arXiv subjects

Peng Xu

Publications and source records attributed to Peng Xu.

At least 253 records · Page 14Linked to original sources

arXiv2023

Unsupervised noise reductions for gravitational reference sensors or accelerometers based on Noise2Noise method

Onboard electrostatic suspension inertial sensors are important applications for gravity satellites and space gravitational wave detection missions, and it is important to suppress noise in the measurement signal. Due to the complex coupling between the working space environment and the satellite platform, the process of noise generation is extremely complex, and traditional noise modeling and subtraction methods have certain limitations. With the development of deep learning, applying it to high-precision inertial sensors to improve the signal-to-noise ratio is a practically meaningful task. Since there is a single noise sample and unknown true value in the measured data in orbit, odd-even sub-samplers and periodic sub-samplers are designed to process general signals and periodic signals, and adds reconstruction layers consisting of fully connected layers to the model. Experimental analysis and comparison are conducted based on simulation data, GRACE-FO acceleration data and Taiji-1 acceleration data. The results show that the deep learning method is superior to traditional data smoothing processing sol

physics.geo-ph↗

arXiv2023

Multimodal Learning with Transformers: A Survey

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.

cs.CV↗

arXiv2023

Context Generation Improves Open Domain Question Answering

Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge. However, they do not fully exploit the parameterized knowledge. To address this issue, we propose a two-stage, closed-book QA framework which employs a coarse-to-fine approach to extract relevant knowledge and answer a question. Our approach first generates a related context for a given question by prompting a pretrained LM. We then prompt the same LM for answer prediction using the generated context and the question. Additionally, to eliminate failure caused by context uncertainty, we marginalize over generated contexts. Experimental results on three QA benchmarks show that our method significantly outperforms previous closed-book QA methods (e.g. exact matching 68.6% vs. 55.3%), and is on par with open-book methods that exploit external knowledge sources (e.g. 68.6% vs. 68.0%). Our method is able to better exploit the stored knowledge in pretrained LMs without adding extra learnable parameters or needing finetuning, and paves the way for hybrid models that integrate pretrained LMs with external knowledge.

cs.CL↗

arXiv2023

High speed free-space optical communication using standard fiber communication component without optical amplification

Free-space optical communication (FSO) can achieve fast, secure and license-free communication without need for physical cables, making it a cost-effective, energy-efficient and flexible solution when the fiber connection is unavailable. To establish FSO connection on-demand, it is essential to build portable FSO devices with compact structure and light weight. Here, we develop a miniaturized FSO system and realize 9.16 Gbps FSO between two nodes that is 1 km apart, using a commercial single-mode-fiber-coupled optical transceiver module without optical amplification. Using our 4-stage acquisition, pointing and tracking (APT) systems, the tracking error is within 3 μrad and results an average link loss of 13.7 dB, which is the key for this high-bandwidth FSO demonstration without optical amplification. Our FSO link has been tested up to 4 km, with link loss of 18 dB that is limited by the foggy weather during the test. Longer FSO distances can be expected with better weather condition and optical amplification. With single FSO device weight of only 9.5 kg, this result arouses massive applications of field-deployable high-speed wireless communication.

eess.SP↗

arXiv2023

Deep Image Feature Learning with Fuzzy Rules

The methods of extracting image features are the key to many image processing tasks. At present, the most popular method is the deep neural network which can automatically extract robust features through end-to-end training instead of hand-crafted feature extraction. However, the deep neural network currently faces many challenges: 1) its effectiveness is heavily dependent on large datasets, so the computational complexity is very high; 2) it is usually regarded as a black box model with poor interpretability. To meet the above challenges, a more interpretable and scalable feature learning method, i.e., deep image feature learning with fuzzy rules (DIFL-FR), is proposed in the paper, which combines the rule-based fuzzy modeling technique and the deep stacked learning strategy. The method progressively learns image features through a layer-by-layer manner based on fuzzy rules, so the feature learning process can be better explained by the generated rules. More importantly, the learning process of the method is only based on forward propagation without back propagation and iterative learning, which results in the high learning efficiency. In addition, the method is under the settings of unsupervised learning and can be easily extended to scenes of supervised and semi-supervised learning. Extensive experiments are conducted on image datasets of different scales. The results obviously show the effectiveness of the proposed method.

