Search

We find that there exist Majorana flat bands (MFBs) in the vortex line of superconducting (SC) Weyl semimetals which break time reversal symmetry. Since a Weyl semimetal can be regarded as Chern insulators stacked along one (z) direction, so we decompose the vortex bound states of SC Weyl semimetals into the vortex bound states of SC Chern insulators labelled by kz. After calculating the topological phase diagram of the SC Chern insulators both analytically and numerically, we can explain the appearance of MFBs and determine the exact boundaries of them in SC Weyl semimetals. What's more, tuning the chemical potential or the pairing strength can result in the MFBs along the whole kz axis. Based on the above understanding, we propose a kz-dependent Z2 Chern-Simons invariant to characterize the MFBs. Finally, if we further consider an attractive Hubbard interaction, the aforementioned SC Weyl semimetal and MFBs can be realized under appropriate parameters., Comment: 12 pages, 4+2 figures

We establish a duality between a pair of mirabolic quantum groups, i.e., the mirabolic counterpart of quantum Howe duality.

Autonomous driving technology is rapidly evolving and becoming a pivotal element of modern automation systems. Effective decision-making and planning are essential to ensuring autonomous vehicles operate safely and efficiently in complex environments. This paper introduces a decision-making and planning framework for autonomous vehicles, leveraging dynamic programming (DP) for global path planning and quadratic programming (QP) for local trajectory optimization. The proposed approach utilizes S-T graphs to achieve both dynamic and static obstacle avoidance. A comprehensive vehicle dynamics model supports the control system, enabling precise path tracking and obstacle handling. Simulation studies are conducted to evaluate the system's performance in a variety of scenarios, including global path planning, static obstacle avoidance, and dynamic obstacle avoidance involving pedestrian interactions. The results confirm the effectiveness and robustness of the proposed decision-making and planning algorithms in navigating complex environments, demonstrating the feasibility of this approach for autonomous driving applications.

Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. This becomes especially critical in reasoning-related tasks with sandbox checkers, such as math or code, where the goal is to generate correct solutions to specific problems with higher probability. In this work, we introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling, a simple yet highly effective method to efficiently find good responses. Our empirical findings show that FIRE sampling enhances inference-time generation quality and also benefits training in the alignment stage. Furthermore, we explore how FIRE sampling improves performance by promoting diversity and analyze the impact of employing FIRE at different positions within a response.

Trace distance and infidelity (induced by square root fidelity), as basic measures of the closeness of quantum states, are commonly used in quantum state discrimination, certification, and tomography. However, the sample complexity for their estimation still remains open. In this paper, we solve this problem for pure states. We present a quantum algorithm that estimates the trace distance and square root fidelity between pure states to within additive error $\varepsilon$, given sample access to their identical copies. Our algorithm achieves the optimal sample complexity $\Theta(1/\varepsilon^2)$, improving the long-standing folklore $O(1/\varepsilon^4)$. Our algorithm is composed of a samplized phase estimation of the product of two Householder reflections. Notably, an improved (multi-)samplizer for pure states is used as an algorithmic tool in our construction, through which any quantum query algorithm using $Q$ queries to the reflection operator about a pure state $|\psi\rangle$ can be converted to a $\delta$-close (in the diamond norm) quantum sample algorithm using $\Theta(Q^2/\delta)$ samples of $|\psi\rangle$. This samplizer for pure states is shown to be optimal., Comment: 24 pages, 3 figures, 1 table, 1 algorithm

Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these challenges, we present Perception Compressor, a training-free prompt compression framework. It includes a perception retriever that leverages guiding questions and instruction to retrieve the most relevant demonstrations, a dual-slope ratio allocator to dynamically allocate compression ratios and open-book ratios, and a semi-guided iterative compression that retains key information at the token level while removing tokens that distract the LLM. We conduct extensive experiments on long context benchmarks, i.e., NaturalQuestions, LongBench, and MuSiQue. Experiment results show that Perception Compressor outperforms existing methods by a large margin, achieving state-of-the-art performance., Comment: Accepted at NAACL 2025 Findings

Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by \textbf{$5\%$} on the DESED and MAESTRO Real datasets. Code is available at https://github.com/Visitor-W/MTDA., Comment: Submit to Icassp2025

Diffusion tensor imaging (DTI) holds significant importance in clinical diagnosis and neuroscience research. However, conventional model-based fitting methods often suffer from sensitivity to noise, leading to decreased accuracy in estimating DTI parameters. While traditional data-driven deep learning methods have shown potential in terms of accuracy and efficiency, their limited generalization to out-of-training-distribution data impedes their broader application due to the diverse scan protocols used across centers, scanners, and studies. This work aims to tackle these challenges and promote the use of DTI by introducing a data-driven optimization-based method termed DoDTI. DoDTI combines the weighted linear least squares fitting algorithm and regularization by denoising technique. The former fits DW images from diverse acquisition settings into diffusion tensor field, while the latter applies a deep learning-based denoiser to regularize the diffusion tensor field instead of the DW images, which is free from the limitation of fixed-channel assignment of the network. The optimization object is solved using the alternating direction method of multipliers and then unrolled to construct a deep neural network, leveraging a data-driven strategy to learn network parameters. Extensive validation experiments are conducted utilizing both internally simulated datasets and externally obtained in-vivo datasets. The results, encompassing both qualitative and quantitative analyses, showcase that the proposed method attains state-of-the-art performance in DTI parameter estimation. Notably, it demonstrates superior generalization, accuracy, and efficiency, rendering it highly reliable for widespread application in the field.

We present flow matching for reaction coordinates (FMRC), a novel deep learning algorithm designed to identify optimal reaction coordinates (RC) in biomolecular reversible dynamics. FMRC is based on the mathematical principles of lumpability and decomposability, which we reformulate into a conditional probability framework for efficient data-driven optimization using deep generative models. While FMRC does not explicitly learn the well-established transfer operator or its eigenfunctions, it can effectively encode the dynamics of leading eigenfunctions of the system transfer operator into its low-dimensional RC space. We further quantitatively compare its performance with several state-of-the-art algorithms by evaluating the quality of Markov state models (MSM) constructed in their respective RC spaces, demonstrating the superiority of FMRC in three increasingly complex biomolecular systems. In addition, we successfully demonstrated the efficacy of FMRC for bias deposition in the enhanced sampling of a simple model system. Finally, we discuss its potential applications in downstream applications such as enhanced sampling methods and MSM construction., Comment: For Supporting Information, please see https://pubs.acs.org/doi/full/10.1021/acs.jctc.4c01139

Reaction coordinates (RCs) are low-dimensional representations of complex dynamical systems that capture their long-term dynamics. In this work, we focus on the criteria of lumpability and decomposability, previously established for assessing RCs, and propose a new flow matching approach for the analysis and optimization of reaction coordinates based on these criteria. This method effectively utilizes data to quantitatively determine whether a given RC satisfies these criteria and enables end-to-end optimization of the reaction coordinate mapping model. Furthermore, we provide a theoretical analysis of the relationship between the loss function used in our approach and the operator error induced by dimension reduction.

Quantum recursive programming has been recently introduced for describing sophisticated and complicated quantum algorithms in a compact and elegant way. However, implementation of quantum recursion involves intricate interplay between quantum control flows and recursive procedure calls. In this paper, we aim at resolving this fundamental challenge and develop a series of techniques to efficiently implement quantum recursive programs. Our main contributions include: 1. We propose a notion of quantum register machine, the first purely quantum architecture (including an instruction set) that supports quantum control flows and recursive procedure calls at the same time. 2. Based on quantum register machine, we describe the first comprehensive implementation process of quantum recursive programs, including the compilation, the partial evaluation of quantum control flows, and the execution on the quantum register machine. 3. As a bonus, our efficient implementation of quantum recursive programs also offers automatic parallelisation of quantum algorithms. For implementing certain quantum algorithmic subroutine, like the widely used quantum multiplexor, we can even obtain exponential parallel speed-up (over the straightforward implementation) from this automatic parallelisation. This demonstrates that quantum recursive programming can be win-win for both modularity of programs and efficiency of their implementation., Comment: Minor revision. 72 pages, 26 figures

