically generate the answer. To evaluate our proposed method, we conduct the experiments on two datasets: $\textMSM ^\textplus $ the modified version of benchmark dataset MS-MARCO and the AntQA dataset which is the first large-scale CQA dataset with four types of MIS. Extensive experiments on two datasets show that our model outperforms all the baselines in terms of all the metrics.

Stochastic recurrent neural networks have shown promising performance for modeling complex sequences. Nonetheless, existing methods adopt KL divergence as distribution regularizations in their latent spaces, which limits the choices of models for latent distribution construction. In this paper, we incorporate maximum mean discrepancy in the recurrent structure for distribution regularization. Maximum mean discrepancy is able to measure the difference between two distributions by just sampling from them, which enables us to construct more complicated latent distributions by neural networks. Therefore, our proposed algorithm is able to model more complex sequences. Experiments conducted on two different sequential modeling tasks show that our method outperforms the state-of-the-art sequential modeling algorithms.

Abstract Cybersecurity has gradually become the public focus between common people and countries with the high development of Internet technology in daily life. The cybersecurity knowledge analysis methods have achieved high evolution with the help of knowledge graph technology, especially a lot of threat intelligence information could be extracted with fine granularity. But named entity recognition (NER) is the primary task for constructing security knowledge graph. Traditional NER models are difficult to determine entities that have a complex structure in the field of cybersecurity, and it is difficult to capture non-local and non-sequential dependencies. In this paper, we propose a cybersecurity entity recognition model CyberEyes that uses non-local dependencies extracted by graph convolutional neural networks. The model can capture both local context and graph-level non-local dependencies. In the evaluation experiments, our model reached an F1 score of 90.28% on the cybersecurity corpus under the gold evaluation standard for NER, which performed better than the 86.49% obtained by the classic CNN-BiLSTM-CRF model.

As the E-commerce thrives, high-quality online advertising copywriting has attracted more and more attention.Different from the advertising copywriting for a single product, an advertisement (AD) post includes an attractive topic that meets the customer needs and description copywriting about several products under its topic.A good AD post can highlight the characteristics of each product, thus helps customers make a good choice among candidate products.Hence, multi-product AD post generation is meaningful and important.We propose a novel end-to-end model named S-MG Net to generate the AD post.Targeted at such a challenging real-world problem, we split the AD post generation task into two subprocesses: (1) select a set of products via the SelectNet (Selection Network).(2) generate a post including selected products via the MGenNet (Multi-Generator Network).Concretely, SelectNet first captures the post topic and the relationship among the products to output the representative products.Then, MGen-Net generates the description copywriting of each product.Experiments conducted on a large-scale real-world AD post dataset demonstrate that our proposed model achieves impressive performance in terms of both automatic metrics as well as human evaluations.

Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Pervious works use heuristic methods to avoid KL-vanishing, but it is hard to find an appropriate degree to which these methods should be applied. In this paper, we propose an explicit optimizing objective function to guide the encoder towards the "best encoder" and directly pull the CVAE away from KL-vanishing. A labeling network is introduced to estimate the "best encoder It provides a continuous label in the latent space of CVAE to help build a close connection between latent variables and targets. The whole proposed method is named Self Labeling CVAE (SLCVAE). To boost the research of diverse text generation, we also propose a large native one-to-many dataset. Extensive experiments are conducted on two tasks, which show that our method largely improves the generating diversity while achieving comparable accuracy compared with state-of-the-art algorithms.

In this paper, we propose an accurate automatic chessboard corner detecting algorithm of sub-pixel precision. The algorithm is based on a novel hyperbolic tangent model. A set of corners are detected initially by Harris' algorithm. Then the hyperbolic tangent model for each corner point is optimized by parameter adjustment. Finally, we use the optimal model to obtain the sub-pixel position of each corner with fake corner elimination. Experiments on three datasets show that the proposed method achieves a detection rate of at least 98% and a reprojection error in camera calibration of at most 0.85 pixels. Our algorithm significantly outperforms the methods in three related works.

In distributed sensing systems that use compressed videos for video analysis tasks, the lossy compression of videos can damage the accuracy of object detection, which is an essential step for various vision applications. This paper aims at constructing a new quality model to predict the performance of object detection. To achieve this goal, a distorted video database is constructed by applying object detection algorithms on a variety of videos that are compressed with different levels of distortion. Based on the database, a parametric quality prediction model is built using features that can be easily obtained during the encoding process. Experimental results show that the model can achieve high accuracy in predicting the performance of object detection. The model introduces low computation cost and can be easily integrated in video encoders for rate-quality optimization.

This paper addresses resource management problem in a heterogeneous network consisting of cellular users and multiple D2D pairs. The D2D users share spectrum with cellular uplink under the QoS constraint of cellular system and pay for the interference they cause. We propose a two-step resource management scheme to optimize D2D user's transmitting power and the spectrum efficiency of the network. Firstly, the interference pricing and power allocation problem between a D2D pair and their allocated cellular uplink is formulated as a Stackelberg game. Then the Stackelberg equilibrium, i.e., the optimal interference price and transmitting power that maximize utilities of two players (the base station and the D2D transmitter), is obtained in close form. In the second step, with the close form expressions as important parameters, the situation is extended to multiple D2D pairs and a Hungarian algorithm based method is utilized to assign spectrum band to each D2D pair with the purpose of maximizing system spectrum efficiency. Simulation results demonstrate the advantageous performance of our scheme in network capacity and spectrum efficiency.

