Search

Evaluating the decision-making system is indispensable in developing autonomous vehicles, while realistic and challenging safety-critical test scenarios play a crucial role. Obtaining these scenarios is non-trivial, thanks to the long-tailed distribution, sparsity, and rarity in real-world data sets. To tackle this problem, in this paper, we introduce a natural adversarial scenario generation solution using naturalistic human driving priors and reinforcement learning techniques. By doing this, we can obtain large-scale test scenarios that are both diverse and realistic. Specifically, we build a simulation environment that mimics natural traffic interaction scenarios. Informed by this environment, we implement a two-stage procedure. The first stage incorporates conventional rule-based models, e.g., IDM~(Intelligent Driver Model) and MOBIL~(Minimizing Overall Braking Induced by Lane changes) model, to coarsely and discretely capture and calibrate key control parameters from the real-world dataset. Next, we leverage GAIL~(Generative Adversarial Imitation Learning) to represent driver behaviors continuously. The derived GAIL can be further used to design a PPO~(Proximal Policy Optimization)-based actor-critic network framework to fine-tune the reward function, and then optimizes our natural adversarial scenario generation solution. Extensive experiments have been conducted in the NGSIM dataset including the trajectory of 3,000 vehicles. Essential traffic parameters were measured in comparison with the baseline model, e.g., the collision rate, accelerations, steering, and the number of lane changes. Our findings demonstrate that the proposed model can generate realistic safety-critical test scenarios covering both naturalness and adversariality, which can be a cornerstone for the development of autonomous vehicles., Comment: Published in IEEE Transactions on Intelligent Vehicles, 2023

Metal Sintering is a necessary step for Metal Injection Molded parts and binder jet such as HP's metal 3D printer. The metal sintering process introduces large deformation varying from 25 to 50% depending on the green part porosity. In this paper, we use a graph-based deep learning approach to predict the part deformation, which can speed up the deformation simulation substantially at the voxel level. Running a well-trained Metal Sintering inferencing engine only takes a range of seconds to obtain the final sintering deformation value. The tested accuracy on example complex geometry achieves 0.7um mean deviation for a 63mm testing part.

Simulation is pivotal in evaluating the performance of autonomous driving systems due to the advantages of high efficiency and low cost compared to on-road testing. Bridging the gap between simulation and the real world requires realistic agent behaviors. However, the existing works have the following shortcomings in achieving this goal: (1) log replay offers realistic scenarios but often leads to collisions due to the absence of dynamic interactions, and (2) both heuristic-based and data-based solutions, which are parameterized and trained on real-world datasets, encourage interactions but often deviate from real-world data over long horizons. In this work, we propose LitSim, a long-term interactive simulation approach that maximizes realism by minimizing the interventions in the log. Specifically, our approach primarily uses log replay to ensure realism and intervenes only when necessary to prevent potential conflicts. We then encourage interactions among the agents and resolve the conflicts, thereby reducing the risk of unrealistic behaviors. We train and validate our model on the real-world dataset NGSIM, and the experimental results demonstrate that LitSim outperforms the currently popular approaches in terms of realism and reactivity., Comment: 9 pages, 6 figures, under review

Using machine learning (ML) techniques to predict material properties is a crucial research topic. These properties depend on numerical data and semantic factors. Due to the limitations of small-sample datasets, existing methods typically adopt ML algorithms to regress numerical properties or transfer other pre-trained knowledge graphs (KGs) to the material. However, these methods cannot simultaneously handle semantic and numerical information. In this paper, we propose a numerical reasoning method for material KGs (NR-KG), which constructs a cross-modal KG using semantic nodes and numerical proxy nodes. It captures both types of information by projecting KG into a canonical KG and utilizes a graph neural network to predict material properties. In this process, a novel projection prediction loss is proposed to extract semantic features from numerical information. NR-KG facilitates end-to-end processing of cross-modal data, mining relationships and cross-modal information in small-sample datasets, and fully utilizes valuable experimental data to enhance material prediction. We further propose two new High-Entropy Alloys (HEA) property datasets with semantic descriptions. NR-KG outperforms state-of-the-art (SOTA) methods, achieving relative improvements of 25.9% and 16.1% on two material datasets. Besides, NR-KG surpasses SOTA methods on two public physical chemistry molecular datasets, showing improvements of 22.2% and 54.3%, highlighting its potential application and generalizability. We hope the proposed datasets, algorithms, and pre-trained models can facilitate the communities of KG and AI for materials.

