Search

Superconducting transmon qubits have established as a leading candidate for quantum computation, as well as a flexible platform for exploring exotic quantum phases and dynamics. However, physical coupling naturally yields isotropic transverse interactions between qubits, restricting their access to diverse quantum phases that require spatially dependent interactions. Here, we demonstrate the simultaneous realization of both pairing (XX-YY) and hopping (XX+YY) interactions between transmon qubits by Floquet engineering. The coherent superposition of these interactions enables independent control over the XX and YY terms, yielding anisotropic transverse interactions. By aligning the transverse interactions along a 1D chain of six qubits, as calibrated via Aharonov-Bohm interference in synthetic space, we synthesize a transverse field Ising chain model and explore its dynamical phase transition under varying external field. The scalable synthesis of anisotropic transverse interactions paves the way for the implementation of more complex physical systems requiring spatially dependent interactions, enriching the toolbox for engineering quantum phases with superconducting qubits., Comment: 7+14 pages; 4+12 figures

As superconducting quantum computing continues to advance at an unprecedented pace, there is a compelling demand for the innovation of specialized electronic instruments that act as crucial conduits between quantum processors and host computers. Here, we introduce a Microwave Measurement and Control System (M2CS) dedicated for large-scale superconducting quantum processors. M2CS features a compact modular design that balances overall performance, scalability, and flexibility. Electronic tests of M2CS show key metrics comparable to commercial instruments. Benchmark tests on transmon superconducting qubits further show qubit coherence and gate fidelities comparable to state-of-the-art results, confirming M2CS's capability to meet the stringent requirements of quantum experiments run on intermediate-scale quantum processors. The system's compact and scalable design offers significant room for further enhancements that could accommodate the measurement and control requirements of over 1000 qubits, and can also be adopted to other quantum computing platforms such as trapped ions and silicon quantum dots. The M2CS architecture may also be applied to wider range of scenarios, such as microwave kinetic inductance detectors, as well as phased array radar systems.

Mixers play a crucial role in superconducting quantum computing, primarily by facilitating frequency conversion of signals to enable precise control and readout of quantum states. However, imperfections, particularly carrier leakage and unwanted sideband signal, can significantly compromise control fidelity. To mitigate these defects, regular and precise mixer calibrations are indispensable, yet they pose a formidable challenge in large-scale quantum control. Here, we introduce an in situ calibration technique and outcome-focused mixer calibration scheme using superconducting qubits. Our method leverages the qubit's response to imperfect signals, allowing for calibration without modifying the wiring configuration. We experimentally validate the efficacy of this technique by benchmarking single-qubit gate fidelity and qubit coherence time., Comment: 9 pages, 7 figures

Random fluctuations can lead to cooperative effects in complex systems. We here report the experimental observation of noise-induced quantum synchronization in a chain of superconducting transmon qubits with nearest-neighbor interactions. The application of Gaussian white noise to a single site leads to synchronous oscillations in the entire chain. We show that the two synchronized end qubits are entangled, with nonzero concurrence, and that they belong to a class of generalized Bell states known as maximally entangled mixed states, whose entanglement cannot be increased by any global unitary. We further demonstrate the stability against frequency detuning of both synchronization and entanglement by determining the corresponding generalized Arnold tongue diagrams. Our results highlight the constructive influence of noise in a quantum many-body system and uncover the potential role of synchronization for mixed-state quantum information science.

