arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 397 records · Page 22Linked to original sources

arXiv2025

Understanding Xe isotopes near $A=130$ through the prolate-oblate shape phase transition

A simple algebraic scheme incorporating the prolate-oblate shape phase transition (SPT) is proposed within the framework of the interacting boson model to describe the quadrupole deformation features of Xe isotopes near $A=130$. The analysis demonstrates that novel $γ$-soft modes, characterized by the unusual quadrupole moments $Q(2_1^+)<0$ and $0<Q(2_2^+)\ll |Q(2_1^+)|$, can emerge near the critical point of this SPT. This finding is further applied to interpret the properties of low-lying states in the relevant Xe nuclei, particularly the experimentally observed nearly vanishing spectroscopic quadrupole moment $Q(2_2^+)$, thereby offering new insights into the structure of a $γ$-soft deformed nucleus.

nucl-th↗

arXiv2025

Data-Efficient Learning of Anomalous Diffusion with Wavelet Representations: Enabling Direct Learning from Experimental Trajectories

Machine learning (ML) has become a versatile tool for analyzing anomalous diffusion trajectories, yet most existing pipelines are trained on large collections of simulated data. In contrast, experimental trajectories, such as those from single-particle tracking (SPT), are typically scarce and may differ substantially from the idealized models used for simulation, leading to degradation or even breakdown of performance when ML methods are applied to real data. To address this mismatch, we introduce a wavelet-based representation of anomalous diffusion that enables data-efficient learning directly from experimental recordings. This representation is constructed by applying six complementary wavelet families to each trajectory and combining the resulting wavelet modulus scalograms. We first evaluate the wavelet representation on simulated trajectories from the andi-datasets benchmark, where it clearly outperforms both feature-based and trajectory-based methods with as few as 1000 training trajectories and still retains an advantage on large training sets. We then use this representation to learn directly from experimental SPT trajectories of fluorescent beads diffusing in F-actin networks, where the wavelet representation remains superior to existing alternatives for both diffusion-exponent regression and mesh-size classification. In particular, when predicting the diffusion exponents of experimental trajectories, a model trained on 1200 experimental tracks using the wavelet representation achieves significantly lower errors than state-of-the-art deep learning models trained purely on $10^6$ simulated trajectories. We associate this data efficiency with the emergence of distinct scale fingerprints disentangling underlying diffusion mechanisms in the wavelet spectra.

physics.bio-ph↗

arXiv2025

AgriGPT-VL: Agricultural Vision-Language Understanding Suite

Despite rapid advances in multimodal large language models, agricultural applications remain constrained by the scarcity of domain-tailored models, curated vision-language corpora, and rigorous evaluation. To address these challenges, we present the AgriGPT-VL Suite, a unified multimodal framework for agriculture. Our contributions are threefold. First, we introduce Agri-3M-VL, the largest vision-language corpus for agriculture to our knowledge, curated by a scalable multi-agent data generator; it comprises 1M image-caption pairs, 2M image-grounded VQA pairs, 50K expert-level VQA instances, and 15K GRPO reinforcement learning samples. Second, we develop AgriGPT-VL, an agriculture-specialized vision-language model trained via a progressive curriculum of textual grounding, multimodal shallow/deep alignment, and GRPO refinement. This method achieves strong multimodal reasoning while preserving text-only capability. Third, we establish AgriBench-VL-4K, a compact yet challenging evaluation suite with open-ended and image-grounded questions, paired with multi-metric evaluation and an LLM-as-a-judge framework. Experiments show that AgriGPT-VL outperforms leading general-purpose VLMs on AgriBench-VL-4K, achieving higher pairwise win rates in the LLM-as-a-judge evaluation. Meanwhile, it remains competitive on the text-only AgriBench-13K with no noticeable degradation of language ability. Ablation studies further confirm consistent gains from our alignment and GRPO refinement stages. We will open source all of the resources to support reproducible research and deployment in low-resource agricultural settings.

