arXiv subjects

Lin Wang

Publications and source records attributed to Lin Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Flexible Sampling for Long-tailed Skin Lesion Classification

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the long-tailed distribution. However, considering that some challenging classes may present diverse intra-class distributions, re-balancing all classes equally may lead to a significant performance drop. To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task. Specifically, we initially sample a subset of training data as anchor points based on the individual class prototypes. Then, these anchor points are used to pre-train an inference model to evaluate the per-class learning difficulty. Finally, we use a curriculum sampling module to dynamically query new samples from the rest training samples with the learning difficulty-aware sampling probability. We evaluated our model against several state-of-the-art methods on the ISIC dataset. The results with two long-tailed settings have demonstrated the superiority of our proposed training strategy, which achieves a new benchmark for long-tailed skin lesion classification.

cs.CV↗

arXiv2025

Spin relaxation in a single-electron bilayer graphene quantum dot

We study the spin relaxation in a single-electron bilayer graphene quantum dot due to the spin-orbit coupling. The spin relaxation is assisted by the emission of acoustic phonons via the bond-length change and deformation potential mechanisms and $1/f$ charge noise. In the perpendicular magnetic-field dependence of the spin relaxation rate $T_1^{-1}$, we predict a monotonic increase of $T_1^{-1}$ at higher fields where the electron-phonon coupling via the deformation potential plays a dominant role in spin relaxation. We show a less pronounced dip in $T_1^{-1}$ at lower magnetic fields due to the competition between the electron-phonon coupling due to bond-length change and $1/f$ charge noise. Finally, detailed comparisons of the magnetic-field dependence of the spin relaxation with the existing experiments by Banszerus et al. [Nat. Commun. 13, 3637 (2022)] and Gächter et al. [PRX Quantum 3, 020343 (2022)] are reported.

cond-mat.mes-hall↗

arXiv2025

Entropy-driven Fair and Effective Federated Learning

Federated Learning (FL) enables collaborative model training across distributed devices while preserving data privacy. Nonetheless, the heterogeneity of edge devices often leads to inconsistent performance of the globally trained models, resulting in unfair outcomes among users. Existing federated fairness algorithms strive to enhance fairness but often fall short in maintaining the overall performance of the global model, typically measured by the average accuracy across all clients. To address this issue, we propose a novel algorithm that leverages entropy-based aggregation combined with model and gradient alignments to simultaneously optimize fairness and global model performance. Our method employs a bi-level optimization framework, where we derive an analytic solution to the aggregation probability in the inner loop, making the optimization process computationally efficient. Additionally, we introduce an innovative alignment update and an adaptive strategy in the outer loop to further balance global model's performance and fairness. Theoretical analysis indicates that our approach guarantees convergence even in non-convex FL settings and demonstrates significant fairness improvements in generalized regression and strongly convex models. Empirically, our approach surpasses state-of-the-art federated fairness algorithms, ensuring consistent performance among clients while improving the overall performance of the global model.

cs.LG↗

arXiv2025

Searching for pulsars in Globular Clusters with the Fast Fold Algorithm and a new pulsar discovered in M13

We employed the Fast Folding Algorithm (FFA) on L-Band Globular Cluster (GC) observations taken with Five-hundred-meter Aperture Spherical radio Telescope (FAST) to search for new pulsars, especially those with a long rotational period. We conducted a search across 16 GCs that collectively host 93 known pulsars, as well as 14 GCs that do not contain any known pulsars. The majority of these known pulsars were successfully re-detected in our survey. The few non-detections could be attributed to the high accelerations of these pulsars. Additionally, we have discovered a new binary millisecond pulsar, namely M13I (or PSR J1641+3627I) in GC M13 (or NGC 6205), and obtained its phase-coherent timing solution using observations spanning 6 years. M13I has a spin period of 6.37 ms, and an orbital period of 18.23 days. The eccentricity of the binary orbit is 0.064, with a companion mass range of approximately 0.45 to 1.37 M$_{\odot}$. The orbital properties of M13I are remarkably different from those of the other known pulsars in M13, indicating that this pulsar has undergone a different evolutionary path compared to the rest.