Superconducting qubits are a promising platform for building fault-tolerant quantum computers, with recent achievement showing the suppression of logical error with increasing code size. However, leakage into non-computational states, a common issue in practical quantum systems including superconducting circuits, introduces correlated errors that undermine QEC scalability. Here, we propose and demonstrate a leakage reduction scheme utilizing tunable couplers, a widely adopted ingredient in large-scale superconducting quantum processors. Leveraging the strong frequency tunability of the couplers and stray interaction between the couplers and readout resonators, we eliminate state leakage on the couplers, thus suppressing space-correlated errors caused by population propagation among the couplers. Assisted by the couplers, we further reduce leakage to higher qubit levels with high efficiency (98.1%) and low error rate on the computational subspace (0.58%), suppressing time-correlated errors during QEC cycles. The performance of our scheme demonstrates its potential as an indispensable building block for scalable QEC with superconducting qubits., Comment: 25 pages, 15 figures

Autonomous driving systems require the ability to fully understand and predict the surrounding environment to make informed decisions in complex scenarios. Recent advancements in learning-based systems have highlighted the importance of integrating prediction and planning modules. However, this integration has brought forth three major challenges: inherent trade-offs by sole prediction, consistency between prediction patterns, and social coherence in prediction and planning. To address these challenges, we introduce a hybrid-prediction integrated planning (HPP) system, which possesses three novelly designed modules. First, we introduce marginal-conditioned occupancy prediction to align joint occupancy with agent-wise perceptions. Our proposed MS-OccFormer module achieves multi-stage alignment per occupancy forecasting with consistent awareness from agent-wise motion predictions. Second, we propose a game-theoretic motion predictor, GTFormer, to model the interactive future among individual agents with their joint predictive awareness. Third, hybrid prediction patterns are concurrently integrated with Ego Planner and optimized by prediction guidance. HPP achieves state-of-the-art performance on the nuScenes dataset, demonstrating superior accuracy and consistency for end-to-end paradigms in prediction and planning. Moreover, we test the long-term open-loop and closed-loop performance of HPP on the Waymo Open Motion Dataset and CARLA benchmark, surpassing other integrated prediction and planning pipelines with enhanced accuracy and compatibility.

With the increasing availability of consumer depth sensors, 3D face recognition (FR) has attracted more and more attention. However, the data acquired by these sensors are often coarse and noisy, making them impractical to use directly. In this paper, we introduce an innovative Depth map denoising network (DMDNet) based on the Denoising Implicit Image Function (DIIF) to reduce noise and enhance the quality of facial depth images for low-quality 3D FR. After generating clean depth faces using DMDNet, we further design a powerful recognition network called Lightweight Depth and Normal Fusion network (LDNFNet), which incorporates a multi-branch fusion block to learn unique and complementary features between different modalities such as depth and normal images. Comprehensive experiments conducted on four distinct low-quality databases demonstrate the effectiveness and robustness of our proposed methods. Furthermore, when combining DMDNet and LDNFNet, we achieve state-of-the-art results on the Lock3DFace database., Comment: Accepted by Pattern Recognition

Superconducting qubits have emerged as a premier platform for large-scale quantum computation, yet the fidelity of state readout is often hindered by random noise and crosstalk, especially in multi-qubit systems. While neural networks trained on labeled data have shown promise in reducing crosstalk effects during readout, their current capabilities are limited to binary discrimination of joint-qubit states due to architectural constraints. Here we introduce a time-resolved modulated neural network capable of full-state tomography for individual qubits, enabling detailed time-resolved measurements like Rabi oscillations. This scalable approach, with a dedicated module per qubit, mitigated readout error by an order of magnitude under low signal-to-noise ratios and substantially reduced variance in Rabi oscillation measurements. This advancement bolsters quantum state discrimination with neural networks, and propels the development of next-generation quantum processors with enhanced performance and scalability.

As the basis for generating multi-particle quantum correlations, inter-particle interaction plays a crucial role in collective quantum phenomena, quantum phase transitions, and quantum information processing. It can profoundly alter the band structure of quantum many-body systems and give rise to exotic topological phenomena. Conventional topological pumping, which has been well demonstrated in driven linear or noninteracting systems, may break down in the presence of strong interaction. However, the interplay between band topology and interaction could also induce emergent topological pumping of interacting particles, but its experimental realization has proven challenging. Here we demonstrate interaction-induced topological pumping in a solid-state quantum system comprising an array of 36 superconducting qubits. With strong interaction inherent in the qubits and site-resolved controllability of the lattice potential and hopping strength, we realize the topological Thouless pumping of single and two bounded particles. Beyond these topological phenomena with linear or noninteracting counterparts, we also observe topologically resonant tunneling and asymmetric edge-state transport of interacting particles. Our work creates a paradigm for multi-particle topological effects, and provides a new pathway to the study of exotic topological phenomena, many-body quantum transport, and quantum information transfer., Comment: 8+29 pages, 4+24 figures