cs.CL↗

arXiv2025

MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling

Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate training. Current frameworks preserve training performance using mixed-granularity quantization, i.e., applying per-group quantization for activations and per-tensor/block quantization for weights. While effective, per-group quantization requires scaling along the inner dimension of matrix multiplication, introducing additional dequantization overhead. Moreover, these frameworks often rely on just-in-time scaling to dynamically adjust scaling factors based on the current data distribution. However, this online quantization is inefficient for FP8 training, as it involves multiple memory reads and writes that negate the performance benefits of FP8. To overcome these limitations, we propose MOSS, a novel FP8 training framework that ensures both efficiency and numerical stability. MOSS introduces two key innovations: (1) a two-level microscaling strategy for quantizing sensitive activations, which balances precision and dequantization cost by combining a high-precision global scale with compact, power-of-two local scales; and (2) automatic scaling for weights in linear layers, which eliminates the need for costly max-reduction operations by predicting and adjusting scaling factors during training. Leveraging these techniques, MOSS enables efficient FP8 training of a 7B parameter model, achieving performance comparable to the BF16 baseline while achieving up to 34% higher training throughput.

cs.LG↗

arXiv2025

SN 2025coe: A Multiple-Peaked Calcium-Strong Transient from A White-Dwarf Progenitor

SN 2025coe is a calcium-strong transient located at an extremely large projected offset $\sim$39.3 kpc from the center of its host, the nearby early-type galaxy NGC 3277 at a distance of $\sim$25.5 Mpc. In this paper, we present multi-band photometric and spectroscopic observations spanning $\sim$100 days post-discovery. Its multi-band light curves display {multiple} distinct peaks: (1) an initial peak at $t \approx 1.6$ days attributed to shock cooling emission, (2) a secondary peak of $M_{R, \, peak} \approx$ $-$15.8 mag at $t \approx 10.2$ days powered by radioactive decay, and (3) a {possible} late-time bump at $t \approx 42.8$ days likely caused by ejecta-circumstellar material/clump interaction. Spectral evolution of SN 2025coe reveals a fast transition to the nebular phase within 2 months, where it exhibits an exceptionally high [Ca II]/[O I] ratio larger than 6. Modeling of the bolometric light curve suggests an ejecta mass of $M_{\rm ej} = 0.29^{+0.14}_{-0.15} \, M_{\odot}$, a $^{56}$Ni mass of $M_{\rm ^{56}Ni} = 2.4^{+0.06}_{-0.05} \times 10^{-2} M_{\odot}$, and a progenitor envelope with mass $M_e = 1.4^{+6.9}_{-1.2} \times 10^{-3} \, M_{\odot}$ and radius $R_e = 13.5^{+64.1}_{-11.1} \, R_{\odot}$. The tidal disruption of a hybrid HeCO white dwarf (WD) by a low-mass CO WD provides a natural explanation for the low ejecta mass, the small fraction of $^{56}$Ni, and the presence of an extended, low-mass envelope.

astro-ph.HE↗

arXiv2025

Generative Editing in the Joint Vision-Language Space for Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) enables fine-grained visual search by combining a reference image with a textual modification. While supervised CIR methods achieve high accuracy, their reliance on costly triplet annotations motivates zero-shot solutions. The core challenge in zero-shot CIR (ZS-CIR) stems from a fundamental dilemma: existing text-centric or diffusion-based approaches struggle to effectively bridge the vision-language modality gap. To address this, we propose Fusion-Diff, a novel generative editing framework with high effectiveness and data efficiency designed for multimodal alignment. First, it introduces a multimodal fusion feature editing strategy within a joint vision-language (VL) space, substantially narrowing the modality gap. Second, to maximize data efficiency, the framework incorporates a lightweight Control-Adapter, enabling state-of-the-art performance through fine-tuning on only a limited-scale synthetic dataset of 200K samples. Extensive experiments on standard CIR benchmarks (CIRR, FashionIQ, and CIRCO) demonstrate that Fusion-Diff significantly outperforms prior zero-shot approaches. We further enhance the interpretability of our model by visualizing the fused multimodal representations.

cs.CV↗

arXiv2025

NeutrSHINE: a high repetition rate ultrafast neutron source driven by SHINE electron beam