cs.CV↗

arXiv2023

Advanced Analytics on 3D X-ray Tomography of Irradiated Silicon Carbide Claddings

Silicon Carbide (SiC) ceramic matrix composite (CMC) cladding is currently being pursued as one of the leading candidates for accident-tolerant fuels. To enable an improved understanding of SiC-SiC composite performance, the development of non-destructive evaluation techniques to assess critical defects is needed. Three-dimensional (3D) X-ray imaging, also referred to as X-ray computed tomography (CT), is a non-destructive, data-rich characterization technique that can provide surface and subsurface spatial information. This paper discusses the design and implementation of a fully automatic workflow to detect and analyze SiC-SiC defects using image processing techniques on 3D X-ray images. The workflow consists of four processing blocks, including data preparation, void/crack detection, visualization, and analysis. In this work, three SiC samples (two irradiated and one unirradiated) provided by General Atomics are investigated. The irradiated samples were exposed in a way that was expected to induce cracking, and indeed, the automated workflow developed in this work was able to successfully identify and characterize the crack formation in the irradiated samples while detecting no observed cracking in the unirradiated sample. These results demonstrate the value of automated XCT tools to better understand the damage and damage propagation in SiC-SiC structures for nuclear applications.

physics.app-ph↗

arXiv2023

Factuality Enhanced Language Models for Open-Ended Text Generation

Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test set and metrics to measure the factuality of LM generations. Based on that, we study the factual accuracy of LMs with parameter sizes ranging from 126M to 530B. Interestingly, we find that larger LMs are more factual than smaller ones, although a previous study suggests that larger LMs can be less truthful in terms of misconceptions. In addition, popular sampling algorithms (e.g., top-p) in open-ended text generation can harm the factuality due to the ''uniform randomness'' introduced at every sampling step. We propose the factual-nucleus sampling algorithm that dynamically adapts the randomness to improve the factuality of generation while maintaining quality. Furthermore, we analyze the inefficiencies of the standard training method in learning correct associations between entities from factual text corpus (e.g., Wikipedia). We propose a factuality-enhanced training method that uses TopicPrefix for better awareness of facts and sentence completion as the training objective, which can vastly reduce the factual errors. We release our code and FactualityPrompts benchmark at: https://github.com/nayeon7lee/FactualityPrompt.

cs.CL↗

arXiv2023

High Recovery with Fewer Injections: Practical Binary Volumetric Injection Attacks against Dynamic Searchable Encryption

Searchable symmetric encryption enables private queries over an encrypted database, but it also yields information leakages. Adversaries can exploit these leakages to launch injection attacks (Zhang et al., USENIX'16) to recover the underlying keywords from queries. The performance of the existing injection attacks is strongly dependent on the amount of leaked information or injection. In this work, we propose two new injection attacks, namely BVA and BVMA, by leveraging a binary volumetric approach. We enable adversaries to inject fewer files than the existing volumetric attacks by using the known keywords and reveal the queries by observing the volume of the query results. Our attacks can thwart well-studied defenses (e.g., threshold countermeasure, static padding) without exploiting the distribution of target queries and client databases. We evaluate the proposed attacks empirically in real-world datasets with practical queries. The results show that our attacks can obtain a high recovery rate (>80%) in the best case and a roughly 60% recovery even under a large-scale dataset with a small number of injections (<20 files).

cs.CR↗

arXiv2022

VG-Swarm: A Vision-based Gene Regulation Network for UAVs Swarm Behavior Emergence

Unmanned Aerial Vehicles (UAVs) dynamic encirclement is an emerging field with great potential. Researchers often get inspiration from biological systems, either from macro-world like fish schools or bird flocks etc, or from micro-world like gene regulatory networks (GRN). However, most swarm control algorithms rely on centralized control, global information acquisition, and communications among neighboring agents. In this work, we propose a distributed swarm control method based purely on vision and GRN without any direct communications, in which swarm agents of e.g. UAVs can generate an entrapping pattern to encircle an escaping target of UAV based purely on their installed omnidirectional vision sensors. A finite-state-machine (FSM) describing the behavioral model of each drone is also designed so that a swarm of drones can accomplish searching and entrapping of the target collectively in an integrated way. We verify the effectiveness and efficiency of the proposed method in various simulation and real-world experiments.