Automated driving vehicles~(ADV) promise to enhance driving efficiency and safety, yet they face intricate challenges in safety-critical scenarios. As a result, validating ADV within generated safety-critical scenarios is essential for both development and performance evaluations. This paper investigates the complexities of employing two major scenario-generation solutions: data-driven and knowledge-driven methods. Data-driven methods derive scenarios from recorded datasets, efficiently generating scenarios by altering the existing behavior or trajectories of traffic participants but often falling short in considering ADV perception; knowledge-driven methods provide effective coverage through expert-designed rules, but they may lead to inefficiency in generating safety-critical scenarios within that coverage. To overcome these challenges, we introduce BridgeGen, a safety-critical scenario generation framework, designed to bridge the benefits of both methodologies. Specifically, by utilizing ontology-based techniques, BridgeGen models the five scenario layers in the operational design domain (ODD) from knowledge-driven methods, ensuring broad coverage, and incorporating data-driven strategies to efficiently generate safety-critical scenarios. An optimized scenario generation toolkit is developed within BridgeGen. This expedites the crafting of safety-critical scenarios through a combination of traditional optimization and reinforcement learning schemes. Extensive experiments conducted using Carla simulator demonstrate the effectiveness of BridgeGen in generating diverse safety-critical scenarios.

Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data efficiency hinders their practical applications. In this work, we propose LayoutPrompter, which leverages large language models (LLMs) to address the above problems through in-context learning. LayoutPrompter is made up of three key components, namely input-output serialization, dynamic exemplar selection and layout ranking. Specifically, the input-output serialization component meticulously designs the input and output formats for each layout generation task. Dynamic exemplar selection is responsible for selecting the most helpful prompting exemplars for a given input. And a layout ranker is used to pick the highest quality layout from multiple outputs of LLMs. We conduct experiments on all existing layout generation tasks using four public datasets. Despite the simplicity of our approach, experimental results show that LayoutPrompter can compete with or even outperform state-of-the-art approaches on these tasks without any model training or fine-tuning. This demonstrates the effectiveness of this versatile and training-free approach. In addition, the ablation studies show that LayoutPrompter is significantly superior to the training-based baseline in a low-data regime, further indicating the data efficiency of LayoutPrompter. Our project is available at https://github.com/microsoft/LayoutGeneration/tree/main/LayoutPrompter., Comment: NeurIPS 2023

Vehicular crowd intelligence (VCI) is an emerging research field. Facilitated by state-of-the-art vehicular ad-hoc networks and artificial intelligence, various VCI applications come to place, e.g., collaborative sensing, positioning, and mapping. The collaborative property of VCI applications generally requires data to be shared among participants, thus forming network-wide intelligence. How to fulfill this process without compromising data privacy remains a challenging issue. Although federated learning (FL) is a promising tool to solve the problem, adapting conventional FL frameworks to VCI is nontrivial. First, the centralized model aggregation is unreliable in VCI because of the existence of stragglers with unfavorable channel conditions. Second, existing FL schemes are vulnerable to Non-IID data, which is intensified by the data heterogeneity in VCI. This paper proposes a novel federated learning framework called RaftFed to facilitate privacy-preserving VCI. The experimental results show that RaftFed performs better than baselines regarding communication overhead, model accuracy, and model convergence., Comment: 8 pages,8 figures

3D style transfer aims to render stylized novel views of 3D scenes with the specified style, which requires high-quality rendering and keeping multi-view consistency. Benefiting from the ability of 3D representation from Neural Radiance Field (NeRF), existing methods learn the stylized NeRF by giving a reference style from an image. However, they suffer the challenges of high-quality stylization with texture details for multi-style transfer and stylization with multimodal guidance. In this paper, we reveal that the same objects in 3D scenes show various states (color tone, details, etc.) from different views after stylization since previous methods optimized by single-view image-based style loss functions, leading NeRF to tend to smooth texture details, further resulting in low-quality rendering. To tackle these problems, we propose a novel Multimodal-guided 3D Multi-style transfer of NeRF, termed MM-NeRF, which achieves high-quality 3D multi-style rendering with texture details and can be driven by multimodal-style guidance. First, MM-NeRF adopts a unified framework to project multimodal guidance into CLIP space and extracts multimodal style features to guide the multi-style stylization. To relieve the problem of lacking details, we propose a novel Multi-Head Learning Scheme (MLS), in which each style head predicts the parameters of the color head of NeRF. MLS decomposes the learning difficulty caused by the inconsistency of multi-style transfer and improves the quality of stylization. In addition, the MLS can generalize pre-trained MM-NeRF to any new styles by adding heads with small training costs (a few minutes). Extensive experiments on three real-world 3D scene datasets show that MM-NeRF achieves high-quality 3D multi-style stylization with multimodal guidance, keeps multi-view consistency, and keeps semantic consistency of multimodal style guidance. Codes will be released later.

