arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 595 records · Page 33Linked to original sources

arXiv2023

ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries

Perception and prediction are two separate modules in the existing autonomous driving systems. They interact with each other via hand-picked features such as agent bounding boxes and trajectories. Due to this separation, prediction, as a downstream module, only receives limited information from the perception module. To make matters worse, errors from the perception modules can propagate and accumulate, adversely affecting the prediction results. In this work, we propose ViP3D, a query-based visual trajectory prediction pipeline that exploits rich information from raw videos to directly predict future trajectories of agents in a scene. ViP3D employs sparse agent queries to detect, track, and predict throughout the pipeline, making it the first fully differentiable vision-based trajectory prediction approach. Instead of using historical feature maps and trajectories, useful information from previous timestamps is encoded in agent queries, which makes ViP3D a concise streaming prediction method. Furthermore, extensive experimental results on the nuScenes dataset show the strong vision-based prediction performance of ViP3D over traditional pipelines and previous end-to-end models.

cs.CV↗

arXiv2023

Neural Map Prior for Autonomous Driving

High-definition (HD) semantic maps are crucial in enabling autonomous vehicles to navigate urban environments. The traditional method of creating offline HD maps involves labor-intensive manual annotation processes, which are not only costly but also insufficient for timely updates. Recent studies have proposed an alternative approach that generates local maps using online sensor observations. However, this approach is limited by the sensor's perception range and its susceptibility to occlusions. In this study, we propose Neural Map Prior (NMP), a neural representation of global maps. This representation automatically updates itself and improves the performance of local map inference. Specifically, we utilize two approaches to achieve this. Firstly, to integrate a strong map prior into local map inference, we apply cross-attention, a mechanism that dynamically identifies correlations between current and prior features. Secondly, to update the global neural map prior, we utilize a learning-based fusion module that guides the network in fusing features from previous traversals. Our experimental results, based on the nuScenes dataset, demonstrate that our framework is highly compatible with various map segmentation and detection architectures. It significantly improves map prediction performance, even in challenging weather conditions and situations with a longer perception range. To the best of our knowledge, this is the first learning-based system for creating a global map prior.

cs.CV↗

arXiv2023

Inactivated COVID-19 Vaccination did not affect In vitro fertilization (IVF) / Intra-Cytoplasmic Sperm Injection (ICSI) cycle outcomes

Background: The objective of this study is to evaluate the impact of COVID-19 inactivated vaccine administration on the outcomes of in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) cycles in infertile couples in China. Methods: We collected data from the CYART prospective cohort, which included couples undergoing IVF treatment from January 2021 to September 2022 at Sichuan Jinxin Xinan Women & Children's Hospital. Based on whether they received vaccination before ovarian stimulation, the couples were divided into the vaccination group and the non-vaccination group. We compared the laboratory parameters and pregnancy outcomes between the two groups. Findings: After performing propensity score matching (PSM), the analysis demonstrated similar clinical pregnancy rates, biochemical pregnancy and ongoing pregnancy rates between vaccinated and unvaccinated women. No significant disparities were found in terms of embryo development and laboratory parameters among the groups. Moreover, male vaccination had no impact on patient performance or pregnancy outcomes in assisted reproductive technology treatments. Additionally, there were no significant differences observed in the effects of vaccination on embryo development and pregnancy outcomes among couples undergoing ART. Interpretation: The findings suggest that COVID-19 vaccination did not have a significant effect on patients undergoing IVF/ICSI with fresh embryo transfer. Therefore, it is recommended that couples should receive COVID-19 vaccination as scheduled to help mitigate the COVID-19 pandemic.

stat.AP↗

arXiv2023

Privately generating tabular data using language models

Privately generating synthetic data from a table is an important brick of a privacy-first world. We propose and investigate a simple approach of treating each row in a table as a sentence and training a language model with differential privacy. We show this approach obtains competitive results in modelling tabular data across multiple datasets, even at small scales that favor alternative methods based on marginal distributions.

cs.LG↗

arXiv2023

NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

Neural networks have shown great potential in accelerating the solution of partial differential equations (PDEs). Recently, there has been a growing interest in introducing physics constraints into training neural PDE solvers to reduce the use of costly data and improve the generalization ability. However, these physics constraints, based on certain finite dimensional approximations over the function space, must resolve the smallest scaled physics to ensure the accuracy and stability of the simulation, resulting in high computational costs from large input, output, and neural networks. This paper proposes a general acceleration methodology called NeuralStagger by spatially and temporally decomposing the original learning tasks into several coarser-resolution subtasks. We define a coarse-resolution neural solver for each subtask, which requires fewer computational resources, and jointly train them with the vanilla physics-constrained loss by simply arranging their outputs to reconstruct the original solution. Due to the perfect parallelism between them, the solution is achieved as fast as a coarse-resolution neural solver. In addition, the trained solvers bring the flexibility of simulating with multiple levels of resolution. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations, which leads to an additional $10\sim100\times$ speed-up. Moreover, the experiment also shows that the learned model could be well used for optimal control.