cs.RO↗

arXiv2022

Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms

We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms. Meta relies on both handcrafted and learned risk models to flag potentially violating content for human review. Our approach aggregates these risk models into a single ranking score, calibrating them to prioritize more reliable risk models. A key challenge is that violation trends change over time, affecting which risk models are most reliable. Our system additionally handles production challenges such as changing risk models and novel risk models. We use a contextual bandit to update the calibration in response to such trends. Our approach increases Meta's top-line metric for measuring the effectiveness of its content moderation strategy by 13%.

cs.LG↗

arXiv2022

Topologically protected boundary discrete time crystal for a solvable model

Floquet time crystal, which breaks discrete time-translation symmetry, is an intriguing phenomenon in non-equilibrium systems. It is crucial to understand the rigidity and robustness of discrete time crystal (DTC) phases in a many-body system, and finding a precisely solvable model can pave a way for understanding of the DTC phase. Here, we propose and study a solvable spin chain model by mapping it to a Floquet superconductor through the Jordan-Wigner transformation. The phase diagrams of Floquet topological systems are characterized by topological invariants and tell the existence of anomalous edge states. The sub-harmonic oscillation, which is the typical signal of the DTC, can be generated from such edge states and protected by topology. We also examine the robustness of the DTC by adding symmetry-preserving and symmetry-breaking perturbations. Our results on topologically protected DTC can provide a deep understanding of the DTC when generalized to other interacting or dissipative systems.

cond-mat.quant-gas↗

arXiv2022

Evaluating Parameter Efficient Learning for Generation

Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downstream task. However, these conclusions are mostly drawn from in-domain evaluations over the full training set. In this paper, we present comparisons between PERMs and finetuning from three new perspectives: (1) the effect of sample and model size to in-domain evaluations, (2) generalization to unseen domains and new datasets, and (3) the faithfulness of generations. Our results show that for in-domain settings (a) there is a cross point of sample size for which PERMs will perform better than finetuning when training with fewer samples, and (b) larger PLMs have larger cross points. For cross-domain and cross-dataset cases, we show that (a) Adapter (Houlsby et al., 2019) performs the best amongst all the PERMs studied here, and (b) it outperforms finetuning if the task dataset is below a certain size. We also compare the faithfulness of generations and show that PERMs can achieve better faithfulness score than finetuning, especially for small training set, by as much as 6%. Finally, we apply Adapter to MT-NLG 530b (Smith et al., 2022) and achieve new state-of-the-art results on Xsum (Narayan et al., 2018) for all ROUGE scores (ROUGE-1 49.17, ROUGE-2 27.20, ROUGE-L 40.98).

cs.CL↗

arXiv2022

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training corpus, model size, and parameter efficiency. For the training corpus, we propose to leverage the generative power of LMs and generate nontoxic datasets for domain-adaptive training, which mitigates the exposure bias and is shown to be more data-efficient than using a curated pre-training corpus. We demonstrate that the self-generation method consistently outperforms the existing baselines across various model sizes on both automatic and human evaluations, even when it uses a 1/3 smaller training corpus. We then comprehensively study detoxifying LMs with parameter sizes ranging from 126M up to 530B (3x larger than GPT-3), a scale that has never been studied before. We find that i) large LMs have similar toxicity levels as smaller ones given the same pre-training corpus, and ii) large LMs require more endeavor to detoxify. We also explore parameter-efficient training methods for detoxification. We demonstrate that adding and training adapter-only layers in LMs not only saves a lot of parameters but also achieves a better trade-off between toxicity and perplexity than whole model adaptation for the large-scale models.

