L. Wang

L. Wang, A. S. Morse

A time-invariant, linear, distributed observer is described for estimating the state of an $m>0$ channel, $n$-dimensional continuous-time linear system of the form $ \dot{x} = Ax,\ y_i = C_i x,\ i \in \{1,2,\cdots, m\}$. The state $x$ is simultaneously estimated by $m$ agents assuming each agent $i$ senses $y_i$ and receives the state $z_j$ of each of its neighbors' estimators. Neighbor relations are characterized by a constant directed graph $\mathbb{N}$ whose vertices correspond to agents and whose arcs depict neighbor relations. The overall distributed observer consists of $m$ linear estimators, one for each agent; $m-1$ of the estimators are of dimension $n$ and one estimator is of dimension $n+m-1$. Using results from classical decentralized control theory, it is shown that subject to the assumptions that (i) none of the $C_i$ are zero, (ii) the neighbor graph $\mathbb{N}$ is strongly connected, (iii) the system whose state is to be estimated is jointly observable, and nothing more, it is possible to freely assign the spectrum of the overall distributed observer.

MiroMind Team, S. Bai, L. Bing et al.

We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.

L. Wang, J. Liu, A. S. Morse et al.

A discrete-time modulus consensus model is considered in which the interaction among a family of networked agents is described by a time-dependent gain graph whose vertices correspond to agents and whose arcs are assigned complex numbers from a cyclic group. Limiting behavior of the model is studied using a graphical approach. It is shown that, under appropriate connectedness, a certain type of clustering will be reached exponentially fast for almost all initial conditions if and only if the sequence of gain graphs is "repeatedly jointly structurally balanced" corresponding to that type of clustering, where the number of clusters is at most the order of a cyclic group. It is also shown that the model will reach a consensus asymptotically at zero if the sequence of gain graphs is repeatedly jointly strongly connected and structurally unbalanced. In the special case when the cyclic group is of order two, the model simplifies to the so-called Altafini model whose gain graph is simply a signed graph.

X. Li, X. Zhang, X. Yi et al.

Medical data mainly includes various types of biomedical signals and medical images, which can be used by professional doctors to make judgments on patients' health conditions. However, the interpretation of medical data requires a lot of human cost and there may be misjudgments, so many scholars use neural networks and deep learning to classify and study medical data, which can improve the efficiency and accuracy of doctors and detect diseases early for early diagnosis, etc. Therefore, it has a wide range of application prospects. However, traditional neural networks have disadvantages such as high energy consumption and high latency (slow computation speed). This paper presents recent research on signal classification and disease diagnosis based on a third-generation neural network, the spiking neuron network, using medical data including EEG signals, ECG signals, EMG signals and MRI images. The advantages and disadvantages of pulsed neural networks compared with traditional networks are summarized and its development orientation in the future is prospected.

L. Xiao, J. Xu, D. Zhao et al.

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transformation (specifically, image rotation) and ask the learner to predict the properties of the transformation. However, the obtained feature representation may contain a large amount of irrelevant information with respect to the main task. To provide further guidance, we force the feature representation of the augmented data to be consistent with that of the original data. Intuitively, the consistency introduces additional constraints to representation learning, therefore, the learned representation is more likely to focus on the right information about the main task. Our experimental results validate the proposed method and demonstrate state-of-the-art performance on classical domain adaptation benchmarks. Code is available at https://github.com/Jiaolong/ss-da-consistency.

C. Z. Cao, J. Z. Han, M. Xiong et al.

Generating and preserving metrologically useful quantum states is a central challenge in quantum-enhanced atomic magnetometry. In multilevel atoms operated in the low-field regime, the nonlinear Zeeman (NLZ) effect is both a resource and a limitation. It nonlinearly redistributes internal spin fluctuations to generate spin-squeezed states within a single atomic qudit, yet under fixed readout it distorts the measurement-relevant quadrature and limits the accessible metrological gain. This challenge is compounded by the time dependence of both the squeezing axis and the effective nonlinear action. Here we show that physics-informed reinforcement learning can transform NLZ dynamics from a source of readout degradation into a sustained metrological resource. Using only experimentally accessible low-order spin moments, a trained agent identifies, in the $f=21/2$ manifold of $^{161}\mathrm{Dy}$, a unified control policy that rapidly prepares strongly squeezed internal states and stabilizes more than $4\,\mathrm{dB}$ of fixed-axis spin squeezing under always-on NLZ evolution. Including state-preparation overhead, the learned protocol yields a single-atom magnetic sensitivity of $13.9\,\mathrm{pT}/\sqrt{\mathrm{Hz}}$, corresponding to an advantage of approximately $3\,\mathrm{dB}$ beyond the standard quantum limit. Our results establish learning-based control as a practical route for converting unavoidable intrinsic nonlinear dynamics in multilevel quantum sensors into operational metrological advantage.

J. Guo, L. Wang, F. Li et al.

In order to achieve reliable communication with a high data rate of massive multiple-input multiple-output (MIMO) systems in frequency division duplex (FDD) mode, the estimated channel state information (CSI) at the receiver needs to be fed back to the transmitter. However, the feedback overhead becomes exorbitant with the increasing number of antennas. In this paper, a two stages low rank (TSLR) CSI feedback scheme for millimeter wave (mmWave) massive MIMO systems is proposed to reduce the feedback overhead based on model-driven deep learning. Besides, we design a deep iterative neural network, named FISTA-Net, by unfolding the fast iterative shrinkage thresholding algorithm (FISTA) to achieve more efficient CSI feedback. Moreover, a shrinkage thresholding network (ST-Net) is designed in FISTA-Net based on the attention mechanism, which can choose the threshold adaptively. Simulation results show that the proposed TSLR CSI feedback scheme and FISTA-Net outperform the existing algorithms in various scenarios.

