Search

We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing approaches. To accomplish this task, we design a hierarchical learning and control framework, which consists of a learned heightmap predictor for robust terrain perception, a reinforcement-learning-based centroidal-level motion policy for versatile and terrain-adaptive planning, and a low-level model-based leg controller for accurate motion tracking. In addition, we minimize the sim-to-real gap by accurately modeling the hardware characteristics. Our framework enables a Unitree Go1 robot to perform agile and continuous jumps on human-sized stairs and sparse stepping stones, for the first time to the best of our knowledge. In particular, the robot can cross two stair steps in each jump and completes a 3.5m long, 2.8m high, 14-step staircase in 4.5 seconds. Moreover, the same policy outperforms baselines in various other parkour tasks, such as jumping over single horizontal or vertical discontinuities. Experiment videos can be found at \url{https://yxyang.github.io/jumping\_cod/}., Comment: Website: https://yxyang.github.io/jumping_cod/

This tutorial introduces a systematic approach for addressing the key question of quantum metrology: For a generic task of sensing an unknown parameter, what is the ultimate precision given a constrained set of admissible strategies. The approach outputs the maximal attainable precision (in terms of the maximum of quantum Fisher information) as a semidefinite program and optimal strategies as feasible solutions thereof. Remarkably, the approach can identify the optimal precision for different sets of strategies, including parallel, sequential, quantum SWITCH-enhanced, causally superposed, and generic indefinite-causal-order strategies. The tutorial consists of a pedagogic introduction to the background and mathematical tools of optimal quantum metrology, a detailed derivation of the main approach, and various concrete examples. As shown in the tutorial, applications of the approach include, but are not limited to, strict hierarchy of strategies in noisy quantum metrology, memory effect in non-Markovian metrology, and designing optimal strategies. Compared with traditional approaches, the approach here yields the exact value of the optimal precision, offering more accurate criteria for experiments and practical applications. It also allows for the comparison between conventional strategies and the recently discovered causally-indefinite strategies, serving as a powerful tool for exploring this new area of quantum metrology., Comment: Tutorial. 38 pages, 18 figures

Quantum control plays a crucial role in enhancing precision scaling for quantum sensing. However, most existing protocols require perfect control, even though real-world devices inevitably have control imperfections. Here, we consider a fundamental setting of quantum sensing with imperfect clocks, where the duration of control pulses and the interrogation time are all subject to uncertainty. Under this scenario, we investigate the task of frequency estimation in the presence of a non-Markovian environment. We design a control strategy and prove that it outperforms any control-free strategies, recovering the optimal Heisenberg scaling up to a small error term that is intrinsic to this model. We further demonstrate the advantage of our control strategy via experiments on a nuclear magnetic resonance (NMR) platform. Our finding confirms that the advantage of quantum control in quantum sensing persists even in the presence of imperfections., Comment: 18 pages, 7 figures

Goal-driven mobile robot navigation in map-less environments requires effective state representations for reliable decision-making. Inspired by the favorable properties of Bird's-Eye View (BEV) in point clouds for visual perception, this paper introduces a novel navigation approach named BEVNav. It employs deep reinforcement learning to learn BEV representations and enhance decision-making reliability. First, we propose a self-supervised spatial-temporal contrastive learning approach to learn BEV representations. Spatially, two randomly augmented views from a point cloud predict each other, enhancing spatial features. Temporally, we combine the current observation with consecutive frames' actions to predict future features, establishing the relationship between observation transitions and actions to capture temporal cues. Then, incorporating this spatial-temporal contrastive learning in the Soft Actor-Critic reinforcement learning framework, our BEVNav offers a superior navigation policy. Extensive experiments demonstrate BEVNav's robustness in environments with dense pedestrians, outperforming state-of-the-art methods across multiple benchmarks. \rev{The code will be made publicly available at https://github.com/LanrenzzzZ/BEVNav.

Deep learning has revolutionized the early detection of breast cancer, resulting in a significant decrease in mortality rates. However, difficulties in obtaining annotations and huge variations in distribution between training sets and real scenes have limited their clinical applications. To address these limitations, unsupervised domain adaptation (UDA) methods have been used to transfer knowledge from one labeled source domain to the unlabeled target domain, yet these approaches suffer from severe domain shift issues and often ignore the potential benefits of leveraging multiple relevant sources in practical applications. To address these limitations, in this work, we construct a Three-Branch Mixed extractor and propose a Bi-level Multi-source unsupervised domain adaptation method called BTMuda for breast cancer diagnosis. Our method addresses the problems of domain shift by dividing domain shift issues into two levels: intra-domain and inter-domain. To reduce the intra-domain shift, we jointly train a CNN and a Transformer as two paths of a domain mixed feature extractor to obtain robust representations rich in both low-level local and high-level global information. As for the inter-domain shift, we redesign the Transformer delicately to a three-branch architecture with cross-attention and distillation, which learns domain-invariant representations from multiple domains. Besides, we introduce two alignment modules - one for feature alignment and one for classifier alignment - to improve the alignment process. Extensive experiments conducted on three public mammographic datasets demonstrate that our BTMuda outperforms state-of-the-art methods.

Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for motion-centric tracking. This decouples feature extraction from temporal fusion, significantly enhancing tracking performance. Additionally, we design a Spatio-Temporal Feature Aggregation module to integrate Siamese features at multiple scales, capturing motion information effectively. We also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation. SiamMo is a purely motion-centric tracker that eliminates the need for additional processes like segmentation and box refinement. Without whistles and bells, SiamMo not only surpasses state-of-the-art methods across multiple benchmarks but also demonstrates exceptional robustness in challenging scenarios. SiamMo sets a new record on the KITTI tracking benchmark with 90.1\% precision while maintaining a high inference speed of 108 FPS. The code will be released at https://github.com/HDU-VRLab/SiamMo.

Existing auto-regressive language models have demonstrated a remarkable capability to perform a new task with just a few examples in prompt, without requiring any additional training. In order to extend this capability to a multi-modal setting (i.e. speech and language), this paper introduces the Seal model, an abbreviation for speech language model. It incorporates a novel alignment method, in which Kullback-Leibler divergence loss is performed to train a projector that bridges a frozen speech encoder with a frozen language model decoder. The resulting Seal model exhibits robust performance as a few-shot learner on two speech understanding tasks. Additionally, consistency experiments are conducted to validate its robustness on different pre-trained language models.

Facial Expression Recognition (FER) holds significant importance in human-computer interactions. Existing cross-domain FER methods often transfer knowledge solely from a single labeled source domain to an unlabeled target domain, neglecting the comprehensive information across multiple sources. Nevertheless, cross-multidomain FER (CMFER) is very challenging for (i) the inherent inter-domain shifts across multiple domains and (ii) the intra-domain shifts stemming from the ambiguous expressions and low inter-class distinctions. In this paper, we propose a novel Learning with Alignments CMFER framework, named LA-CMFER, to handle both inter- and intra-domain shifts. Specifically, LA-CMFER is constructed with a global branch and a local branch to extract features from the full images and local subtle expressions, respectively. Based on this, LA-CMFER presents a dual-level inter-domain alignment method to force the model to prioritize hard-to-align samples in knowledge transfer at a sample level while gradually generating a well-clustered feature space with the guidance of class attributes at a cluster level, thus narrowing the inter-domain shifts. To address the intra-domain shifts, LA-CMFER introduces a multi-view intra-domain alignment method with a multi-view clustering consistency constraint where a prediction similarity matrix is built to pursue consistency between the global and local views, thus refining pseudo labels and eliminating latent noise. Extensive experiments on six benchmark datasets have validated the superiority of our LA-CMFER., Comment: Accepted by ACM MM 2024

Localization is critical to numerous applications. The performance of classical localization protocols is limited by the specific form of distance information and suffer from considerable ranging errors. This paper foresees a new opportunity by utilizing the exceptional property of entangled quantum states to measure a linear combination of target-anchor distances. Specifically, we consider localization with quantum-based TDoA measurements. Classical TDoA ranging takes the difference of two separate measurements. Instead, quantum ranging allows TDoA estimation within a single measurement, thereby reducing the ranging errors. Numerical simulations demonstrate that the new quantum-based localization significantly outperforms conventional algorithms based on classical ranging, with over 50% gains on average.

Remarkable advances have been achieved in localization techniques in past decades, rendering it one of the most important technologies indispensable to our daily lives. In this paper, we investigate a novel localization approach for future computing by presenting QuERLoc, the first study on localization using quantum-enhanced ranging. By fine-tuning the evolution of an entangled quantum probe, quantum ranging can output the information integrated in the probe as a specific mapping of distance-related parameters. QuERLoc is inspired by this unique property to measure a special combination of distances between a target sensor and multiple anchors within one single physical measurement. Leveraging this capability, QuERLoc settles two drawbacks of classical localization approaches: (i) the target-anchor distances must be measured individually and sequentially, and (ii) the resulting optimization problems are non-convex and are sensitive to noise. We first present the theoretical formulation of preparing the probing quantum state and controlling its dynamic to induce a convexified localization problem, and then solve it efficiently via optimization. We conduct extensive numerical analysis of QuERLoc under various settings. The results show that QuERLoc consistently outperforms classical approaches in accuracy and closely follows the theoretical lowerbound, while maintaining low time complexity. It achieves a minimum reduction of 73% in RMSE and 97.6% in time consumption compared to baselines. By introducing range-based quantum localization to the mobile computing community and showing its superior performance, QuERLoc sheds light on next-generation localization technologies and opens up new directions for future research.

Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target classes). Existing solutions focus on excavating image features to detect unknown samples, ignoring abundant information contained in textual semantics. In this paper, we propose an Adaptive Prompt learning with Negative textual semantics and uncErtainty modeling method based on Contrastive Language-Image Pre-training (APNE-CLIP) for UniMDA classification tasks. Concretely, we utilize the CLIP with adaptive prompts to leverage textual information of class semantics and domain representations, helping the model identify unknown samples and address domain shifts. Additionally, we design a novel global instance-level alignment objective by utilizing negative textual semantics to achieve more precise image-text pair alignment. Furthermore, we propose an energy-based uncertainty modeling strategy to enlarge the margin distance between known and unknown samples. Extensive experiments demonstrate the superiority of our proposed method., Comment: Accepted by ICME2024

Shallow quantum circuits feature not only computational advantage over their classical counterparts but also cutting-edge applications. Storing quantum information generated by shallow circuits is a fundamental question of both theoretical and practical importance that remained largely unexplored. In this work, we show that $N$ copies of an unknown $n$-qubit state generated by a fixed-depth circuit can be compressed into a hybrid memory of $O(n \log_2 N)$ (qu)bits, which achieves the optimal scaling of memory cost. Our work shows that the computational complexity of resources can significantly impact the rate of quantum information processing, offering a unique and unified view of quantum Shannon theory and quantum computing in the NISQ era., Comment: 22 pages, 2 figures; comments are very welcome

In this paper, we uncover a new side-channel vulnerability in the widely used NAT port preservation strategy and an insufficient reverse path validation strategy of Wi-Fi routers, which allows an off-path attacker to infer if there is one victim client in the same network communicating with another host on the Internet using TCP. After detecting the presence of TCP connections between the victim client and the server, the attacker can evict the original NAT mapping and reconstruct a new mapping at the router by sending fake TCP packets due to the routers' vulnerability of disabling TCP window tracking strategy, which has been faithfully implemented in most of the routers for years. In this way, the attacker can intercept TCP packets from the server and obtain the current sequence and acknowledgment numbers, which in turn allows the attacker to forcibly close the connection, poison the traffic in plain text, or reroute the server's incoming packets to the attacker. We test 67 widely used routers from 30 vendors and discover that 52 of them are affected by this attack. Also, we conduct an extensive measurement study on 93 real-world Wi-Fi networks. The experimental results show that 75 of these evaluated Wi-Fi networks (81%) are fully vulnerable to our attack. Our case study shows that it takes about 17.5, 19.4, and 54.5 seconds on average to terminate an SSH connection, download private files from FTP servers, and inject fake HTTP response packets with success rates of 87.4%, 82.6%, and 76.1%. We responsibly disclose the vulnerability and suggest mitigation strategies to all affected vendors and have received positive feedback, including acknowledgments, CVEs, rewards, and adoption of our suggestions., Comment: Accepted by Network and Distributed System Security (NDSS) Symposium 2024

Quadrupedal robots have emerged as versatile agents capable of locomoting and manipulating in complex environments. Traditional designs typically rely on the robot's inherent body parts or incorporate top-mounted arms for manipulation tasks. However, these configurations may limit the robot's operational dexterity, efficiency and adaptability, particularly in cluttered or constrained spaces. In this work, we present LocoMan, a dexterous quadrupedal robot with a novel morphology to perform versatile manipulation in diverse constrained environments. By equipping a Unitree Go1 robot with two low-cost and lightweight modular 3-DoF loco-manipulators on its front calves, LocoMan leverages the combined mobility and functionality of the legs and grippers for complex manipulation tasks that require precise 6D positioning of the end effector in a wide workspace. To harness the loco-manipulation capabilities of LocoMan, we introduce a unified control framework that extends the whole-body controller (WBC) to integrate the dynamics of loco-manipulators. Through experiments, we validate that the proposed whole-body controller can accurately and stably follow desired 6D trajectories of the end effector and torso, which, when combined with the large workspace from our design, facilitates a diverse set of challenging dexterous loco-manipulation tasks in confined spaces, such as opening doors, plugging into sockets, picking objects in narrow and low-lying spaces, and bimanual manipulation., Comment: Project page: https://linchangyi1.github.io/LocoMan

Optimized quantum control can enhance the performance and noise resilience of quantum metrology. However, the optimization quickly becomes intractable when multiple control operations are applied sequentially. In this work, we propose efficient tensor network algorithms for optimizing strategies of quantum metrology enhanced by a long sequence of control operations. Our approach covers a general and practical scenario where the experimenter applies $N-1$ interleaved control operations between $N$ queries of the channel to estimate and uses no or bounded ancilla. Tailored to different experimental capabilities, these control operations can be generic quantum channels or variational unitary gates. Numerical experiments show that our algorithm has a good performance in optimizing the metrological strategy for as many as $N=100$ queries. In particular, our algorithm identifies a strategy that can outperform the state-of-the-art strategy when $N$ is finite but large., Comment: 12+3 pages, 7 figures; improved efficiency; added variational unitary control optimization; more numerical experiments