Since DARPA started Grand Challenges in 2004 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. This paper gives an overview about technical aspects of autonomous driving technologies and open problems. We investigate the major fields of self-driving systems, such as perception, mapping and localization, prediction, planning and control, simulation, V2X and safety etc. Especially we elaborate on all these issues in a framework of data closed loop, a popular platform to solve the long tailed autonomous driving problems.

Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability to produce high-quality synthesized neural speech in neural speech synthesis systems. In SGMs, the U-Net architecture and its variants have long dominated as the backbone since its first successful adoption. In this research, we mainly focus on the neural network in diffusion-model-based Text-to-Speech (TTS) systems and propose the U-DiT architecture, exploring the potential of vision transformer architecture as the core component of the diffusion models in a TTS system. The modular design of the U-DiT architecture, inherited from the best parts of U-Net and ViT, allows for great scalability and versatility across different data scales. The proposed U-DiT TTS system is a mel spectrogram-based acoustic model and utilizes a pretrained HiFi-GAN as the vocoder. The objective (ie Frechet distance) and MOS results show that our DiT-TTS system achieves state-of-art performance on the single speaker dataset LJSpeech. Our demos are publicly available at: https://eihw.github.io/u-dit-tts/

Recent years have seen a rapid increase in digital medicine research in an attempt to transform traditional healthcare systems to their modern, intelligent, and versatile equivalents that are adequately equipped to tackle contemporary challenges. This has led to a wave of applications that utilise AI technologies; first and foremost in the fields of medical imaging, but also in the use of wearables and other intelligent sensors. In comparison, computer audition can be seen to be lagging behind, at least in terms of commercial interest. Yet, audition has long been a staple assistant for medical practitioners, with the stethoscope being the quintessential sign of doctors around the world. Transforming this traditional technology with the use of AI entails a set of unique challenges. We categorise the advances needed in four key pillars: Hear, corresponding to the cornerstone technologies needed to analyse auditory signals in real-life conditions; Earlier, for the advances needed in computational and data efficiency; Attentively, for accounting to individual differences and handling the longitudinal nature of medical data; and, finally, Responsibly, for ensuring compliance to the ethical standards accorded to the field of medicine.

Modeling dynamics in the form of partial differential equations (PDEs) is an effectual way to understand real-world physics processes. For complex physics systems, analytical solutions are not available and numerical solutions are widely-used. However, traditional numerical algorithms are computationally expensive and challenging in handling multiphysics systems. Recently, using neural networks to solve PDEs has made significant progress, called physics-informed neural networks (PINNs). PINNs encode physical laws into neural networks and learn the continuous solutions of PDEs. For the training of PINNs, existing methods suffer from the problems of inefficiency and unstable convergence, since the PDE residuals require calculating automatic differentiation. In this paper, we propose Dynamic Mesh-based Importance Sampling (DMIS) to tackle these problems. DMIS is a novel sampling scheme based on importance sampling, which constructs a dynamic triangular mesh to estimate sample weights efficiently. DMIS has broad applicability and can be easily integrated into existing methods. The evaluation of DMIS on three widely-used benchmarks shows that DMIS improves the convergence speed and accuracy in the meantime. Especially in solving the highly nonlinear Schr\"odinger Equation, compared with state-of-the-art methods, DMIS shows up to 46% smaller root mean square error and five times faster convergence speed. Code are available at https://github.com/MatrixBrain/DMIS., Comment: Accepted to AAAl-23