Online advertising is a primary source of income for e-commerce platforms. In the current advertising pattern, the oriented targets are the online store owners who are willing to pay extra fees to enhance the position of their stores. On the other hand, brand suppliers are also desirable to advertise their products in stores to boost brand sales. However, the currently used advertising mode cannot satisfy the demand of both stores and brand suppliers simultaneously. To address this, we innovatively propose a joint advertising model termed Joint Auction, allowing brand suppliers and stores to collaboratively bid for advertising slots, catering to both their needs. However, conventional advertising auction mechanisms are not suitable for this novel scenario. In this paper, we propose JRegNet, a neural network architecture for the optimal joint auction design, to generate mechanisms that can achieve the optimal revenue and guarantee near dominant strategy incentive compatibility and individual rationality. Finally, multiple experiments are conducted on synthetic and real data to demonstrate that our proposed joint auction significantly improves platform revenue compared to the known baselines.

In the Sound Event Localization and Detection (SELD) task, Transformer-based models have demonstrated impressive capabilities. However, the quadratic complexity of the Transformer's self-attention mechanism results in computational inefficiencies. In this paper, we propose a network architecture for SELD called SELD-Mamba, which utilizes Mamba, a selective state-space model. We adopt the Event-Independent Network V2 (EINV2) as the foundational framework and replace its Conformer blocks with bidirectional Mamba blocks to capture a broader range of contextual information while maintaining computational efficiency. Additionally, we implement a two-stage training method, with the first stage focusing on Sound Event Detection (SED) and Direction of Arrival (DoA) estimation losses, and the second stage reintroducing the Source Distance Estimation (SDE) loss. Our experimental results on the 2024 DCASE Challenge Task3 dataset demonstrate the effectiveness of the selective state-space model in SELD and highlight the benefits of the two-stage training approach in enhancing SELD performance.

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate these limitations, we introduce CodexGraph, a system that integrates LLM agents with graph database interfaces extracted from code repositories. By leveraging the structural properties of graph databases and the flexibility of the graph query language, CodexGraph enables the LLM agent to construct and execute queries, allowing for precise, code structure-aware context retrieval and code navigation. We assess CodexGraph using three benchmarks: CrossCodeEval, SWE-bench, and EvoCodeBench. Additionally, we develop five real-world coding applications. With a unified graph database schema, CodexGraph demonstrates competitive performance and potential in both academic and real-world environments, showcasing its versatility and efficacy in software engineering. Our application demo: https://github.com/modelscope/modelscope-agent/tree/master/apps/codexgraph_agent., Comment: work in progress

Since Harrow, Hassidim, and Lloyd (2009) showed that a system of linear equations with $N$ variables and condition number $\kappa$ can be solved on a quantum computer in $\operatorname{poly}(\log(N), \kappa)$ time, exponentially faster than any classical algorithms, its improvements and applications have been extensively investigated. The state-of-the-art quantum algorithm for this problem is due to Costa, An, Sanders, Su, Babbush, and Berry (2022), with optimal query complexity $\Theta(\kappa)$. An important question left is whether parallelism can bring further optimization. In this paper, we study the limitation of parallel quantum computing on this problem. We show that any quantum algorithm for solving systems of linear equations with time complexity $\operatorname{poly}(\log(N), \kappa)$ has a lower bound of $\Omega(\kappa)$ on the depth of queries, which is tight up to a constant factor., Comment: Minor corrections to references in [v1]. 22 pages, 1 table. Close to the official version

In computed tomography (CT), the presence of metallic implants in patients often leads to disruptive artifacts in the reconstructed images, hindering accurate diagnosis. Recently, a large amount of supervised deep learning-based approaches have been proposed for metal artifact reduction (MAR). However, these methods neglect the influence of initial training weights. In this paper, we have discovered that the uncertainty image computed from the restoration result of initial training weights can effectively highlight high-frequency regions, including metal artifacts. This observation can be leveraged to assist the MAR network in removing metal artifacts. Therefore, we propose an uncertainty constraint (UC) loss that utilizes the uncertainty image as an adaptive weight to guide the MAR network to focus on the metal artifact region, leading to improved restoration. The proposed UC loss is designed to be a plug-and-play method, compatible with any MAR framework, and easily adoptable. To validate the effectiveness of the UC loss, we conduct extensive experiments on the public available Deeplesion and CLINIC-metal dataset. Experimental results demonstrate that the UC loss further optimizes the network training process and significantly improves the removal of metal artifacts.

Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to generate multi-scale spectral and spatial features. The TF-Convolution Module is employed to provide multi-scale temporal features. We incorporated MFF into EINV2 and term the proposed method as MFF-EINV2. Experimental results in 2022 and 2023 DCASE challenge task3 datasets show the effectiveness of our MFF-EINV2, which achieves state-of-the-art (SOTA) performance compared to published methods., Comment: Accepted by Interspeech 2024

Micro-expressions are nonverbal facial expressions that reveal the covert emotions of individuals, making the micro-expression recognition task receive widespread attention. However, the micro-expression recognition task is challenging due to the subtle facial motion and brevity in duration. Many 2D image-based methods have been developed in recent years to recognize MEs effectively, but, these approaches are restricted by facial texture information and are susceptible to environmental factors, such as lighting. Conversely, depth information can effectively represent motion information related to facial structure changes and is not affected by lighting. Motion information derived from facial structures can describe motion features that pixel textures cannot delineate. We proposed a network for micro-expression recognition based on facial depth information, and our experiments have demonstrated the crucial role of depth maps in the micro-expression recognition task. Initially, we transform the depth map into a point cloud and obtain the motion information for each point by aligning the initiating frame with the apex frame and performing a differential operation. Subsequently, we adjusted all point cloud motion feature input dimensions and used them as inputs for multiple point cloud networks to assess the efficacy of this representation. PointNet++ was chosen as the ultimate outcome for micro-expression recognition due to its superior performance. Our experiments show that our proposed method significantly outperforms the existing deep learning methods, including the baseline, on the $CAS(ME)^3$ dataset, which includes depth information.

Recently, Transformer-based models for long sequence time series forecasting have demonstrated promising results. The self-attention mechanism as the core component of these Transformer-based models exhibits great potential in capturing various dependencies among data points. Despite these advancements, it has been a subject of concern to improve the efficiency of the self-attention mechanism. Unfortunately, current specific optimization methods are facing the challenges in applicability and scalability for the future design of long sequence time series forecasting models. Hence, in this article, we propose a novel architectural framework that enhances Transformer-based models through the integration of Surrogate Attention Blocks (SAB) and Surrogate Feed-Forward Neural Network Blocks (SFB). The framework reduces both time and space complexity by the replacement of the self-attention and feed-forward layers with SAB and SFB while maintaining their expressive power and architectural advantages. The equivalence of this substitution is fully demonstrated. The extensive experiments on 10 Transformer-based models across five distinct time series tasks demonstrate an average performance improvement of 12.4%, alongside 61.3% reduction in parameter counts.

Multi-agent reinforcement learning (MARL) algorithms often struggle to find strategies close to Pareto optimal Nash Equilibrium, owing largely to the lack of efficient exploration. The problem is exacerbated in sparse-reward settings, caused by the larger variance exhibited in policy learning. This paper introduces MESA, a novel meta-exploration method for cooperative multi-agent learning. It learns to explore by first identifying the agents' high-rewarding joint state-action subspace from training tasks and then learning a set of diverse exploration policies to "cover" the subspace. These trained exploration policies can be integrated with any off-policy MARL algorithm for test-time tasks. We first showcase MESA's advantage in a multi-step matrix game. Furthermore, experiments show that with learned exploration policies, MESA achieves significantly better performance in sparse-reward tasks in several multi-agent particle environments and multi-agent MuJoCo environments, and exhibits the ability to generalize to more challenging tasks at test time., Comment: Accepted to AAMAS 2024. 15 pages