The asymptotic theory of quantum channel estimation has been well established, but in general noiseless and controllable ancilla is required for attaining the ultimate limit in the asymptotic regime. Little is known about the metrological performance without noiseless ancilla, which is more relevant in practical circumstances. In this work, we present a novel theoretical framework to address this problem, bridging quantum metrology and the asymptotic theory of quantum channels. Leveraging this framework, we prove sufficient conditions for achieving the Heisenberg limit with repeated application of the channel to estimate, both with and without applying interleaved unitary control operations. For the latter case, we design an algorithm to identify the control operation. Finally, we analyze several intriguing examples by our approach., Comment: 15 pages + 2 figures

In this paper, we unveil a fundamental side channel in Wi-Fi networks, specifically the observable frame size, which can be exploited by attackers to conduct TCP hijacking attacks. Despite the various security mechanisms (e.g., WEP and WPA2/WPA3) implemented to safeguard Wi-Fi networks, our study reveals that an off path attacker can still extract sufficient information from the frame size side channel to hijack the victim's TCP connection. Our side channel attack is based on two significant findings: (i) response packets (e.g., ACK and RST) generated by TCP receivers vary in size, and (ii) the encrypted frames containing these response packets have consistent and distinguishable sizes. By observing the size of the victim's encrypted frames, the attacker can detect and hijack the victim's TCP connections. We validate the effectiveness of this side channel attack through two case studies, i.e., SSH DoS and web traffic manipulation. Precisely, our attack can terminate the victim's SSH session in 19 seconds and inject malicious data into the victim's web traffic within 28 seconds. Furthermore, we conduct extensive measurements to evaluate the impact of our attack on real-world Wi-Fi networks. We test 30 popular wireless routers from 9 well-known vendors, and none of these routers can protect victims from our attack. Besides, we implement our attack in 80 real-world Wi-Fi networks and successfully hijack the victim's TCP connections in 75 (93.75%) evaluated Wi-Fi networks. We have responsibly disclosed the vulnerability to the Wi-Fi Alliance and proposed several mitigation strategies to address this issue.

Animal Pose Estimation and Tracking (APT) is a critical task in detecting and monitoring the keypoints of animals across a series of video frames, which is essential for understanding animal behavior. Past works relating to animals have primarily focused on either animal tracking or single-frame animal pose estimation only, neglecting the integration of both aspects. The absence of comprehensive APT datasets inhibits the progression and evaluation of animal pose estimation and tracking methods based on videos, thereby constraining their real-world applications. To fill this gap, we introduce APTv2, the pioneering large-scale benchmark for animal pose estimation and tracking. APTv2 comprises 2,749 video clips filtered and collected from 30 distinct animal species. Each video clip includes 15 frames, culminating in a total of 41,235 frames. Following meticulous manual annotation and stringent verification, we provide high-quality keypoint and tracking annotations for a total of 84,611 animal instances, split into easy and hard subsets based on the number of instances that exists in the frame. With APTv2 as the foundation, we establish a simple baseline method named \posetrackmethodname and provide benchmarks for representative models across three tracks: (1) single-frame animal pose estimation track to evaluate both intra- and inter-domain transfer learning performance, (2) low-data transfer and generalization track to evaluate the inter-species domain generalization performance, and (3) animal pose tracking track. Our experimental results deliver key empirical insights, demonstrating that APTv2 serves as a valuable benchmark for animal pose estimation and tracking. It also presents new challenges and opportunities for future research. The code and dataset are released at \href{https://github.com/ViTAE-Transformer/APTv2}{https://github.com/ViTAE-Transformer/APTv2}.

The rich-club phenomenon, which provides information about the association between nodes, is a useful method to study the hierarchy structure of networks. In this work, we explore the behavior of rich-club coefficient (RCC) in scale-free networks, and find that the degree-based RCC is a power function of degree centrality with power exponent \b{eta} and the betweenness-based RCC is a linear function of betweenness centrality with slope {\theta}. The findings from the New York metro network further validate our conclusions. Moreover, we calculate the value of RCC in a BA network by deleting nodes and obtain a general expression for RCC as a function of node sequence. On this basis, the solution of RCC for centrality is also obtained, which shows that the curve of RCC is determined by the centrality distribution. In order to find out what affects \b{eta} and {\theta}, we conduct numerical simulations in scale-free networks, and observe: \b{eta} and {\gamma} (the degree distribution exponent) increase together, {\theta} increases with m (the number of new edges) and decreases to convergence as {\gamma} increases., Comment: 7pages,7 figures