cs.LG↗

arXiv2023

'Tax-free' 3DMM Conditional Face Generation

3DMM conditioned face generation has gained traction due to its well-defined controllability; however, the trade-off is lower sample quality: Previous works such as DiscoFaceGAN and 3D-FM GAN show a significant FID gap compared to the unconditional StyleGAN, suggesting that there is a quality tax to pay for controllability. In this paper, we challenge the assumption that quality and controllability cannot coexist. To pinpoint the previous issues, we mathematically formalize the problem of 3DMM conditioned face generation. Then, we devise simple solutions to the problem under our proposed framework. This results in a new model that effectively removes the quality tax between 3DMM conditioned face GANs and the unconditional StyleGAN.

cs.CV↗

arXiv2023

Complex-valued neural operator assisted soliton identification

The numerical determination of solitary states is an important topic for such research areas as Bose-Einstein condensates, nonlinear optics, plasma physics, etc. In this paper, we propose a data-driven approach for identifying solitons based on dynamical solutions of real-time differential equations. Our approach combines a machine-learning architecture called the complex-valued neural operator (CNO) with an energy-restricted gradient optimization. The former serves as a generalization of the traditional neural operator to the complex domain, and constructs a smooth mapping between the initial and final states; the latter facilitates the search for solitons by constraining the energy space. We concretely demonstrate this approach on the quasi-one-dimensional Bose-Einstein condensate with homogeneous and inhomogeneous nonlinearities. Our work offers a new idea for data-driven effective modeling and studies of solitary waves in nonlinear physical systems.

cond-mat.quant-gas↗

arXiv2023

Leveraging BEV Representation for 360-degree Visual Place Recognition

This paper investigates the advantages of using Bird's Eye View (BEV) representation in 360-degree visual place recognition (VPR). We propose a novel network architecture that utilizes the BEV representation in feature extraction, feature aggregation, and vision-LiDAR fusion, which bridges visual cues and spatial awareness. Our method extracts image features using standard convolutional networks and combines the features according to pre-defined 3D grid spatial points. To alleviate the mechanical and time misalignments between cameras, we further introduce deformable attention to learn the compensation. Upon the BEV feature representation, we then employ the polar transform and the Discrete Fourier transform for aggregation, which is shown to be rotation-invariant. In addition, the image and point cloud cues can be easily stated in the same coordinates, which benefits sensor fusion for place recognition. The proposed BEV-based method is evaluated in ablation and comparative studies on two datasets, including on-the-road and off-the-road scenarios. The experimental results verify the hypothesis that BEV can benefit VPR by its superior performance compared to baseline methods. To the best of our knowledge, this is the first trial of employing BEV representation in this task.

cs.CV↗

arXiv2023

Discounted Thompson Sampling for Non-Stationary Bandit Problems

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change at unknown time steps, and smoothly changing, where reward distributions evolve smoothly based on unknown dynamics. In this paper, we propose Discounted Thompson Sampling (DS-TS) with Gaussian priors to address both non-stationary settings. Our algorithm passively adapts to changes by incorporating a discounted factor into Thompson Sampling. DS-TS method has been experimentally validated, but analysis of the regret upper bound is currently lacking. Under mild assumptions, we show that DS-TS with Gaussian priors can achieve nearly optimal regret bound on the order of $\tilde{O}(\sqrt{TB_T})$ for abruptly changing and $\tilde{O}(T^β)$ for smoothly changing, where $T$ is the number of time steps, $B_T$ is the number of breakpoints, $β$ is associated with the smoothly changing environment and $\tilde{O}$ hides the parameters independent of $T$ as well as logarithmic terms. Furthermore, empirical comparisons between DS-TS and other non-stationary bandit algorithms demonstrate its competitive performance. Specifically, when prior knowledge of the maximum expected reward is available, DS-TS has the potential to outperform state-of-the-art algorithms.