Matrix geometric means between two positive definite matrices can be defined equivalently from distinct perspectives - as solutions to certain nonlinear systems of equations, as points along geodesics in Riemannian geometry, and as solutions to certain optimisation problems. This diversity already suggests the potential for varied applications, as well as acting as a bridge between different domains. Here we devise new quantum subroutines to efficiently prepare quantum unitary operators that embed the standard matrix geometric mean and its generalisations called the weighted matrix geometric mean. This enables the construction of solutions to the algebraic Riccati equation, which is an important class of nonlinear systems of equations that appears in machine learning, optimal control, estimation, and filtering. Using these subroutines, we present a new class of quantum learning algorithms called quantum geometric mean metric learning. This has applications in efficiently finding the best distance measure and solving classification problems in the weakly supervised limit and for anomaly detection, for both classical and quantum problems. We also show how our method can be generalised to a particular p^th-order system of nonlinear equations. These quantum subroutines for matrix geometric means are also useful in other areas of quantum information. For example, we show how to use them in the estimation of geometric Renyi relative entropies and the Uhlmann fidelity by means of the Fuchs-Caves observable. In particular, our quantum algorithms for estimating the Uhlmann and Matsumoto fidelities have optimal dependence on the precision. Finally, we provide a BQP-complete problem based on matrix geometric means that can be solved by our subroutines, thus characterising their computational capability.

Atomicity is a ubiquitous assumption in distributed computing, under which actions are indivisible and appear sequential. In classical computing, this assumption has several theoretical and practical guarantees. In quantum computing, although atomicity is still commonly assumed, it has not been seriously studied, and a rigorous basis for it is missing. Classical results on atomicity do not directly carry over to distributed quantum computing, due to new challenges caused by quantum entanglement and the measurement problem from the underlying quantum mechanics. In this paper, we initiate the study of atomicity in distributed quantum computing. A formal model of (non-atomic) distributed quantum system is established. Based on the Dijkstra-Lamport condition, the system dynamics and observable dynamics of a distributed quantum system are defined, which correspond to the quantum state of and classically observable events in the system, respectively. Within this framework, we prove that local actions can be regarded as if they were atomic, up to the observable dynamics of the system., Comment: 36 pages, 5 figures

Vision-Language Models (VLMs) are a significant technique for Artificial General Intelligence (AGI). With the fast growth of AGI, the security problem become one of the most important challenges for VLMs. In this paper, through extensive experiments, we demonstrate the vulnerability of the conventional adaptation methods for VLMs, which may bring significant security risks. In addition, as the size of the VLMs increases, performing conventional adversarial adaptation techniques on VLMs results in high computational costs. To solve these problems, we propose a parameter-efficient \underline{Adv}ersarial adaptation method named \underline{AdvLoRA} by \underline{Lo}w-\underline{R}ank \underline{A}daptation. At first, we investigate and reveal the intrinsic low-rank property during the adversarial adaptation for VLMs. Different from LoRA, we improve the efficiency and robustness of adversarial adaptation by designing a novel reparameterizing method based on parameter clustering and parameter alignment. In addition, an adaptive parameter update strategy is proposed to further improve the robustness. By these settings, our proposed AdvLoRA alleviates the model security and high resource waste problems. Extensive experiments demonstrate the effectiveness and efficiency of the AdvLoRA.

Ultrasound (US) has been widely used in daily clinical practice for screening internal organs and guiding interventions. However, due to the acoustic shadow cast by the subcutaneous rib cage, the US examination for thoracic application is still challenging. To fully cover and reconstruct the region of interest in US for diagnosis, an intercostal scanning path is necessary. To tackle this challenge, we present a reinforcement learning (RL) approach for planning scanning paths between ribs to monitor changes in lesions on internal organs, such as the liver and heart, which are covered by rib cages. Structured anatomical information of the human skeleton is crucial for planning these intercostal paths. To obtain such anatomical insight, an RL agent is trained in a virtual environment constructed using computational tomography (CT) templates with randomly initialized tumors of various shapes and locations. In addition, task-specific state representation and reward functions are introduced to ensure the convergence of the training process while minimizing the effects of acoustic attenuation and shadows during scanning. To validate the effectiveness of the proposed approach, experiments have been carried out on unseen CTs with randomly defined single or multiple scanning targets. The results demonstrate the efficiency of the proposed RL framework in planning non-shadowed US scanning trajectories in areas with limited acoustic access.