Spatial L{\'{e}}vy-like flights are introduced as a way in the absorbing phase transitions to produce non-local interactions. We utilize the autoencoder, an unsupervised learning method, to predict the critical points for $(1+1)$-d directed percolation with such spatial long-range interactions. After making a global coverage of the reaction-diffusion distance and taking a series of different values for the parameter ${\beta}$ in the distribution $P(r){\sim}1/r^{\beta}$, the critical points $P_c$ that can be continuously varied are obtained. And the dynamic decay of the particle density under the critical points was counted as a way to determine the critical exponent ${\delta}$ of the survival rate. We also investigate the active behavior of the system's particles under the critical point with increasing time steps, which allows us to determine the characteristic time $t_f$ of the finite-scale systems. And the dynamic exponents $z$ are obtained using the scaling relation $t_f{\sim}L^{z}$. We find that the autoencoder can identify this characteristic evolutionary behavior of particles. Finally, we discuss the compliance of the scaling form $1/{\delta}-({\beta}-2)/{\delta}z=2$ in different ${\beta}$ intervals as well as a method to introduce a global scaling mechanism by generating a random walking step using the L{\'{e}}vy distribution.

Neural networks have shown their effectiveness in various tasks in the realm of quantum computing. However, their application in quantum error mitigation, a crucial step towards realizing practical quantum advancements, has been restricted by reliance on noise-free statistics. To tackle this critical challenge, we propose a data augmentation empowered neural model for error mitigation (DAEM). Our model does not require any prior knowledge about the specific noise type and measurement settings and can estimate noise-free statistics solely from the noisy measurement results of the target quantum process, rendering it highly suitable for practical implementation. In numerical experiments, we show the model's superior performance in mitigating various types of noise, including Markovian noise and Non-Markovian noise, compared with previous error mitigation methods. We further demonstrate its versatility by employing the model to mitigate errors in diverse types of quantum processes, including those involving large-scale quantum systems and continuous-variable quantum states. This powerful data augmentation-empowered neural model for error mitigation establishes a solid foundation for realizing more reliable and robust quantum technologies in practical applications., Comment: 10 pages, 6 figures + appendix; comments are welcome

This paper investigates the multi-agent cooperative exploration problem, which requires multiple agents to explore an unseen environment via sensory signals in a limited time. A popular approach to exploration tasks is to combine active mapping with planning. Metric maps capture the details of the spatial representation, but are with high communication traffic and may vary significantly between scenarios, resulting in inferior generalization. Topological maps are a promising alternative as they consist only of nodes and edges with abstract but essential information and are less influenced by the scene structures. However, most existing topology-based exploration tasks utilize classical methods for planning, which are time-consuming and sub-optimal due to their handcrafted design. Deep reinforcement learning (DRL) has shown great potential for learning (near) optimal policies through fast end-to-end inference. In this paper, we propose Multi-Agent Neural Topological Mapping (MANTM) to improve exploration efficiency and generalization for multi-agent exploration tasks. MANTM mainly comprises a Topological Mapper and a novel RL-based Hierarchical Topological Planner (HTP). The Topological Mapper employs a visual encoder and distance-based heuristics to construct a graph containing main nodes and their corresponding ghost nodes. The HTP leverages graph neural networks to capture correlations between agents and graph nodes in a coarse-to-fine manner for effective global goal selection. Extensive experiments conducted in a physically-realistic simulator, Habitat, demonstrate that MANTM reduces the steps by at least 26.40% over planning-based baselines and by at least 7.63% over RL-based competitors in unseen scenarios., Comment: Accepted by Robotics and Automation Letters

In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs). Our key insight is that most variables, such as gradients and optimizer states, in LLM training can employ low-precision data formats without compromising model accuracy and requiring no changes to hyper-parameters. Specifically, we propose a new FP8 automatic mixed-precision framework for training LLMs. This framework offers three levels of FP8 utilization to streamline mixed-precision and distributed parallel training for LLMs. It gradually incorporates 8-bit gradients, optimizer states, and distributed learning in an incremental manner. Experiment results show that, during the training of GPT-175B model on H100 GPU platform, our FP8 mixed-precision training framework not only achieved a remarkable 39% reduction in real memory usage but also ran 75% faster than the widely adopted BF16 framework (i.e., Megatron-LM), surpassing the speed of Nvidia Transformer Engine by 37%. This largely reduces the training costs for large foundation models. Furthermore, our FP8 mixed-precision training methodology is generic. It can be seamlessly applied to other tasks such as LLM instruction tuning and reinforcement learning with human feedback, offering savings in fine-tuning expenses. Our FP8 low-precision training framework is open-sourced at {https://github.com/Azure/MS-AMP}{aka.ms/MS.AMP}.