cs.LG↗

arXiv2023

PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy

AI-Generated Content (AIGC) has recently gained a surge in popularity, powered by its high efficiency and consistency in production, and its capability of being customized and diversified. The cross-modality nature of the representation learning mechanism in most AIGC technology allows for more freedom and flexibility in exploring new types of art that would be impossible in the past. Inspired by the pictogram subset of Chinese characters, we proposed PaCaNet, a CycleGAN-based pipeline for producing novel artworks that fuse two different art types, traditional Chinese painting and calligraphy. In an effort to produce stable and diversified output, we adopted three main technical innovations: 1. Using one-shot learning to increase the creativity of pre-trained models and diversify the content of the fused images. 2. Controlling the preference over generated Chinese calligraphy by freezing randomly sampled parameters in pre-trained models. 3. Using a regularization method to encourage the models to produce images similar to Chinese paintings. Furthermore, we conducted a systematic study to explore the performance of PaCaNet in diversifying fused Chinese painting and calligraphy, which showed satisfying results. In conclusion, we provide a new direction of creating arts by fusing the visual information in paintings and the stroke features in Chinese calligraphy. Our approach creates a unique aesthetic experience rooted in the origination of Chinese hieroglyph characters. It is also a unique opportunity to delve deeper into traditional artwork and, in doing so, to create a meaningful impact on preserving and revitalizing traditional heritage.

cs.CV↗

arXiv2023

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations in terms of architecture and pretraining tasks. First, they often adopt a specific architecture (encoder-only or decoder-only) or rely on a unified encoder-decoder network for different downstream tasks. The former paradigm is limited by inflexibility in applications while in the latter, the model is treated as a single system for all tasks, leading to suboptimal performance on a subset of tasks. Secondly, they often employ a limited set of pretraining objectives which might not be relevant to some downstream tasks and hence result in substantial performance degrade. To address these limitations, we propose ``CodeT5+'', a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. Such flexibility is enabled by our proposed mixture of pretraining objectives to mitigate the pretrain-finetune discrepancy. These objectives cover span denoising, contrastive learning, text-code matching, and causal LM pretraining tasks, on both unimodal and bimodal multilingual code corpora. Furthermore, we propose to initialize CodeT5+ with frozen off-the-shelf LLMs without training from scratch to efficiently scale up our models, and explore instruction-tuning to align with natural language instructions. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning. We observe state-of-the-art (SoTA) model performance on various code-related tasks, such as code generation and completion, math programming, and text-to-code retrieval tasks. Particularly, our instruction-tuned CodeT5+ 16B achieves new SoTA results on HumanEval code generation task against other open code LLMs.

cs.CL↗

arXiv2023

Model-Free Robust Average-Reward Reinforcement Learning

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free setting. We first theoretically characterize the structure of solutions to the robust average-reward Bellman equation, which is essential for our later convergence analysis. We then design two model-free algorithms, robust relative value iteration (RVI) TD and robust RVI Q-learning, and theoretically prove their convergence to the optimal solution. We provide several widely used uncertainty sets as examples, including those defined by the contamination model, total variation, Chi-squared divergence, Kullback-Leibler (KL) divergence and Wasserstein distance.

cs.LG↗

arXiv2023

GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud representation learning framework, based on geometric feature reconstruction. In contrast to recent papers that directly adopt masked autoencoder (MAE) and only predict original coordinates or occupancy from masked point clouds, our method revisits differences between images and point clouds and identifies three self-supervised learning objectives peculiar to point clouds, namely centroid prediction, normal estimation, and curvature prediction. Combined with occupancy prediction, these four objectives yield an nontrivial self-supervised learning task and mutually facilitate models to better reason fine-grained geometry of point clouds. Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder; second, a lightweight Transformer decoder predicts centroid, normal, and curvature for points in each voxel. We transfer the pre-trained Transformer encoder to a downstream peception model. On the nuScene Datset, our model achieves 3.38 mAP improvment for object detection, 2.1 mIoU gain for segmentation, and 1.7 AMOTA gain for multi-object tracking. We also conduct experiments on the Waymo Open Dataset and achieve significant performance improvements over baselines as well.

cs.CV↗

arXiv2023

Van der Waals Nanoantennas on Gold as Hosts for Hybrid Mie-Plasmonic Resonances

Dielectric nanoresonators have been shown to circumvent the heavy optical losses associated with plasmonic devices, however they suffer from less confined resonances. By constructing a hybrid system of both dielectric and metallic materials, one can retain the low losses of dielectric resonances, whilst gaining additional control over the tuning of the modes with the metal, and achieving stronger mode confinement. In particular, multi-layered van der Waals materials are emerging as promising candidates for integration with metals owing to their weak attractive forces, which enable deposition onto such substrates without the requirement of lattice matching. Here we use layered, high refractive index WS$_2$ exfoliated on gold, to fabricate and optically characterize a hybrid nanoantenna-on-gold system. We experimentally observe a hybridization of Mie resonances, Fabry-Pérot modes, and surface plasmon-polaritons launched from the nanoantennas into the substrate. We achieve experimental quality factors of Mie-plasmonic modes of up to 20 times that of Mie resonances in nanoantennas on silica, and observe signatures of a supercavity mode with a Q factor of 263 $\pm$ 28, resulting from strong mode coupling between a higher-order anapole and Fabry-Pérot-plasmonic mode. We further simulate WS$_2$ nanoantennas on gold with an hBN spacer, resulting in calculated electric field enhancements exceeding 2600, and a Purcell factor of 713. Our results demonstrate dramatic changes in the optical response of dielectric nanophotonic structures placed on gold, opening new possibilities for nanophotonics and sensing with simple-to-fabricate devices.