We commence by constructing the mirabolic quantum Schur algebra, utilizing the convolution algebra defined on the variety of triples of two $n$-step partial flags and a vector. Subsequently, we employ a stabilization procedure to derive the mirabolic quantum $\mathfrak{gl}_n$. Then we present the geometric approach of the mirabolic Schur-Weyl duality of type $A$.

Recursive techniques have recently been introduced into quantum programming so that a variety of large quantum circuits and algorithms can be elegantly and economically programmed. In this paper, we present a proof system for formal verification of the correctness of recursively defined quantum circuits. The soundness and (relative) completeness of the proof system are established. To demonstrating its effectiveness, a series of application examples of the proof system are given, including (multi-qubit) controlled gates, a quantum circuit generating (multi-qubit) GHZ (Greenberger-Horne-Zeilinger) states, recursive definition of quantum Fourier transform, quantum state preparation, and quantum random-access memories (QRAM).

We study the power of local test for bipartite quantum states. Our central result is that, for properties of bipartite pure states, unitary invariance on one part implies an optimal (over all global testers) local tester acting only on the other part. This suggests a canonical local tester for entanglement spectra (i.e., Schmidt coefficients), and reveals that purified samples offer no advantage in property testing of mixed states. As applications, we show new sample lower bounds, e.g.: - The first general lower bound $\Omega(r/\epsilon^2)$ for testing whether the Schmidt rank of a bipartite state is at most $r$ or $\epsilon$-far, settling an open question raised in Montanaro and de Wolf (ToC 2016). - A lower bound $\Omega((\sqrt n+\sqrt r)\cdot\sqrt r/\epsilon^2)$ for testing whether an $n$-partite state is a matrix product state of bond dimension $r$ or $\epsilon$-far, improving the prior lower bound $\Omega(\sqrt n/\epsilon^2)$ by Soleimanifar and Wright (SODA 2022) and $\Omega(\sqrt r)$ by Aaronson et al. (ITCS 2024). Further, when perfect completeness is required, we provide a matching lower bound $\Omega(r^2/\epsilon^2)$ with respect to $r$ and $\epsilon$. - A matching lower bound $\Omega(d/\epsilon^2)$ for testing whether a $d$-dimensional bipartite state is maximally entangled or $\epsilon$-far, showing that the algorithm of O'Donnell and Wright (STOC 2015) is optimal for this task. Beyond sample complexity, we also contribute new query lower bounds: - A query lower bound $\tilde\Omega(\sqrt{d/\Delta})$ for the $d$-dimensional entanglement entropy problem with gap $\Delta$, improving the prior best $\Omega(\sqrt[4]{d})$ by She and Yuen (ITCS 2023) and $\tilde\Omega(1/\sqrt\Delta)$ by Wang and Zhang (2023) and Weggemans (2024). Further, our central result can be extended when the tested state is mixed: one-way LOCC is sufficient to realize the optimal tester., Comment: 51 pages. Compared to [v1], we (i) extended testers with parameterized completeness and soundness, (ii) added new lower bounds for testing the bond dimension of matrix product states (MPS), and (iii) improved the lower bounds for testing Schmidt rank

Camouflaged vision perception is an important vision task with numerous practical applications. Due to the expensive collection and labeling costs, this community struggles with a major bottleneck that the species category of its datasets is limited to a small number of object species. However, the existing camouflaged generation methods require specifying the background manually, thus failing to extend the camouflaged sample diversity in a low-cost manner. In this paper, we propose a Latent Background Knowledge Retrieval-Augmented Diffusion (LAKE-RED) for camouflaged image generation. To our knowledge, our contributions mainly include: (1) For the first time, we propose a camouflaged generation paradigm that does not need to receive any background inputs. (2) Our LAKE-RED is the first knowledge retrieval-augmented method with interpretability for camouflaged generation, in which we propose an idea that knowledge retrieval and reasoning enhancement are separated explicitly, to alleviate the task-specific challenges. Moreover, our method is not restricted to specific foreground targets or backgrounds, offering a potential for extending camouflaged vision perception to more diverse domains. (3) Experimental results demonstrate that our method outperforms the existing approaches, generating more realistic camouflage images., Comment: Accepted by CVPR 2024, Fig.2 and Equation 4 revised