3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving. It remains challenging to localize the target from surroundings due to appearance variations, distractors, and the high sparsity of point clouds. To address these issues, prior Siamese and motion-centric trackers both require elaborate designs and solving multiple subtasks. In this paper, we propose BEVTrack, a simple yet effective baseline method. By estimating the target motion in Bird's-Eye View (BEV) to perform tracking, BEVTrack demonstrates surprising simplicity from various aspects, i.e., network designs, training objectives, and tracking pipeline, while achieving superior performance. Besides, to achieve accurate regression for targets with diverse attributes (e.g., sizes and motion patterns), BEVTrack constructs the likelihood function with the learned underlying distributions adapted to different targets, rather than making a fixed Laplacian or Gaussian assumption as in previous works. This provides valuable priors for tracking and thus further boosts performance. While only using a single regression loss with a plain convolutional architecture, BEVTrack achieves state-of-the-art performance on three large-scale datasets, KITTI, NuScenes, and Waymo Open Dataset while maintaining a high inference speed of about 200 FPS. The code will be released at https://github.com/xmm-prio/BEVTrack., Comment: The code will be released at https://github.com/xmm-prio/BEVTrack

Armed with quantum correlations, quantum sensors in a network have shown the potential to outclass their classical counterparts in distributed sensing tasks such as clock synchronization and reference frame alignment. On the other hand, this analysis was done for simple and idealized networks, whereas the correlation shared within a practical quantum network, captured by the notion of network states, is much more complex. Here, we prove a general bound that limits the performance of using quantum network states to estimate a global parameter, establishing the necessity of genuine multipartite entanglement for achieving a quantum advantage. The bound can also serve as an entanglement witness in networks and can be generalized to states generated by shallow circuits. Moreover, while our bound prohibits local network states from achieving the Heisenberg limit, we design a probabilistic protocol that, once successful, attains this ultimate limit of quantum metrology and preserves the privacy of involved parties. Our work establishes both the limitation and the possibility of quantum metrology within quantum networks., Comment: 5 pages, 2 figures + appendix; close to the published version

We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centroidal policy, which specifies the gait timing, base velocity, and swing foot position for the leg controller. The leg controller optimizes motor commands for the swing and stance legs according to the gait timing to track the swing foot target and base velocity commands using optimal control. Additionally, we reformulate the stance leg optimizer in the leg controller to speed up policy training by an order of magnitude. Our system combines the versatility of learning with the robustness of optimal control. By combining RL with optimal control methods, our system achieves the versatility of learning while enjoys the robustness from control methods, making it easily transferable to real robots. We show that after 20 minutes of training on a single GPU, CAJun can achieve continuous, long jumps with adaptive distances on a Go1 robot with small sim-to-real gaps. Moreover, the robot can jump across gaps with a maximum width of 70cm, which is over 40% wider than existing methods., Comment: Please visit https://yxyang.github.io/cajun/ for additional results

Heisenberg's uncertainty principle implies fundamental constraints on what properties of a quantum system can we simultaneously learn. However, it typically assumes that we probe these properties via measurements at a single point in time. In contrast, inferring causal dependencies in complex processes often requires interactive experimentation - multiple rounds of interventions where we adaptively probe the process with different inputs to observe how they affect outputs. Here we demonstrate universal uncertainty principles for general interactive measurements involving arbitrary rounds of interventions. As a case study, we show that they imply an uncertainty trade-off between measurements compatible with different causal dependencies., Comment: 7 pages (main text) + 47 pages (supplemental material), 5 figures (main text) + 17 figures (supplemental material). Accepted for publication in Physical Review Letters

Two-stage point-to-box network acts as a critical role in the recent popular 3D Siamese tracking paradigm, which first generates proposals and then predicts corresponding proposal-wise scores. However, such a network suffers from tedious hyper-parameter tuning and task misalignment, limiting the tracking performance. Towards these concerns, we propose a simple yet effective one-stage point-to-box network for point cloud-based 3D single object tracking. It synchronizes 3D proposal generation and center-ness score prediction by a parallel predictor without tedious hyper-parameters. To guide a task-aligned score ranking of proposals, a center-aware focal loss is proposed to supervise the training of the center-ness branch, which enhances the network's discriminative ability to distinguish proposals of different quality. Besides, we design a binary target classifier to identify target-relevant points. By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment. Finally, we present a novel one-stage Siamese tracker OSP2B equipped with the designed network. Extensive experiments on challenging benchmarks including KITTI and Waymo SOT Dataset show that our OSP2B achieves leading performance with a considerable real-time speed.Code will be available at https://github.com/haooozi/OSP2B., Comment: Accepted to IJCAI'23. Code will be available at https://github.com/haooozi/OSP2B

Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. The core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. As the acceleration controller warm starts policy for efficient training, the trained policy overcomes the limitation of the acceleration controller and improves the jumping stability. In addition, a low-level whole-body controller converts the body pose command from the stance controller to motor commands. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions, including omni-directional jumps at up to 50cm high, 60cm forward, and jump-turning at up to 90 degrees. Please visit our website for more results: https://sites.google.com/view/learning-to-jump., Comment: To be presented at L4DC 2023

Siamese trackers based on 3D region proposal network (RPN) have shown remarkable success with deep Hough voting. However, using a single seed point feature as the cue for voting fails to produce high-quality 3D proposals. Additionally, the equal treatment of seed points in the voting process, regardless of their significance, exacerbates this limitation. To address these challenges, we propose a novel transformer-based voting scheme to generate better proposals. Specifically, a global-local transformer (GLT) module is devised to integrate object- and patch-aware geometric priors into seed point features, resulting in robust and accurate cues for offset learning of seed points. To train the GLT module, we introduce an importance prediction branch that learns the potential importance weights of seed points as a training constraint. Incorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds. Moreover, we identify that the highest-scored proposal in the Siamese paradigm may not be the most accurate proposal, which limits tracking performance. Towards this concern, we approach the binary score prediction task as a ranking problem, and design a target-aware ranking loss and a localization-aware ranking loss to produce accurate ranking of proposals. With the ranking losses, we further present GLT-T++, an enhanced version of GLT-T. Extensive experiments on multiple benchmarks demonstrate that our GLT-T and GLT-T++ outperform state-of-the-art methods in terms of tracking accuracy while maintaining a real-time inference speed. The source code will be made available at https://github.com/haooozi/GLT-T., Comment: Need further revision

The precision of quantum metrology is widely believed to be restricted by the Heisenberg limit, corresponding to a root mean square error that is inversely proportional to the number of independent processes probed in an experiment, N. In the past, some proposals have challenged this belief, for example using non-linear interactions among the probes. However, these proposals turned out to still obey the Heisenberg limit with respect to other relevant resources, such as the total energy of the probes. Here, we present a photonic implementation of a quantum metrology protocol surpassing the Heisenberg limit by probing two groups of independent processes in a superposition of two alternative causal orders. Each process creates a phase space displacement, and our setup is able to estimate a geometric phase associated to two sets of N displacements with an error that falls quadratically with N. Our results only require a single-photon probe with an initial energy that is independent of N. Using a superposition of causal orders outperforms every setup where the displacements are probed in a definite order. Our experiment features the demonstration of indefinite causal order in a continuous-variable system, and opens up the experimental investigation of quantum metrology setups boosted by indefinite causal order.

This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) has shown promising results for solving this issue. However, it is inefficient for MARL to directly explore the (nearly) optimal policy in the large search space, which is exacerbated as the agent number increases (e.g., 10+ agents) or the environment is more complex (e.g., 3D simulator). Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a hierarchical structure to decompose the search space, where the low-level policy predicts primitive actions in the guidance of the goals derived from the high-level policy. In this paper, we propose Multi-Agent Graph-Enhanced Commander-Executor (MAGE-X), a graph-based goal-conditioned hierarchical method for multi-agent navigation tasks. MAGE-X comprises a high-level Goal Commander and a low-level Action Executor. The Goal Commander predicts the probability distribution of goals and leverages them to assign each agent the most appropriate final target. The Action Executor utilizes graph neural networks (GNN) to construct a subgraph for each agent that only contains crucial partners to improve cooperation. Additionally, the Goal Encoder in the Action Executor captures the relationship between the agent and the designated goal to encourage the agent to reach the final target. The results show that MAGE-X outperforms the state-of-the-art MARL baselines with a 100% success rate with only 3 million training steps in multi-agent particle environments (MPE) with 50 agents, and at least a 12% higher success rate and 2x higher data efficiency in a more complicated quadrotor 3D navigation task., Comment: This paper is accepted by aamas 2023

The processing of quantum information always has a cost in terms of physical resources such as energy or time. Determining the resource requirements is not only an indispensable step in the design of practical devices - the resources need to be actually provided - but may also yield fundamental constraints on the class of processes that are physically possible. Here we study how much energy is required to implement a desired unitary gate on a quantum system with a non-trivial energy spectrum. We derive a general lower bound on the energy requirement, extending the main result of Ref. [1] from finite dimensional systems to systems with unbounded Hamiltonians. Such an extension has immediate applications in quantum information processing with optical systems, and allows us to provide bounds on the energy requirement of continuous variable quantum gates, such as displacement and squeezing gates., Comment: 16 pages + appendix; published version

Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D proposals. Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning. Subsequently, a simple yet effective training strategy is designed to train the GLT module. We develop an importance prediction branch to learn the potential importance of the seed points and treat the output weights vector as a training constraint term. By incorporating the above components together, we exhibit a superior tracking method GLT-T. Extensive experiments on challenging KITTI and NuScenes benchmarks demonstrate that GLT-T achieves state-of-the-art performance in the 3D single object tracking task. Besides, further ablation studies show the advantages of the proposed global-local transformer voting scheme over the original VoteNet. Code and models will be available at https://github.com/haooozi/GLT-T., Comment: Accepted to AAAI 2023. The source code and models will be available at https://github.com/haooozi/GLT-T