astro-ph.HE↗

arXiv2025

Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience

Autonomous AI is no longer a hard-to-reach concept, it enables the agents to move beyond executing tasks to independently addressing complex problems, adapting to change while handling the uncertainty of the environment. However, what makes the agents truly autonomous? It is agentic reasoning, that is crucial for foundation models to develop symbolic logic, statistical correlations, or large-scale pattern recognition to process information, draw inferences, and make decisions. However, it remains unclear why and how existing agentic reasoning approaches work, in comparison to biological reasoning, which instead is deeply rooted in neural mechanisms involving hierarchical cognition, multimodal integration, and dynamic interactions. In this work, we propose a novel neuroscience-inspired framework for agentic reasoning. Grounded in three neuroscience-based definitions and supported by mathematical and biological foundations, we propose a unified framework modeling reasoning from perception to action, encompassing four core types, perceptual, dimensional, logical, and interactive, inspired by distinct functional roles observed in the human brain. We apply this framework to systematically classify and analyze existing AI reasoning methods, evaluating their theoretical foundations, computational designs, and practical limitations. We also explore its implications for building more generalizable, cognitively aligned agents in physical and virtual environments. Finally, building on our framework, we outline future directions and propose new neural-inspired reasoning methods, analogous to chain-of-thought prompting. By bridging cognitive neuroscience and AI, this work offers a theoretical foundation and practical roadmap for advancing agentic reasoning in intelligent systems. The associated project can be found at: https://github.com/BioRAILab/Awesome-Neuroscience-Agent-Reasoning .

q-bio.NC↗

arXiv2025

TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion

Video frame interpolation (VFI) that leverages the bio-inspired event cameras as guidance has recently shown better performance and memory efficiency than the frame-based methods, thanks to the event cameras' advantages, such as high temporal resolution. A hurdle for event-based VFI is how to effectively deal with non-linear motion, caused by the dynamic changes in motion direction and speed within the scene. Existing methods either use events to estimate sparse optical flow or fuse events with image features to estimate dense optical flow. Unfortunately, motion errors often degrade the VFI quality as the continuous motion cues from events do not align with the dense spatial information of images in the temporal dimension. In this paper, we find that object motion is continuous in space, tracking local regions over continuous time enables more accurate identification of spatiotemporal feature correlations. In light of this, we propose a novel continuous point tracking-based VFI framework, named TimeTracker. Specifically, we first design a Scene-Aware Region Segmentation (SARS) module to divide the scene into similar patches. Then, a Continuous Trajectory guided Motion Estimation (CTME) module is proposed to track the continuous motion trajectory of each patch through events. Finally, intermediate frames at any given time are generated through global motion optimization and frame refinement. Moreover, we collect a real-world dataset that features fast non-linear motion. Extensive experiments show that our method outperforms prior arts in both motion estimation and frame interpolation quality.

cs.CV↗

arXiv2025

HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation

Current text-to-avatar methods often rely on implicit representations (e.g., NeRF, SDF, and DMTet), leading to 3D content that artists cannot easily edit and animate in graphics software. This paper introduces a novel framework for generating stylized head avatars from text guidance, which leverages locally learnable mesh deformation and 2D diffusion priors to achieve high-quality digital assets for attribute-preserving manipulation. Given a template mesh, our method represents mesh deformation with per-face Jacobians and adaptively modulates local deformation using a learnable vector field. This vector field enables anisotropic scaling while preserving the rotation of vertices, which can better express identity and geometric details. We employ landmark- and contour-based regularization terms to balance the expressiveness and plausibility of generated avatars from multiple views without relying on any specific shape prior. Our framework can generate realistic shapes and textures that can be further edited via text, while supporting seamless editing using the preserved attributes from the template mesh, such as 3DMM parameters, blendshapes, and UV coordinates. Extensive experiments demonstrate that our framework can generate diverse and expressive head avatars with high-quality meshes that artists can easily manipulate in graphics software, facilitating downstream applications such as efficient asset creation and animation with preserved attributes.

cs.GR↗

arXiv2025

FreeBeacon: Efficient Communication and Data Aggregation in Battery-Free IoT

To improve sustainability, Internet-of-Things (IoT) is increasingly adopting battery-free devices powered by ambient energy scavenged from the environment. The unpredictable availability of ambient energy leads to device intermittency, bringing critical challenges to device communication and related fundamental operations like data aggregation. We propose FreeBeacon, a novel scheme for efficient communication and data aggregation in battery-free IoT. We argue that the communication challenge between battery-free devices originates from the complete uncertainty of the environment. FreeBeacon is built on the insight that by introducing just a small degree of certainty into the system, the communication problem can be largely simplified. To this end, FreeBeacon first introduces a small number of battery-powered devices as beacons for battery-free devices. Then, FreeBeacon features protocols for battery-free devices to achieve interaction with the beacon and to perform communication efficiently following customized schedules that implement different data aggregation schemes while achieving resilience. We evaluate FreeBeacon with extensive prototype-based experiments and simulation studies. Results show that FreeBeacon can consistently achieve an order of magnitude data aggregation efficiency when compared with the state-of-the-art approaches.

cs.NI↗

arXiv2025

Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN

Up to now, the training processes of typical Generative Adversarial Networks (GANs) are still particularly sensitive to data properties and hyperparameters, which may lead to severe oscillations, difficulties in convergence, or even failures to converge, especially when the overall variances of the training sets are large. These phenomena are often attributed to the training characteristics of such networks. Aiming at the problem, this paper develops a new intelligent optimizer, Fast-Slow Co-advancing Optimizer (FSCO), which employs reinforcement learning in the training process of GANs to make training easier. Specifically, this paper allows the training step size to be controlled by an agent to improve training stability, and makes the training process more intelligent with variable learning rates, making GANs less sensitive to step size. Experiments have been conducted on three benchmark datasets to verify the effectiveness of the developed FSCO.