This paper proposes a method of fast integral image computing on hardware. We propose a high efficient hardware-based algorithm, and design a pipelined architecture suitable for our algorithm. Parallelism and time complexity of the algorithm are analyzed. And the hardware implementation of each operations of the algorithm is presented. Compared with two related works, we find that our architecture is of the highest efficiency, as it reaches the highest speed by consuming the comparatively lowest logic resources and power.

This paper concerns energy harvesting from vehicle suspension systems. Theoretical and experimental presentation of energy harvesting from suspension is explored. The generated power associated with random excitation inputs to vehicle is determined. The potential values of power generation from various road conditions are calculated. The effect of suspension energy regeneration on the ride comfort and road handling is presented. This includes study of tire deflection, damping, and spring stiffness for a regenerative suspension. The concept of self-powered actuation using the harvested energy from suspension is discussed with regards to applications of self-powered vibration control.

Under current popularity of full duplex radio, this paper explores the adaption of energy detector (ED) to full duplex scenario. To improve sensing performance,firstly a correlation based channel estimation algorithm is formulated to cancel out self-interference. We then notice traditional ED has a long delay in finding sensing error. To tackle this problem, sliding window ED is proposed, in which samples utilized for different sensing instances are allowed to overlap. Moreover, it is also observed that sensing performance degrades seriously when primary user sate changes in the sensing period, which happens frequently in full duplex sensing. Therefore, weighted ED is proposed, in which samples at the end of the sensing period are assigned bigger weights. Simulation results show that our strategies can better adapt energy detector to full duplex sensing with marginal loss in accuracy.

With recent breakthroughs in full-duplex radio, there is a growing trend to combine it with cognitive radio. Thus the topic of spectrum sensing in full-duplex scenario is addressed in this paper. Firstly, the concept of full-duplex spectrum sensing and its advantage over traditional half-duplex spectrum sensing are analyzed. Then a correlation based least square algorithm is formulated to cancel out self-interference, in which no preamble is required. We notice that the phase distribution of noise differs greatly from that of noise-perturbed signals. Therefore, a novel spectrum sensing scheme using phase difference as test statistics is introduced. Its theoretical performance is also analyzed by approximating the test statistics as Gaussian distribution. The proposed detector is simple and immune to noise uncertainty due to the independence of its threshold on noise power. Simulation results show that robust sensing performance can be achieved in full-duplex scenario using correlation based least square and the phase based sensing scheme.

The scaling laws for the throughputs of cognitive network with transmission power of secondary users being constrained are studied. The primary nodes and secondary nodes are randomly and uniformly distributed over the same unit square, with density of n and m (n > m). In this paper, we propose a new hybrid access scheme of multi-hop cognitive network, with primary users and secondary users using TDMA scheme and CDMA scheme respectively. It is shown that primary network achieves the same throughput scaling as that in the case when both primary and secondary network adopts TDMA scheme. Meanwhile, we demonstrate that the upper bound of secondary per- node throughput increases with node density m, in contrast to the decreasing pernode throughput in the existing research, which shows that our scheme not only guarantees primary network but also improves the performance of secondary network.

Powering wireless cellular system by green renewable energy cuts greenhouse gas emissions and electricity bill. However, green energy sources have the limitation of unsustainable availability and capacity. Therefore, the criteria of optimizing network planning for such system should involve both static and dynamic aspects. In this paper, the network planning scheme aims to jointly maximize cell coverage and energy sustainability, which indicate static and dynamic system performance respectively. Firstly, the energy buffer describing green energy evolution is modeled as a G/G/1 queue to investigate energy sustainability. Based on this model, the closed-form expression of service outage probability, which characterizes energy sustainability, is given. Secondly, effective coverage is introduced as a comprehensive parameter which balances cell coverage and energy sustainability. The network planning problem turns to be an effective coverage maximizing problem and solved by automatic cell management. Finally, simulation results are illustrated to validate the proposed automatic cell management.

This paper analyzes the connectivity of cognitive radio networks. The connectivity of cognitive network which is more consistent with reality is redefined in our article and the closed-form formula of relation between connectivity and density of PUs, density of SUs, and transmission radius of SU is given. Specifically, the impact of correlation of adjacent nodes for connectivity of cognitive radio ad hoc network is illustrated. On the basis of Random geometric graph and probability theory, a novel method that divides connectivity of cognitive radio ad hoc network into topological connectivity and physical connectivity is proposed to derive the close-form formula. We prove theoretically that once the density of secondary users is large enough and the transmission radius is appropriate, the probability of cognitive network connectivity tends to a stable non-zero value under the condition that density of primary users is small.

Besides energy-efficient technologies, increasing attention is paid on powering cellular networks with renewable energy sources, concerning climate change, fossil fuel prices and energy security. In this paper, we not only aim to reduce the absolute energy consumption of cellular networks, but also provide a guideline to utilize the renewable energy efficiently in cellular networks. The renewable energy sources have the limitation of unstable availability and capacity. It is thus challenging to improve renewable energy efficiency while maintaining the energy supply sustainability. The energy supply sustainability problem is modeled as an optimization problem aiming to maximize the network energy residue ratio (ERR), which is NP-hard. To solve the optimization problem in polynomial time, the network ERR maximization algorithm is proposed after analyzing the relation between energy efficiency and energy depleting rate (EDR). The algorithm maximizes link energy efficiency via power control at physical (PHY) layer and maximizes network ERR via access control at media access control (MAC) layer jointly in a cross-layer manner. The network ERR maximization algorithm performs excellently in improving both the lifetime and the number of users served by renewable energy.