Quantum teleportation~\cite{Bennett1993} is of both fundamental interest and great practical importance in quantum information science. To date, quantum teleportation has been implemented in various physical systems~\cite{Pirandola2015}, among which superconducting qubits are of particular practical significance as they emerge as a leading system to realize large-scale quantum computation~\cite{Arute2019,Wu2021}. Nevertheless, the number of superconducting qubits on the same chip is severely limited by the available chip size, the cooling power, and the wiring complexity. Realization of quantum teleportation and remote computation over qubits on distant superconducting chips is a key quantum communication technology to scaling up the system through a distributed quantum computational network~\cite{Gottesman1999,Eisert2000,Jiang2007,Kimble2008,Monroe2014}. However, this goal has not been realized yet in experiments due to the technical challenge of making a quantum interconnect between distant superconducting chips and the inefficient transfer of flying microwave photons over the lossy interconnects~\cite{Kurpiers2018,Axline2018,Campagne2018,Magnard2020}. Here we demonstrate deterministic teleportation of quantum states and entangling gates between distant superconducting chips connected by a 64-meter-long cable bus featuring an ultralow loss of 0.32~dB/km at cryogenic temperatures, where high fidelity remote entanglement is generated via flying microwave photons utilizing time-reversal-symmetry~\cite{Cirac1997,Korotkov2011}. Apart from the fundamental interest of teleporting macroscopic superconducting qubits over a long distance, our work lays a foundation to realization of large-scale superconducting quantum computation through a distributed computational network~\cite{Gottesman1999,Eisert2000,Jiang2007,Kimble2008,Monroe2014}.

Predicting the behaviors of other road users is crucial to safe and intelligent decision-making for autonomous vehicles (AVs). However, most motion prediction models ignore the influence of the AV's actions and the planning module has to treat other agents as unalterable moving obstacles. To address this problem, this paper proposes an interaction-aware motion prediction model that is able to predict other agents' future trajectories according to the ego agent's future plan, i.e., their reactions to the ego's actions. Specifically, we employ Transformers to effectively encode the driving scene and incorporate the AV's plan in decoding the predicted trajectories. To train the model to accurately predict the reactions of other agents, we develop an online learning framework, where the ego agent explores the environment and collects other agents' reactions to itself. We validate the decision-making and learning framework in three highly interactive simulated driving scenarios. The results reveal that our decision-making method significantly outperforms the reinforcement learning methods in terms of data efficiency and performance. We also find that using the interaction-aware model can bring better performance than the non-interaction-aware model and the exploration process helps improve the success rate in testing.

Scaling is now a key challenge in superconducting quantum computing. One solution is to build modular systems in which smaller-scale quantum modules are individually constructed and calibrated, and then assembled into a larger architecture. This, however, requires the development of suitable interconnects. Here, we report low-loss interconnects based on pure aluminium coaxial cables and on-chip impedance transformers featuring quality factors up to $8.1 \times 10^5$, which is comparable to the performance of our transmon qubits fabricated on single-crystal sapphire substrate. We use these interconnects to link five quantum modules with inter-module quantum state transfer and Bell state fidelities up to 99\%. To benchmark the overall performance of the processor, we create maximally-entangled, multi-qubit Greenberger-Horne-Zeilinger (GHZ) states. The generated inter-module four-qubit GHZ state exhibits 92.0\% fidelity. We also entangle up to 12 qubits in a GHZ state with $55.8 \pm 1.8\%$ fidelity, which is above the genuine multipartite entanglement threshold of 1/2. These results represent a viable modular approach for large-scale superconducting quantum processors.