cond-mat.mes-hall↗

arXiv2023

An Efficient Multi-solution Solver for the Inverse Kinematics of 3-Section Constant-Curvature Robots

Piecewise constant curvature is a popular kinematics framework for continuum robots. Computing the model parameters from the desired end pose, known as the inverse kinematics problem, is fundamental in manipulation, tracking and planning tasks. In this paper, we propose an efficient multi-solution solver to address the inverse kinematics problem of 3-section constant-curvature robots by bridging both the theoretical reduction and numerical correction. We derive analytical conditions to simplify the original problem into a one-dimensional problem. Further, the equivalence of the two problems is formalised. In addition, we introduce an approximation with bounded error so that the one dimension becomes traversable while the remaining parameters analytically solvable. With the theoretical results, the global search and numerical correction are employed to implement the solver. The experiments validate the better efficiency and higher success rate of our solver than the numerical methods when one solution is required, and demonstrate the ability of obtaining multiple solutions with optimal path planning in a space with obstacles.

cs.RO↗

arXiv2023

Learning adaptive manipulation of objects with revolute joint: A case study on varied cabinet doors opening

This paper introduces a learning-based framework for robot adaptive manipulating the object with a revolute joint in unstructured environments. We concentrate our discussion on various cabinet door opening tasks. To improve the performance of Deep Reinforcement Learning in this scene, we analytically provide an efficient sampling manner utilizing the constraints of the objects. To open various kinds of doors, we add encoded environment parameters that define the various environments to the input of out policy. To transfer the policy into the real world, we train an adaptation module in simulation and fine-tune the adaptation module to cut down the impact of the policy-unaware environment parameters. We design a series of experiments to validate the efficacy of our framework. Additionally, we testify to the model's performance in the real world compared to the traditional door opening method.

cs.RO↗

arXiv2023

Zero-shot Transfer Learning of Driving Policy via Socially Adversarial Traffic Flow

Acquiring driving policies that can transfer to unseen environments is challenging when driving in dense traffic flows. The design of traffic flow is essential and previous studies are unable to balance interaction and safety-criticism. To tackle this problem, we propose a socially adversarial traffic flow. We propose a Contextual Partially-Observable Stochastic Game to model traffic flow and assign Social Value Orientation (SVO) as context. We then adopt a two-stage framework. In Stage 1, each agent in our socially-aware traffic flow is driven by a hierarchical policy where upper-level policy communicates genuine SVOs of all agents, which the lower-level policy takes as input. In Stage 2, each agent in the socially adversarial traffic flow is driven by the hierarchical policy where upper-level communicates mistaken SVOs, taken by the lower-level policy trained in Stage 1. Driving policy is adversarially trained through a zero-sum game formulation with upper-level policies, resulting in a policy with enhanced zero-shot transfer capability to unseen traffic flows. Comprehensive experiments on cross-validation verify the superior zero-shot transfer performance of our method.

cs.RO↗

arXiv2023

Gate-tunable ferromagnetism in a van der Waals magnetic semimetal

Magnetic semimetals form an attractive class of materials because of the non-trivial contributions of itinerant electrons to magnetism. Due to their relatively low-carrier-density nature, a doping level of those materials could be largely tuned by a gating technique. Here we demonstrate gate-tunable ferromagnetism in an emergent van der Waals magnetic semimetal Cr3Te4 based on an ion-gating technique. Upon doping electrons into the system, the Curie temperature (TC) sharply increases, approaching near to room temperature, then decreases to some extent. Interestingly, this non-monotonous variation of TC accompanies the switching of the magnetic anisotropy. Furthermore, such evolutions of TC and anisotropy occur synchronously with the sigh changes of the ordinary and anomalous Hall effects. Those results clearly elucidate that the magnetism in Cr3Te4 should be governed by its semimetallic band nature, where the band crossing points play a crucial role both for the magneto-transport properties and magnetism itself.

cond-mat.mtrl-sci↗