cs.CL↗

arXiv2022

Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

We propose a framework to enable multipurpose assistive mobile robots to autonomously wipe tables to clean spills and crumbs. This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations. Simultaneously, we must guarantee constraints satisfaction to enable safe deployment in unstructured cluttered environments. To tackle this problem, we first propose a stochastic differential equation to model crumbs and spill dynamics and absorption with a robot wiper. Using this model, we train a vision-based policy for planning wiping actions in simulation using reinforcement learning (RL). To enable zero-shot sim-to-real deployment, we dovetail the RL policy with a whole-body trajectory optimization framework to compute base and arm joint trajectories that execute the desired wiping motions while guaranteeing constraints satisfaction. We extensively validate our approach in simulation and on hardware. Video: https://youtu.be/inORKP4F3EI

cs.RO↗

arXiv2022

RoleSeer: Understanding Informal Social Role Changes in MMORPGs via Visual Analytics

Massively multiplayer online role-playing games create virtual communities that support heterogeneous "social roles" determined by gameplay interaction behaviors under a specific social context. For all social roles, formal roles are pre-defined, obvious, and explicitly ascribed to the people holding the roles, whereas informal roles are not well-defined and unspoken. Identifying the informal roles and understanding their subtle changes are critical to designing sociability mechanisms. However, it is nontrivial to understand the existence and evolution of such roles due to their loosely defined, interconvertible, and dynamic characteristics. We propose a visual analytics system, RoleSeer, to investigate informal roles from the perspectives of behavioral interactions and depict their dynamic interconversions and transitions. Two cases, experts' feedback, and a user study suggest that RoleSeer helps interpret the identified informal roles and explore the patterns behind role changes. We see our approach's potential in investigating informal roles in a broader range of social games.

cs.HC↗

arXiv2022

A Transformer-based deep neural network model for SSVEP classification

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signal in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data become urgent. In recent years, developing the methods that can work in inter-subject classification scenario has become a promising new direction. As the popular deep learning model nowadays, Transformer has excellent performance and has been used in EEG signal classification tasks. Therefore, in this study, we propose a deep learning model for SSVEP classification based on Transformer structure in inter-subject classification scenario, termed as SSVEPformer, which is the first application of the transformer to the classification of SSVEP. Inspired by previous studies, the model adopts the frequency spectrum of SSVEP data as input, and explores the spectral and spatial domain information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) is proposed to further improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12-class task; Dataset 2: 35 subjects, 40-class task) in the inter-subject classification scenario. The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate, compared with other baseline methods. The proposed model validates the feasibility of deep learning models based on Transformer structure for SSVEP classification task, and could serve as a potential model to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

q-bio.NC↗

arXiv2022

Conformal Navigation Transformations with Application to Robot Navigation in Complex Workspaces

Navigation functions provide both path and motion planning, which can be used to ensure obstacle avoidance and convergence in the sphere world. When dealing with complex and realistic scenarios, constructing a transformation to the sphere world is essential and, at the same time, challenging. This work proposes a novel transformation termed the conformal navigation transformation to achieve collision-free navigation of a robot in a workspace populated with obstacles of arbitrary shapes. The properties of the conformal navigation transformation, including uniqueness, invariance of navigation properties, and no angular deformation, are investigated, which contribute to the solution of the robot navigation problem in complex environments. Based on navigation functions and the proposed transformation, feedback controllers are derived for the automatic guidance and motion control of kinematic and dynamic mobile robots. Moreover, an iterative method is proposed to construct the conformal navigation transformation in a multiply-connected workspace, which transforms the multiply-connected problem into multiple simply-connected problems to achieve fast convergence. In addition to the analytic guarantees, simulation studies verify the effectiveness of the proposed methodology in workspaces with non-trivial obstacles.

cs.RO↗

arXiv2022

Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation

Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e.g., in cluttered home environments or in human-occupied public spaces. To address this, we present a new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC). Our approach, called Performer-MPC, uses a learned cost function parameterized by vision context embeddings provided by Performers -- a low-rank implicit-attention Transformer. We jointly train the cost function and construct the controller relying on it, effectively solving end-to-end the corresponding bi-level optimization problem. We show that the resulting policy improves standard MPC performance by leveraging a few expert demonstrations of the desired navigation behavior in different challenging real-world scenarios. Compared with a standard MPC policy, Performer-MPC achieves >40% better goal reached in cluttered environments and >65% better on social metrics when navigating around humans.

cs.RO↗