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-the-art (SOTA) baselines. The demonstration video (https://www.youtube.com/watch?v=aqJCHcsj4w0) and the source code (https://github.com/OscarHuangWind/DRL-Transformer-SimtoReal-Navigation) are also provided.

Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing the need for executing deeper layers. While existing works mainly focus on the architectural design of multi-exit networks, the training strategies for such models are largely left unexplored. The current state-of-the-art models treat all samples the same during training. However, the early-exiting behavior during testing has been ignored, leading to a gap between training and testing. In this paper, we propose to bridge this gap by sample weighting. Intuitively, easy samples, which generally exit early in the network during inference, should contribute more to training early classifiers. The training of hard samples (mostly exit from deeper layers), however, should be emphasized by the late classifiers. Our work proposes to adopt a weight prediction network to weight the loss of different training samples at each exit. This weight prediction network and the backbone model are jointly optimized under a meta-learning framework with a novel optimization objective. By bringing the adaptive behavior during inference into the training phase, we show that the proposed weighting mechanism consistently improves the trade-off between classification accuracy and inference efficiency. Code is available at https://github.com/LeapLabTHU/L2W-DEN., Comment: ECCV 2022

Decision-making is critical for lane change in autonomous driving. Reinforcement learning (RL) algorithms aim to identify the values of behaviors in various situations and thus they become a promising pathway to address the decision-making problem. However, poor runtime safety hinders RL-based decision-making strategies from complex driving tasks in practice. To address this problem, human demonstrations are incorporated into the RL-based decision-making strategy in this paper. Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the replay buffer and then utilized to enhance the training process of RL. A complex lane change task in an off-ramp scenario is established to examine the performance of the developed strategy. Simulation results suggest that human demonstrations can effectively improve the safety of decisions of RL. And the proposed strategy surpasses other existing learning-based decision-making strategies with respect to multiple driving performances.

Gate-based quantum computation has been extensively investigated using quantum circuits based on qubits. In many cases, such qubits are actually made out of multilevel systems but with only two states being used for computational purpose. While such a strategy has the advantage of being in line with the common binary logic, it in some sense wastes the ready-for-use resources in the large Hilbert space of these intrinsic multi-dimensional systems. Quantum computation beyond qubits (e.g., using qutrits or qudits) has thus been discussed and argued to be more efficient than its qubit counterpart in certain scenarios. However, one of the essential elements for qutrit-based quantum computation, two-qutrit quantum gate, remains a major challenge. In this work, we propose and demonstrate a highly efficient and scalable two-qutrit quantum gate in superconducting quantum circuits. Using a tunable coupler to control the cross-Kerr coupling between two qutrits, our scheme realizes a two-qutrit conditional phase gate with fidelity 89.3% by combining simple pulses applied to the coupler with single-qutrit operations. We further use such a two-qutrit gate to prepare an EPR state of two qutrits with a fidelity of 95.5%. Our scheme takes advantage of a tunable qutrit-qutrit coupling with a large on:off ratio. It therefore offers both high efficiency and low cross talk between qutrits, thus being friendly for scaling up. Our work constitutes an important step towards scalable qutrit-based quantum computation., Comment: 15 pages, 12 figures

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $\epsilon$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing additional bias. Specifically, we design a dual architecture consisting of two branches, one of which is a copy of DQN, namely the Q-branch. The other branch, which we call the preference branch, learns the action preference that the DQN implicit follows. We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values. Consequently, preference-guided $\epsilon$-greedy exploration motivates the DQN agent to take diverse actions, i.e., actions with larger Q-values can be sampled more frequently whereas actions with smaller Q-values still have a chance to be explored, thus encouraging the exploration. We assess the proposed method with four well-known DQN variants in nine different environments. Extensive results confirm the superiority of our proposed method in terms of performance and convergence speed. Index Terms- Preference-guided exploration, stochastic policy, data efficiency, deep reinforcement learning, deep Q-learning.