Entropy is a measure of the randomness of a system. Estimating the entropy of a quantum state is a basic problem in quantum information. In this paper, we introduce a time-efficient quantum approach to estimating the von Neumann entropy $S(\rho)$ and R\'enyi entropy $S_\alpha(\rho)$ of an $N$-dimensional quantum state $\rho$, given access to independent samples of $\rho$. Specifically, we provide the following: 1. A quantum estimator for $S(\rho)$ with time complexity $\tilde O(N^2)$, improving the prior best time complexity $\tilde O(N^6)$ by Acharya, Issa, Shende, and Wagner (2020) and Bavarian, Mehraba, and Wright (2016). 2. A quantum estimator for $S_\alpha(\rho)$ with time complexity $\tilde O(N^{4/\alpha-2})$ for $0<\alpha<1$ and $\tilde O(N^{4-2/\alpha})$ for $\alpha>1$, improving the prior best time complexity $\tilde O(N^{6/\alpha})$ for $0<\alpha<1$ and $\tilde O(N^6)$ for $\alpha>1$ by Acharya, Issa, Shende, and Wagner (2020), though at a cost of a slightly larger sample complexity. Moreover, these estimators are naturally extensible to the low-rank case. We also provide a sample lower bound for estimating $S_{\alpha}(\rho)$. Technically, our method is quite different from the previous ones that are based on weak Schur sampling and Young diagrams. At the heart of our construction, is a novel tool called samplizer, which can "samplize" a quantum query algorithm to a quantum algorithm with similar behavior using only samples of quantum states; this suggests a unified framework for estimating quantum entropies. Specifically, when a quantum oracle $U$ block-encodes a mixed quantum state $\rho$, any quantum query algorithm using $Q$ queries to $U$ can be samplized to a $\delta$-close (in the diamond norm) quantum algorithm using $\tilde\Theta(Q^2/\delta)$ samples of $\rho$. Moreover, this samplization is proven to be optimal, up to a polylogarithmic factor., Comment: 54 pages, 1 table, 13 algorithms, 4 figures. Minor modification on the definition of samplizer

Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named full-frequency dynamic convolution (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability., Comment: Accepted by ICPR2024

Human Pose Estimation (HPE) plays a crucial role in computer vision applications. However, it is difficult to deploy state-of-the-art models on resouce-limited devices due to the high computational costs of the networks. In this work, a binary human pose estimator named BiHRNet(Binary HRNet) is proposed, whose weights and activations are expressed as $\pm$1. BiHRNet retains the keypoint extraction ability of HRNet, while using fewer computing resources by adapting binary neural network (BNN). In order to reduce the accuracy drop caused by network binarization, two categories of techniques are proposed in this work. For optimizing the training process for binary pose estimator, we propose a new loss function combining KL divergence loss with AWing loss, which makes the binary network obtain more comprehensive output distribution from its real-valued counterpart to reduce information loss caused by binarization. For designing more binarization-friendly structures, we propose a new information reconstruction bottleneck called IR Bottleneck to retain more information in the initial stage of the network. In addition, we also propose a multi-scale basic block called MS-Block for information retention. Our work has less computation cost with few precision drop. Experimental results demonstrate that BiHRNet achieves a PCKh of 87.9 on the MPII dataset, which outperforms all binary pose estimation networks. On the challenging of COCO dataset, the proposed method enables the binary neural network to achieve 70.8 mAP, which is better than most tested lightweight full-precision networks., Comment: 12 pages, 6 figures

We introduce a novel scheme of quantum recursive programming, in which large unitary transformations, i.e. quantum gates, can be recursively defined using quantum case statements, which are quantum counterparts of conditionals and case statements extensively used in classical programming. A simple programming language for supporting this kind of quantum recursion is defined, and its semantics is formally described. A series of examples are presented to show that some quantum algorithms can be elegantly written as quantum recursive programs.