cs.LG↗

arXiv2025

On the Destruction of Invariant Lagrangian Graphs for Conformal Symplectic Twist Maps

In this article we investigate the fragility of invariant Lagrangian graphs for dissipative maps, focusing on their destruction under small perturbations. Inspired by Herman's work on conservative systems, we prove that all $C^0$-invariant Lagrangian graphs for an integrable dissipative twist maps can be destroyed by perturbations that are arbitrarily small in the $C^{1-\varepsilon}$-topology. This result is sharp, as evidenced by the persistence of $C^1$-invariant graphs under $C^1$-perturbations guaranteed by the normally hyperbolic invariant manifold theorem.

math.DS↗

arXiv2025

Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences

In this study, Disentanglement in Difference(DiD) is proposed to address the inherent inconsistency between the statistical independence of latent variables and the goal of semantic disentanglement in disentanglement representation learning. Conventional disentanglement methods achieve disentanglement representation by improving statistical independence among latent variables. However, the statistical independence of latent variables does not necessarily imply that they are semantically unrelated, thus, improving statistical independence does not always enhance disentanglement performance. To address the above issue, DiD is proposed to directly learn semantic differences rather than the statistical independence of latent variables. In the DiD, a Difference Encoder is designed to measure the semantic differences; a contrastive loss function is established to facilitate inter-dimensional comparison. Both of them allow the model to directly differentiate and disentangle distinct semantic factors, thereby resolving the inconsistency between statistical independence and semantic disentanglement. Experimental results on the dSprites and 3DShapes datasets demonstrate that the proposed DiD outperforms existing mainstream methods across various disentanglement metrics.

cs.LG↗

arXiv2025

Convolution-Based Converter : A Weak-Prior Approach For Modeling Stochastic Processes Based On Conditional Density Estimation

In this paper, a Convolution-Based Converter (CBC) is proposed to develop a methodology for removing the strong or fixed priors in estimating the probability distribution of targets based on observations in the stochastic process. Traditional approaches, e.g., Markov-based and Gaussian process-based methods, typically leverage observations to estimate targets based on strong or fixed priors (such as Markov properties or Gaussian prior). However, the effectiveness of these methods depends on how well their prior assumptions align with the characteristics of the problem. When the assumed priors are not satisfied, these approaches may perform poorly or even become unusable. To overcome the above limitation, we introduce the Convolution-Based converter (CBC), which implicitly estimates the conditional probability distribution of targets without strong or fixed priors, and directly outputs the expected trajectory of the stochastic process that satisfies the constraints from observations. This approach reduces the dependence on priors, enhancing flexibility and adaptability in modeling stochastic processes when addressing different problems. Experimental results demonstrate that our method outperforms existing baselines across multiple metrics.

cs.LG↗

arXiv2025

Heterogeneous bimodal attention fusion for speech emotion recognition

Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are particularly important for understanding emotions from a human perspective. Most existing studies focus on exploring interactions between audio and text modalities at the same representation level. However, a critical issue is often overlooked: the heterogeneous modality gap between low-level audio representations and high-level text representations. To address this problem, we propose a novel framework called Heterogeneous Bimodal Attention Fusion (HBAF) for multi-level multi-modal interaction in conversational emotion recognition. The proposed method comprises three key modules: the uni-modal representation module, the multi-modal fusion module, and the inter-modal contrastive learning module. The uni-modal representation module incorporates contextual content into low-level audio representations to bridge the heterogeneous multi-modal gap, enabling more effective fusion. The multi-modal fusion module uses dynamic bimodal attention and a dynamic gating mechanism to filter incorrect cross-modal relationships and fully exploit both intra-modal and inter-modal interactions. Finally, the inter-modal contrastive learning module captures complex absolute and relative interactions between audio and text modalities. Experiments on the MELD and IEMOCAP datasets demonstrate that the proposed HBAF method outperforms existing state-of-the-art baselines.

cs.SD↗

arXiv2025

Bimodal Connection Attention Fusion for Speech Emotion Recognition

Multi-modal emotion recognition is challenging due to the difficulty of extracting features that capture subtle emotional differences. Understanding multi-modal interactions and connections is key to building effective bimodal speech emotion recognition systems. In this work, we propose Bimodal Connection Attention Fusion (BCAF) method, which includes three main modules: the interactive connection network, the bimodal attention network, and the correlative attention network. The interactive connection network uses an encoder-decoder architecture to model modality connections between audio and text while leveraging modality-specific features. The bimodal attention network enhances semantic complementation and exploits intra- and inter-modal interactions. The correlative attention network reduces cross-modal noise and captures correlations between audio and text. Experiments on the MELD and IEMOCAP datasets demonstrate that the proposed BCAF method outperforms existing state-of-the-art baselines.