Two-Ievel (qubit) clock systems are often used to perform precise measurement of time. In this work, we propose a compression protocol for $n$ identically prepared states of qubit clocks. The protocol faithfully encodes the states into $(1/2)\log n$ qubits and $(1/2)\log n$ classical bits and works even in the presence of noise. If the purity of the clock states is fixed, $(1/2)\log n$ qubits are sufficient. We also prove that this protocol requires the minimum amount of total memory among all protocols with vanishing error in the large $n$ limit., Comment: 5 pages; published version. arXiv admin note: substantial text overlap with arXiv:1703.05876

The ability to extract relevant information is critical to learning. An ingenious approach as such is the information bottleneck, an optimisation problem whose solution corresponds to a faithful and memory-efficient representation of relevant information from a large system. The advent of the age of quantum computing calls for efficient methods that work on information regarding quantum systems. Here we address this by proposing a new and general algorithm for the quantum generalisation of information bottleneck. Our algorithm excels in the speed and the definiteness of convergence compared with prior results. It also works for a much broader range of problems, including the quantum extension of deterministic information bottleneck, an important variant of the original information bottleneck problem. Notably, we discover that a quantum system can achieve strictly better performance than a classical system of the same size regarding quantum information bottleneck, providing new vision on justifying the advantage of quantum machine learning., Comment: accepted by Quantum

The semantics of the environment, such as the terrain type and property, reveals important information for legged robots to adjust their behaviors. In this work, we present a framework that learns semantics-aware locomotion skills from perception for quadrupedal robots, such that the robot can traverse through complex offroad terrains with appropriate speeds and gaits using perception information. Due to the lack of high-fidelity outdoor simulation, our framework needs to be trained directly in the real world, which brings unique challenges in data efficiency and safety. To ensure sample efficiency, we pre-train the perception model with an off-road driving dataset. To avoid the risks of real-world policy exploration, we leverage human demonstration to train a speed policy that selects a desired forward speed from camera image. For maximum traversability, we pair the speed policy with a gait selector, which selects a robust locomotion gait for each forward speed. Using only 40 minutes of human demonstration data, our framework learns to adjust the speed and gait of the robot based on perceived terrain semantics, and enables the robot to walk over 6km without failure at close-to-optimal speed.

Loading classical data into quantum registers is one of the most important primitives of quantum computing. While the complexity of preparing a generic quantum state is exponential in the number of qubits, in many practical tasks the state to prepare has a certain structure that allows for faster preparation. In this paper, we consider quantum states that can be efficiently represented by (reduced) decision diagrams, a versatile data structure for the representation and analysis of Boolean functions. We design an algorithm that utilises the structure of decision diagrams to prepare their associated quantum states. Our algorithm has a circuit complexity that is linear in the number of paths in the decision diagram. Numerical experiments show that our algorithm reduces the circuit complexity by up to 31.85% compared to the state-of-the-art algorithm, when preparing generic $n$-qubit states with different degrees of non-zero amplitudes. Additionally, for states with sparse decision diagrams, including the initial state of the quantum Byzantine agreement protocol, our algorithm reduces the number of CNOTs by 86.61% $\sim$ 99.9%., Comment: 9 pages, 6 figures; close to the published version

Animal pose estimation and tracking (APT) is a fundamental task for detecting and tracking animal keypoints from a sequence of video frames. Previous animal-related datasets focus either on animal tracking or single-frame animal pose estimation, and never on both aspects. The lack of APT datasets hinders the development and evaluation of video-based animal pose estimation and tracking methods, limiting real-world applications, e.g., understanding animal behavior in wildlife conservation. To fill this gap, we make the first step and propose APT-36K, i.e., the first large-scale benchmark for animal pose estimation and tracking. Specifically, APT-36K consists of 2,400 video clips collected and filtered from 30 animal species with 15 frames for each video, resulting in 36,000 frames in total. After manual annotation and careful double-check, high-quality keypoint and tracking annotations are provided for all the animal instances. Based on APT-36K, we benchmark several representative models on the following three tracks: (1) supervised animal pose estimation on a single frame under intra- and inter-domain transfer learning settings, (2) inter-species domain generalization test for unseen animals, and (3) animal pose estimation with animal tracking. Based on the experimental results, we gain some empirical insights and show that APT-36K provides a valuable animal pose estimation and tracking benchmark, offering new challenges and opportunities for future research. The code and dataset will be made publicly available at https://github.com/pandorgan/APT-36K., Comment: Neurips 2022 dataset and benchmark track