How humans and machines make sense of current inputs for relation reasoning and question-answering while putting the perceived information into context of our past memories, has been a challenging conundrum in cognitive science and artificial intelligence. Inspired by human brain's memory system and cognitive architectures, we propose a PMI framework that consists of perception, memory and inference components. Notably, the memory module comprises working and long-term memory, with the latter endowed with a higher-order structure to retain extensive and complex relational knowledge and experience. Through a differentiable competitive write access, current perceptions update working memory, which is later merged with long-term memory via outer product associations, reducing information conflicts and averting memory overflow. In the inference module, relevant information is retrieved from two separate memory origins and associatively integrated to attain a more comprehensive and precise interpretation of current perceptions. We exploratively apply our PMI to improve prevailing Transformers and CNN models on question-answering tasks like bAbI-20k and Sort-of-CLEVR datasets, as well as detecting equilateral triangles, language modeling and image classification tasks, and in each case, our PMI enhancements consistently outshine their original counterparts significantly. Visualization analyses reveal that relational memory consolidation, along with the interaction and integration of information from diverse memory sources, substantially contributes to the model effectiveness on inference tasks.

Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there is a growing trend to build agent framework that equips LLMs, such as ChatGPT, with tool-use abilities to connect with massive external APIs. In this work, we introduce ModelScope-Agent, a general and customizable agent framework for real-world applications, based on open-source LLMs as controllers. It provides a user-friendly system library, with customizable engine design to support model training on multiple open-source LLMs, while also enabling seamless integration with both model APIs and common APIs in a unified way. To equip the LLMs with tool-use abilities, a comprehensive framework has been proposed spanning over tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation for practical real-world applications. Finally, we showcase ModelScopeGPT, a real-world intelligent assistant of ModelScope Community based on the ModelScope-Agent framework, which is able to connect open-source LLMs with more than 1000 public AI models and localized community knowledge in ModelScope. The ModelScope-Agent library\footnote{https://github.com/modelscope/modelscope-agent} and online demo\footnote{https://modelscope.cn/studios/damo/ModelScopeGPT/summary} are now publicly available.

The polynomial method by Beals, Buhrman, Cleve, Mosca, and de Wolf (FOCS 1998) and the adversary method by Ambainis (STOC 2000) have been shown to be powerful in proving quantum query lower bounds for a wide variety of problems. In this paper, we propose an arguably new method for proving quantum query lower bounds by a quantum sample-to-query lifting theorem, which is from an information theory perspective. Using this method, we obtain the following new results: 1. A quadratic relation between quantum sample and query complexities regarding quantum property testing, which is optimal and saturated by quantum state discrimination. 2. A matching lower bound $\widetilde \Omega(\beta)$ for quantum Gibbs sampling at inverse temperature $\beta$, showing that the quantum Gibbs sampler by Gily\'en, Su, Low, and Wiebe (STOC 2019) is optimal. 3. A new lower bound $\widetilde \Omega(1/\sqrt{\Delta})$ for the entanglement entropy problem with gap $\Delta$, which was recently studied by She and Yuen (ITCS 2023). 4. A series of quantum query lower bounds for matrix spectrum testing, based on the sample lower bounds for quantum state spectrum testing by O'Donnell and Wright (STOC 2015). In addition, we also provide unified proofs for some known lower bounds that have been proven previously via different techniques, including those for phase/amplitude estimation and Hamiltonian simulation., Comment: 43 pages, 3 figures. An error was found in [v1, Corollary 2.8] and it is corrected to [v2, Lemma 2.8], with consequent modifications in Lemma 2.16 and Lemma 2.19

Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.

In this paper, we explore the discrete time sparse feedback control for a linear invariant system, where the proposed optimal feedback controller enjoys input sparsity by using a dynamic linear compensator, i.e., the components of feedback control signal having the smallest possible nonzero values. The resulting augmented dynamics ensures closed-loop stability, which infers sparse feedback controller from open-loop solution to closed-loop realization. In particular, we show that the implemented sparse feedback (closed-loop) control solution is equivalent to the original sparse (open-loop) control solution under a specified basis. We then extend the dynamic compensator to a feedforward tracking control problem. Finally, numerical examples demonstrate the effectiveness of proposed control approach., Comment: 18 pages, 5 figures