cs.SD↗

arXiv2025

Balanced Subsampling for Big Data with Categorical Covariates

Supervised learning under measurement constraints is a common challenge in statistical and machine learning. In many applications, despite extensive design points, acquiring responses for all points is often impractical due to resource limitations. Subsampling algorithms offer a solution by selecting a subset from the design points for observing the response. Existing subsampling methods primarily assume numerical predictors, neglecting the prevalent occurrence of big data with categorical predictors across various disciplines. This paper proposes a novel balanced subsampling approach tailored for data with categorical predictors. A balanced subsample significantly reduces the cost of observing the response and possesses three desired merits. First, it is nonsingular and, therefore, allows linear regression with all dummy variables encoded from categorical predictors. Second, it offers optimal parameter estimation by minimizing the generalized variance of the estimated parameters. Third, it allows robust prediction in the sense of minimizing the worst-case prediction error. We demonstrate the superiority of balanced subsampling over existing methods through extensive simulation studies and a real-world application.

stat.ME↗

arXiv2025

Optimal intrinsic formation using exogenous systems

This paper investigates the intrinsic formation problem of a multi-agent system using an exogenous system. The problem is formulated as an intrinsic infinite time-horizon linear quadratic optimal control problem, namely, no formation error information is incorporated in the performance index. Convergence to the formation is achieved by utilizing an exogenous system, thus expanding the steady-state formation space of the system. For the forward problem, we provide the existence condition for a nonzero steady state and characterize the steady-state space. For the inverse problem, we design both the input matrix and the exogenous system so that the desired formation can be achieved. Finally, numerical simulations are provided to illustrate the effectiveness of the proposed results.

math.OC↗

arXiv2025

PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation

Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its success, it remains an open question regarding DAMs' performance on panorama images that enjoy a large field-of-view (180x360) but suffer from spherical distortions. To address this gap, we conduct an empirical analysis to evaluate the performance of DAMs on panoramic images and identify their limitations. For this, we undertake comprehensive experiments to assess the performance of DAMs from three key factors: panoramic representations, 360 camera positions for capturing scenarios, and spherical spatial transformations. This way, we reveal some key findings, e.g., DAMs are sensitive to spatial transformations. We then propose a semi-supervised learning (SSL) framework to learn a panoramic DAM, dubbed PanDA. Under the umbrella of SSL, PanDA first learns a teacher model by fine-tuning DAM through joint training on synthetic indoor and outdoor panoramic datasets. Then, a student model is trained using large-scale unlabeled data, leveraging pseudo-labels generated by the teacher model. To enhance PanDA's generalization capability, M"obius transformation-based spatial augmentation (MTSA) is proposed to impose consistency regularization between the predicted depth maps from the original and spatially transformed ones. This subtly improves the student model's robustness to various spatial transformations, even under severe distortions. Extensive experiments demonstrate that PanDA exhibits remarkable zero-shot capability across diverse scenes, and outperforms the data-specific panoramic depth estimation methods on two popular real-world benchmarks.

cs.CV↗

arXiv2025

E-SAM: Training-Free Segment Every Entity Model

Entity Segmentation (ES) aims at identifying and segmenting distinct entities within an image without the need for predefined class labels. This characteristic makes ES well-suited to open-world applications with adaptation to diverse and dynamically changing environments, where new and previously unseen entities may appear frequently. Existing ES methods either require large annotated datasets or high training costs, limiting their scalability and adaptability. Recently, the Segment Anything Model (SAM), especially in its Automatic Mask Generation (AMG) mode, has shown potential for holistic image segmentation. However, it struggles with over-segmentation and under-segmentation, making it less effective for ES. In this paper, we introduce E-SAM, a novel training-free framework that exhibits exceptional ES capability. Specifically, we first propose Multi-level Mask Generation (MMG) that hierarchically processes SAM's AMG outputs to generate reliable object-level masks while preserving fine details at other levels. Entity-level Mask Refinement (EMR) then refines these object-level masks into accurate entity-level masks. That is, it separates overlapping masks to address the redundancy issues inherent in SAM's outputs and merges similar masks by evaluating entity-level consistency. Lastly, Under-Segmentation Refinement (USR) addresses under-segmentation by generating additional high-confidence masks fused with EMR outputs to produce the final ES map. These three modules are seamlessly optimized to achieve the best ES without additional training overhead. Extensive experiments demonstrate that E-SAM achieves state-of-the-art performance compared to prior ES methods, demonstrating a significant improvement by +30.1 on benchmark metrics.

cs.CV↗