Building unified conversational agents has been a long-standing goal of the dialogue research community. Most previous works only focus on a subset of various dialogue tasks. In this work, we aim to build a unified foundation model which can solve massive diverse dialogue tasks. To achieve this goal, we first collect a large-scale well-labeled dialogue dataset from 73 publicly available datasets. In addition to this dataset, we further propose two dialogue-oriented self-supervised tasks, and finally use the mixture of supervised and self-supervised datasets to train our foundation model. The supervised examples make the model learn task-specific skills, while the self-supervised examples make the model learn more general skills. We evaluate our model on various downstream dialogue tasks. The experimental results show that our method not only improves the ability of dialogue generation and knowledge distillation, but also the representation ability of models.
This paper considers a scenario in which the Terahertz (THz) transmitter equipped with a linear antenna array wishes to focus its beam to a desired spatial region in the array near-field. The goal is to compute the achievable spatial region and determine how the system parameters such as the carrier frequency, the array dimension and the user's location affect its beam focusing performance. First, based on a theorem from analytic geometry, we show that the achievable focusing spatial region constitutes a rotated ellipse, with the x and y coordinates denoting the range and angle, respectively. In this way, the determination of the spatial region is reduced to a problem of deriving the coverage of an ellipse. The achievable coverage is then obtained in closed form, and the construction of carrier frequency offsets that can analytically control the beam focusing performance is provided. Numerical results validate the theoretical findings and demonstrate the performance of the proposed method.
Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that exhibit intelligible reasoning process. Previous methods have disadvantages: either they rely on labelled support sets that incorporate human biases for objects that are "useful," or they fail to identify multiple concepts that occur within a single image. We reframe the concept discovery task as an unsupervised semantic segmentation problem, and present SegDiscover, a novel framework that discovers semantically meaningful visual concepts from imagery datasets with complex scenes without supervision. Our method contains three important pieces: generating concept primitives from raw images, discovering concepts by clustering in the latent space of a self-supervised pretrained encoder, and concept refinement via neural network smoothing. Experimental results provide evidence that our method can discover multiple concepts within a single image and outperforms state-of-the-art unsupervised methods on complex datasets such as Cityscapes and COCO-Stuff. Our method can be further used as a neural network explanation tool by comparing results obtained by different encoders.
With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU) direction. However, the current DU approaches just employ an individual model for each DU task, independently, without considering the shared knowledge across different DU tasks. In this paper, we investigate a unified generative dialogue understanding framework, namely UniDU, to achieve information exchange among DU tasks. Specifically, we reformulate the DU tasks into unified generative paradigm. In addition, to consider different training data for each task, we further introduce model-agnostic training strategy to optimize unified model in a balanced manner. We conduct the experiments on ten dialogue understanding datasets, which span five fundamental tasks: dialogue summary, dialogue completion, slot filling, intent detection and dialogue state tracking. The proposed UniDU framework outperforms task-specific well-designed methods on all 5 tasks. We further conduct comprehensive analysis experiments to study the effect factors. The experimental results also show that the proposed method obtains promising performance on unseen dialogue domain.
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR. Firstly, we propose a second order spatial compatibility (SC^2) measure to compute the similarity between correspondences. It considers the global compatibility instead of local consistency, allowing for more distinctive clustering between inliers and outliers at early stage. Based on this measure, our registration pipeline employs a global spectral technique to find some reliable seeds from the initial correspondences. Then we design a two-stage strategy to expand each seed to a consensus set based on the SC^2 measure matrix. Finally, we feed each consensus set to a weighted SVD algorithm to generate a candidate rigid transformation and select the best model as the final result. Our method can guarantee to find a certain number of outlier-free consensus sets using fewer samplings, making the model estimation more efficient and robust. In addition, the proposed SC^2 measure is general and can be easily plugged into deep learning based frameworks. Extensive experiments are carried out to investigate the performance of our method. Code will be available at \url{https://github.com/ZhiChen902/SC2-PCR}.