Clone detection is widely exploited for software vulnerability search. The approaches based on source code analysis cannot be applied to binary clone detection because the same source code can produce significantly different binaries. In this paper, we present BinSeeker, a cross-platform binary seeker that integrates semantic learning and emulation. With the help of the labeled semantic flow graph, BinSeeker can quickly identify M candidate functions that are most similar to the vulnerability from the target binary. The value of M is relatively large so this semantic learning procedure essentially eliminates those functions that are very unlikely to have the vulnerability. Then, semantic emulation is conducted on these M candidates to obtain their dynamic signature sequences. By comparing signature sequences, BinSeeker produces top-N functions that exhibit most similar behavior to that of the vulnerability. With fast filtering of semantic learning and accurate comparison of semantic emulation, BinSeeker seeks vulnerability precisely with little overhead. The experiments on six widely used programs with fifteen known CVE vulnerabilities demonstrate that BinSeeker outperforms three state-of-the-art tools Genius, Gemini and CACompare. Regarding search accuracy, BinSeeker achieves an MRR value of 0.65 in the target programs, whereas the MRR values by Genius, Gemini and CACompare are 0.17, 0.07 and 0.42, respectively. If we consider ranking a function with the targeted vulnerability in the top-5 as accurate, BinSeeker achieves the accuracy of 93.33 percent, while the accuracy of the other three tools is merely 33.33, 13.33 and 53.33 percent, respectively. Such accuracy is achieved with 0.27s on average to determine whether the target binary function contains a known vulnerability, and the time for the other three tools are 1.57s, 0.15s and 0.98s, respectively., Comment: This paper appeared in IEEE Transactions on Software Engineering

Speech is the fundamental mode of human communication, and its synthesis has long been a core priority in human-computer interaction research. In recent years, machines have managed to master the art of generating speech that is understandable by humans. But the linguistic content of an utterance encompasses only a part of its meaning. Affect, or expressivity, has the capacity to turn speech into a medium capable of conveying intimate thoughts, feelings, and emotions -- aspects that are essential for engaging and naturalistic interpersonal communication. While the goal of imparting expressivity to synthesised utterances has so far remained elusive, following recent advances in text-to-speech synthesis, a paradigm shift is well under way in the fields of affective speech synthesis and conversion as well. Deep learning, as the technology which underlies most of the recent advances in artificial intelligence, is spearheading these efforts. In the present overview, we outline ongoing trends and summarise state-of-the-art approaches in an attempt to provide a comprehensive overview of this exciting field., Comment: Submitted to the Proceedings of IEEE

Autonomous driving systems (ADSs) must be tested thoroughly before they can be deployed in autonomous vehicles. High-fidelity simulators allow them to be tested against diverse scenarios, including those that are difficult to recreate in real-world testing grounds. While previous approaches have shown that test cases can be generated automatically, they tend to focus on weak oracles (e.g. reaching the destination without collisions) without assessing whether the journey itself was undertaken safely and satisfied the law. In this work, we propose LawBreaker, an automated framework for testing ADSs against real-world traffic laws, which is designed to be compatible with different scenario description languages. LawBreaker provides a rich driver-oriented specification language for describing traffic laws, and a fuzzing engine that searches for different ways of violating them by maximising specification coverage. To evaluate our approach, we implemented it for Apollo+LGSVL and specified the traffic laws of China. LawBreaker was able to find 14 violations of these laws, including 173 test cases that caused accidents., Comment: Accepted by the 37th IEEE/ACM International Conference on Automated Software Engineering (ASE 2022)

Conditional graphic layout generation, which generates realistic layouts according to user constraints, is a challenging task that has not been well-studied yet. First, there is limited discussion about how to handle diverse user constraints flexibly and uniformly. Second, to make the layouts conform to user constraints, existing work often sacrifices generation quality significantly. In this work, we propose LayoutFormer++ to tackle the above problems. First, to flexibly handle diverse constraints, we propose a constraint serialization scheme, which represents different user constraints as sequences of tokens with a predefined format. Then, we formulate conditional layout generation as a sequence-to-sequence transformation, and leverage encoder-decoder framework with Transformer as the basic architecture. Furthermore, to make the layout better meet user requirements without harming quality, we propose a decoding space restriction strategy. Specifically, we prune the predicted distribution by ignoring the options that definitely violate user constraints and likely result in low-quality layouts, and make the model samples from the restricted distribution. Experiments demonstrate that LayoutFormer++ outperforms existing approaches on all the tasks in terms of both better generation quality and less constraint violation., Comment: Accepted by CVPR2023

We propose a novel Dynamic Restrained Uncertainty Weighting Loss to experimentally handle the problem of balancing the contributions of multiple tasks on the ICML ExVo 2022 Challenge. The multitask aims to recognize expressed emotions and demographic traits from vocal bursts jointly. Our strategy combines the advantages of Uncertainty Weight and Dynamic Weight Average, by extending weights with a restraint term to make the learning process more explainable. We use a lightweight multi-exit CNN architecture to implement our proposed loss approach. The experimental H-Mean score (0.394) shows a substantial improvement over the baseline H-Mean score (0.335)., Comment: 5 pages

