arXiv subjects

Yuxiang Yang

Publications and source records attributed to Yuxiang Yang.

At least 73 records · Page 4Linked to original sources

arXiv2024

Learning with Alignments: Tackling the Inter- and Intra-domain Shifts for Cross-multidomain Facial Expression Recognition

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.

cs.CV↗

arXiv2024

Seal: Advancing Speech Language Models to be Few-Shot Learners

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.

cs.CL↗

arXiv2024

Quantum-enhanced metrology with network states

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.

quant-ph↗

arXiv2024

QuERLoc: Towards Next-Generation Localization with Quantum-Enhanced Ranging

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.

cs.ET↗

arXiv2024

Quantum Ranging Enhanced TDoA Localization

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.

cs.ET↗

arXiv2024

Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptation

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.

cs.CV↗

arXiv2024

Exploiting Sequence Number Leakage: TCP Hijacking in NAT-Enabled Wi-Fi Networks

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.

cs.CR↗

arXiv2023

APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond

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}.

cs.CV↗

arXiv2023

FP8-LM: Training FP8 Large Language Models

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}.

cs.LG↗

arXiv2023

GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Loss

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.

cs.CV↗

arXiv2023

Active Neural Topological Mapping for Multi-Agent Exploration

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.

cs.RO↗

arXiv2023

CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller

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.

cs.RO↗

arXiv2023

Quantum Uncertainty Principles for Measurements with Interventions

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.

quant-ph↗

arXiv2023

OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking

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.

cs.CV↗

arXiv2023

Continuous Versatile Jumping Using Learned Action Residuals

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.

cs.RO↗

arXiv2023

Experimental super-Heisenberg quantum metrology with indefinite gate order

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.

quant-ph↗

arXiv2023

ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces

In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate that previous evolutionary algorithms which rely on mutation-based approaches, while flexible over combinatorial spaces, suffer from a curse of dimensionality in high dimensional continuous spaces both theoretically and empirically, which thus limits their scope over hybrid search spaces as well. In order to combat this curse, we propose ES-ENAS, a simple and modular joint optimization procedure combining the class of sample-efficient smoothed gradient techniques, commonly known as Evolutionary Strategies (ES), with combinatorial optimizers in a highly scalable and intuitive way, inspired by the one-shot or supernet paradigm introduced in Efficient Neural Architecture Search (ENAS). By doing so, we achieve significantly more sample efficiency, which we empirically demonstrate over synthetic benchmarks, and are further able to apply ES-ENAS for architecture search over popular RL benchmarks.

cs.LG↗

arXiv2023

Efficient algorithms for quantum information bottleneck

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.

quant-ph↗