Reconfigurable intelligent surface (RIS) has recently emerged as a promising paradigm for future cellular networks. Specifically, due to its capability in reshaping the propagation environment, RIS was introduced to address the blockage issue in millimeter Wave (mmWave) or even Terahertz (THz) communications. The deployment of RIS, however, complicates the system architecture and poses a significant challenge for beam training (BT)/ beam alignment (BA), a process that is required to establish a reliable link between the transmitter and the receiver. In this article, we first review several state-of-the-art beam training solutions for RIS-assisted mmWave systems and discuss their respective advantages and limitations. We also present a new multi-directional BT method, which can achieve a decent BA performance with only a small amount of training overhead. Finally, we outline several important open issues in BT for RIS-assisted mmWave systems.
Generating informative scene graphs from images requires integrating and reasoning from various graph components, i.e., objects and relationships. However, current scene graph generation (SGG) methods, including the unbiased SGG methods, still struggle to predict informative relationships due to the lack of 1) high-level inference such as transitive inference between relationships and 2) efficient mechanisms that can incorporate all interactions of graph components. To address the issues mentioned above, we devise a hyper-relationship learning network, termed HLN, for SGG. Specifically, the proposed HLN stems from hypergraphs and two graph attention networks (GATs) are designed to infer relationships: 1) the object-relationship GAT or OR-GAT to explore interactions between objects and relationships, and 2) the hyper-relationship GAT or HR-GAT to integrate transitive inference of hyper-relationships, i.e., the sequential relationships between three objects for transitive reasoning. As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships. We evaluate HLN on the most popular SGG dataset, i.e., the Visual Genome dataset, and the experimental results demonstrate its great superiority over recent state-of-the-art methods. For example, the proposed HLN improves the recall per relationship from 11.3\% to 13.1\%, and maintains the recall per image from 19.8\% to 34.9\%. We will release the source code and pretrained models on GitHub.
Terahertz (THz) integrated sensing and communication (ISAC) is a promising interdisciplinary technology that realizes simultaneously transmitting Terabit-per-second (Tbps) and millimeter-level accurate environment or human activity sensing. However, both communication performance and sensing accuracy are influenced by the Doppler effects, which are especially severe in the THz band. Moreover, peak-to-average power ratio (PAPR) degrades the THz power amplifier (PA) efficiency. In this paper, a discrete Fourier transform spread orthogonal time frequency space (DFT-s-OTFS) system is proposed to improve the robustness to Doppler effects and reduce PAPR for THz ISAC. Then, a two-phase sensing parameter estimation algorithm is developed to integrate sensing functionality into the DFT-s-OTFS waveform. Meanwhile, a scheme of superimposed pilots is designed, which reduces the pilot overhead and improves the spectral efficiency. Based on the superimposed pilots, a low-complexity iterative channel estimation and data detection method is proposed to recover the data symbols of DFT-s-OTFS. The proposed DFT-s-OTFS waveform can improve the PA efficiency by 10% on average compared to OTFS. Simulation results demonstrate that the proposed two-phase sensing estimation algorithm for THz DFT-s-OTFS systems is able to realize millimeter-level range estimation accuracy and decimeter-per-second-level velocity estimation accuracy. Moreover, the effectiveness of the iterative method for data detection aided by superimposed pilots in DFT-s-OTFS systems is validated by the simulations and the bit error rate performance is not degraded by the Doppler effects.
Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet the stealthiness of such attacks is not well understood. In this paper, we investigate this phenomenon under the clean-label setting (i.e., attackers do not have complete control over the training or labeling process). Empirically, we show that existing backdoor attacks in malware classifiers are still detectable by recent defenses such as MNTD. To improve stealthiness, we propose a new attack, Jigsaw Puzzle (JP), based on the key observation that malware authors have little to no incentive to protect any other authors' malware but their own. As such, Jigsaw Puzzle learns a trigger to complement the latent patterns of the malware author's samples, and activates the backdoor only when the trigger and the latent pattern are pieced together in a sample. We further focus on realizable triggers in the problem space (e.g., software code) using bytecode gadgets broadly harvested from benign software. Our evaluation confirms that Jigsaw Puzzle is effective as a backdoor, remains stealthy against state-of-the-art defenses, and is a threat in realistic settings that depart from reasoning about feature-space only attacks. We conclude by exploring promising approaches to improve backdoor defenses.