In this paper, we propose the Redundancy Reduction Twins Network (RRTN), a redundancy reduction training framework that minimizes redundancy by measuring the cross-correlation matrix between the outputs of the same network fed with distorted versions of a sample and bringing it as close to the identity matrix as possible. RRTN also applies a new loss function, the Barlow Twins loss function, to help maximize the similarity of representations obtained from different distorted versions of a sample. However, as the distribution of losses can cause performance fluctuations in the network, we also propose the use of a Restrained Uncertainty Weight Loss (RUWL) or joint training to identify the best weights for the loss function. Our best approach on CNN14 with the proposed methodology obtains a CCC over emotion regression of 0.678 on the ExVo Multi-task dev set, a 4.8% increase over a vanilla CNN 14 CCC of 0.647, which achieves a significant difference at the 95% confidence interval (2-tailed)., Comment: 5 pages, accepted by ICML Exvo workshop

In this work, we explore a novel few-shot personalisation architecture for emotional vocalisation prediction. The core contribution is an `enrolment' encoder which utilises two unlabelled samples of the target speaker to adjust the output of the emotion encoder; the adjustment is based on dot-product attention, thus effectively functioning as a form of `soft' feature selection. The emotion and enrolment encoders are based on two standard audio architectures: CNN14 and CNN10. The two encoders are further guided to forget or learn auxiliary emotion and/or speaker information. Our best approach achieves a CCC of $.650$ on the ExVo Few-Shot dev set, a $2.5\%$ increase over our baseline CNN14 CCC of $.634$., Comment: Proceedings of the ICML Expressive Vocalizations Workshop and Competition held in conjunction with the $\mathit{39}^{th}$ International Conference on Machine Learning, Copyright 2022 by the author(s)

The fairness characteristic is a critical attribute of trusted AI systems. A plethora of research has proposed diverse methods for individual fairness testing. However, they are suffering from three major limitations, i.e., low efficiency, low effectiveness, and model-specificity. This work proposes ExpGA, an explanationguided fairness testing approach through a genetic algorithm (GA). ExpGA employs the explanation results generated by interpretable methods to collect high-quality initial seeds, which are prone to derive discriminatory samples by slightly modifying feature values. ExpGA then adopts GA to search discriminatory sample candidates by optimizing a fitness value. Benefiting from this combination of explanation results and GA, ExpGA is both efficient and effective to detect discriminatory individuals. Moreover, ExpGA only requires prediction probabilities of the tested model, resulting in a better generalization capability to various models. Experiments on multiple real-world benchmarks, including tabular and text datasets, show that ExpGA presents higher efficiency and effectiveness than four state-of-the-art approaches.

Detecting COVID-19 from audio signals, such as breathing and coughing, can be used as a fast and efficient pre-testing method to reduce the virus transmission. Due to the promising results of deep learning networks in modelling time sequences, and since applications to rapidly identify COVID in-the-wild should require low computational effort, we present a temporal-oriented broadcasting residual learning method that achieves efficient computation and high accuracy with a small model size. Based on the EfficientNet architecture, our novel network, named Temporal-oriented ResNet~(TorNet), constitutes of a broadcasting learning block, i.e. the Alternating Broadcast (AB) Block, which contains several Broadcast Residual Blocks (BC ResBlocks) and a convolution layer. With the AB Block, the network obtains useful audio-temporal features and higher level embeddings effectively with much less computation than Recurrent Neural Networks~(RNNs), typically used to model temporal information. TorNet achieves 72.2% Unweighted Average Recall (UAR) on the INTERPSEECH 2021 Computational Paralinguistics Challenge COVID-19 cough Sub-Challenge, by this showing competitive results with a higher computational efficiency than other state-of-the-art alternatives., Comment: 5 pages,submitted to Intesspeech 2022

Emotional voice conversion (EVC) focuses on converting a speech utterance from a source to a target emotion; it can thus be a key enabling technology for human-computer interaction applications and beyond. However, EVC remains an unsolved research problem with several challenges. In particular, as speech rate and rhythm are two key factors of emotional conversion, models have to generate output sequences of differing length. Sequence-to-sequence modelling is recently emerging as a competitive paradigm for models that can overcome those challenges. In an attempt to stimulate further research in this promising new direction, recent sequence-to-sequence EVC papers were systematically investigated and reviewed from six perspectives: their motivation, training strategies, model architectures, datasets, model inputs, and evaluation methods. This information is organised to provide the research community with an easily digestible overview of the current state-of-the-art. Finally, we discuss existing challenges of sequence-to-sequence EVC., Comment: Submitted to INTERSPEECH 2022