We propose a physical design of a compact all optical terahertz (THz)-driven electron source. The 300 mm accelerator beamline, powered by Joule level laser system, is easily to be integrated to tabletop scale. A dual-feed THz-driven electron gun with an exponential impedance, a tapered dielectric loaded cylindrical waveguide, THz-driven bunch compressors and permanent magnet solenoids (PMS) have been designed and optimized. Dynamics simulations show that the electron source can deliver a 19 fC, 3 MeV electron beams with a normalized transverse emittance of 0.079 {\pi}.mm.mrad. A minimum relative energy spread of 0.04% or a minimum root-mean-square bunch length of 6.1 fs can be achieved by adjusting the beam shaping line. Sensitivity analysis shows that the THz-driven electron source can effectively work under a 1.5% energy jitter of the THz power system. Simulated diffraction pattern up to the fourth order of an aluminum sample based on the beamline can be clearly distinguished. A prototype THz gun has beam fabricated and is now under testing, more results will be reported in future works., Comment: 13 pages, 15 figures

Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore, static models which process all the pixels with an equal amount of computation result in considerable redundancy in terms of time and space consumption. In this paper, we formulate the image recognition problem as a sequential coarse-to-fine feature learning process, mimicking the human visual system. Specifically, the proposed Glance and Focus Network (GFNet) first extracts a quick global representation of the input image at a low resolution scale, and then strategically attends to a series of salient (small) regions to learn finer features. The sequential process naturally facilitates adaptive inference at test time, as it can be terminated once the model is sufficiently confident about its prediction, avoiding further redundant computation. It is worth noting that the problem of locating discriminant regions in our model is formulated as a reinforcement learning task, thus requiring no additional manual annotations other than classification labels. GFNet is general and flexible as it is compatible with any off-the-shelf backbone models (such as MobileNets, EfficientNets and TSM), which can be conveniently deployed as the feature extractor. Extensive experiments on a variety of image classification and video recognition tasks and with various backbone models demonstrate the remarkable efficiency of our method. For example, it reduces the average latency of the highly efficient MobileNet-V3 on an iPhone XS Max by 1.3x without sacrificing accuracy. Code and pre-trained models are available at https://github.com/blackfeather-wang/GFNet-Pytorch., Comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). Journal version of arXiv:2010.05300 (NeurIPS 2020). The first two authors contributed equally

Implementing quantum algorithms on realistic hardware requires translating high-level global operations into sequences of native elementary gates, a process known as quantum compiling. Physical limitations, such as constraints in connectivity and gate alphabets, often result in unacceptable implementation costs. To enable successful near-term applications, it is crucial to optimize compilation by exploiting the potential capabilities of existing hardware. Here, we implement a resource-efficient construction for a quantum version of AND logic that can reduce the cost, enabling the execution of key quantum circuits. On a high-scalability superconducting quantum processor, we demonstrate low-depth synthesis of high-fidelity generalized Toffoli gates with up to 8 qubits and Grover's search algorithm in a search space of up to 64 entries; both are the largest such implementations in scale to date. Our experimental demonstration illustrates a scalable implementation of simplifying quantum algorithms, paving the way for larger, more meaningful quantum applications on noisy devices.

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising way to improve learning performance. In this paper, a comprehensive human guidance-based reinforcement learning framework is established. A novel prioritized experience replay mechanism that adapts to human guidance in the reinforcement learning process is proposed to boost the efficiency and performance of the reinforcement learning algorithm. To relieve the heavy workload on human participants, a behavior model is established based on an incremental online learning method to mimic human actions. We design two challenging autonomous driving tasks for evaluating the proposed algorithm. Experiments are conducted to access the training and testing performance and learning mechanism of the proposed algorithm. Comparative results against the state-of-the-art methods suggest the advantages of our algorithm in terms of learning efficiency, performance, and robustness.