S. Shi, Kai Qiao, Shuai Yang et al.

The Graph Neural Network (GNN) has been widely used for graph data representation. However, the existing researches only consider the ideal balanced dataset, and the imbalanced dataset is rarely considered. Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN. This paper proposes an ensemble model called Boosting-GNN, which uses GNNs as the base classifiers during boosting. In Boosting-GNN, higher weights are set for the training samples that are not correctly classified by the previous classifier, thus achieving higher classification accuracy and better reliability. Besides, transfer learning is used to reduce computational cost and increase fitting ability. Experimental results indicate that the proposed Boosting-GNN model achieves better performance than GCN, GraphSAGE, GAT, SGC, N-GCN, and most advanced reweighting and resampling methods on synthetic imbalanced datasets, with an average performance improvement of 4.5%

JT Wu, L. Wang

The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover, the hard angle restriction also increases the risk of overfitting. In this paper, angular loss suggested by maximizing the angular gradient to promote intra-class compactness avoids overfitting. Besides, our method has only one adjustable constant for intra-class compactness control. We define three metrics to measure inter-class separability and intra-class compactness. In experiments, we test our method, as well as other methods, on many well-known datasets. Experimental results reveal that our method has the superiority of accuracy improvement, discriminative information, and time-consumption.

L. Wang, A. S. Morse, D. Fullmer et al.

A hybrid observer is described for estimating the state of an $m>0$ channel, $n$-dimensional, continuous-time, distributed linear system of the form $\dot{x} = Ax,\;y_i = C_ix,\;i\in\{1,2,\ldots, m\}$. The system's state $x$ is simultaneously estimated by $m$ agents assuming each agent $i$ senses $y_i$ and receives appropriately defined data from each of its current neighbors. Neighbor relations are characterized by a time-varying directed graph $\mathbb{N}(t)$ whose vertices correspond to agents and whose arcs depict neighbor relations. Agent $i$ updates its estimate $x_i$ of $x$ at "event times" $t_1,t_2,\ldots $ using a local observer and a local parameter estimator. The local observer is a continuous time linear system whose input is $y_i$ and whose output $w_i$ is an asymptotically correct estimate of $L_ix$ where $L_i$ a matrix with kernel equaling the unobservable space of $(C_i,A)$. The local parameter estimator is a recursive algorithm designed to estimate, prior to each event time $t_j$, a constant parameter $p_j$ which satisfies the linear equations $w_k(t_j-τ) = L_kp_j+μ_k(t_j-τ),\;k\in\{1,2,\ldots,m\}$, where $τ$ is a small positive constant and $μ_k$ is the state estimation error of local observer $k$. Agent $i$ accomplishes this by iterating its parameter estimator state $z_i$, $q$ times within the interval $[t_j-τ, t_j)$, and by making use of the state of each of its neighbors' parameter estimators at each iteration. The updated value of $x_i$ at event time $t_j$ is then $x_i(t_j) = e^{Aτ}z_i(q)$. Subject to the assumptions that (i) the neighbor graph $\mathbb{N}(t)$ is strongly connected for all time, (ii) the system whose state is to be estimated is jointly observable, (iii) $q$ is sufficiently large, it is shown that each estimate $x_i$ converges to $x$ exponentially fast as $t\rightarrow \infty$ at a rate which can be controlled.

V. Abrol, O. Absil, P. -A. Absil et al.

The third edition of the "international - Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST) took place in Aalborg, the 4th largest city in Denmark situated beautifully in the northern part of the country, from the 24th to 26th of August 2016. The workshop venue was at the Aalborg University campus. One implicit objective of this biennial workshop is to foster collaboration between international scientific teams by disseminating ideas through both specific oral/poster presentations and free discussions. For this third edition, iTWIST'16 gathered about 50 international participants and features 8 invited talks, 12 oral presentations, and 12 posters on the following themes, all related to the theory, application and generalization of the "sparsity paradigm": Sparsity-driven data sensing and processing (e.g., optics, computer vision, genomics, biomedical, digital communication, channel estimation, astronomy); Application of sparse models in non-convex/non-linear inverse problems (e.g., phase retrieval, blind deconvolution, self calibration); Approximate probabilistic inference for sparse problems; Sparse machine learning and inference; "Blind" inverse problems and dictionary learning; Optimization for sparse modelling; Information theory, geometry and randomness; Sparsity? What's next? (Discrete-valued signals; Union of low-dimensional spaces, Cosparsity, mixed/group norm, model-based, low-complexity models, ...); Matrix/manifold sensing/processing (graph, low-rank approximation, ...); Complexity/accuracy tradeoffs in numerical methods/optimization; Electronic/optical compressive sensors (hardware).

A. Khoshkbarforoushha, P. Jamshidi, M. Fahmideh et al.

This work proposes a quantitative metric to analyze potential reusability of a BPEL (Business Process Execution Language) Process. The approach is based on Description and Logic Mismatch Probability of a BPEL Process that will be reused within potential contexts. The mismatch probabilities have been consolidated to a metric formula for quantifying the probability of potential reuse of BPEL processes. An initial empirical evaluation suggests that the proposed metric properly predict potential reusability of BPEL processes. According to the experiment, there exists a significant statistical correlation between results of the metric and the experts judgements. This indicates a predictive dependency between the proposed metric and potential reusability of BPEL processes as a measuring stick for this phenomena. If future studies ascertain these findings by replicating this experiment, the practical implications of such a metric are early detection of the design flaws and aiding architects to judge various design alternatives.