Neutrons serve as unique probes for exploring the microscopic structure of matter, with the performance of a neutron source fundamentally governing the depth of scientific exploration and the breadth of industrial applicability. To address application demands including nuclear data measurement in the ultra-high-energy region, fundamental particle physics research, highly efficient non-destructive neutron testing, and extreme environment simulation, an ultrafast neutron source driven by the 8 GeV electron beam from the Shanghai high-repetition-rate extreme light facility (SHINE) was conceptually proposed, named NeutrSHINE. Using multidisciplinary simulation tools, key neutronic parameters, thermal behavior of high-power neutron targets, and the factors affecting the time resolution of the source were analyzed. The results affirm the technical feasibility and promising application prospects of the NeutrSHINE concept.

physics.acc-ph↗

arXiv2025

The Professional Challenges of Industrial Designer in Industry 4.0

The Industry 4.0 refers to a industrial ecology which will merge the information system, physical system and service system into an integrate platform. Since now the industrial designers either conceive the physical part of products, or design the User Interfaces of computer systems, the new industrial ecology will give them a chance to redefine their roles in R&D work-flow. In this paper we discussed the required qualities of industrial designer in the new era, according to an investigation among Chinese enterprises. Additionally, how to promote these qualities though educational program.

cs.HC↗

arXiv2025

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstrated the effectiveness of combining parameters through strategies such as parameter decomposition, coefficient optimization, and subspace learning, significantly reducing the need for expensive joint training and achieving strong empirical performance across diverse tasks. However, these approaches predominantly treat merging as a problem of parameter space decomposition or fusion coefficient optimization, while overlooking the critical role of directional information in both parameter and feature spaces. In practice, naïve merging introduces inconsistencies in dominant parameter directions and disrupts structural coherence across models, which can degrade performance. Moreover, coefficient-based optimization methods implicitly assume compatible feature-space directions across models. However, Neural Collapse indicates that class features follow structured directional patterns, which may differ across independently trained models, making coefficient optimization alone insufficient. In this work, we emphasize the importance of \emph{directional alignment} and introduce a unified geometric framework, \emph{Merging with Directional Alignment} (\method{}), which aligns directional structures consistently in both the parameter and feature spaces. Our analysis shows that directional alignment improves structural coherence, and extensive experiments across benchmarks, model scales, and task configurations further validate the effectiveness of our approach.

cs.LG↗

arXiv2025

Dual-Balancing for Multi-Task Learning

Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among tasks often leads to performance compromises, and the balancing of tasks remains a significant challenge. In this paper, we propose Dual-Balancing Multi-Task Learning (DB-MTL) to achieve task balancing from both the loss and gradient perspectives. Specifically, DB-MTL achieves loss-scale balancing by performing logarithm transformation on each task loss, and rescales gradient magnitudes by normalizing all task gradients to comparable magnitudes using the maximum gradient norm. Extensive experiments on a number of benchmark datasets demonstrate that DB-MTL consistently performs better than the current state-of-the-art.

cs.LG↗

arXiv2025

E$^{3}$NeRF: Efficient Event-Enhanced Neural Radiance Fields from Blurry Images

Neural Radiance Fields (NeRF) achieves impressive novel view rendering performance by learning implicit 3D representation from sparse view images. However, it is difficult to reconstruct a sharp NeRF from blurry input that often occurs in the wild. To solve this problem, we propose a novel Efficient Event-Enhanced NeRF (E$^{3}$NeRF), reconstructing sharp NeRF by utilizing both blurry images and corresponding event streams. A blur rendering loss and an event rendering loss are introduced, which guide the NeRF training via modeling the physical image motion blur process and event generation process, respectively. To improve the efficiency of the framework, we further leverage the latent spatial-temporal blur information in the event stream to evenly distribute training over temporal blur and focus training on spatial blur. Moreover, a camera pose estimation framework for real-world data is built with the guidance of the events, generalizing the method to more practical applications. Compared to previous image-based and event-based NeRF works, our framework makes more profound use of the internal relationship between events and images. Extensive experiments on both synthetic data and real-world data demonstrate that E\textsuperscript{3}NeRF can effectively learn a sharp NeRF from blurry images, especially for high-speed non-uniform motion and low-light scenes.

cs.CV↗

arXiv2025

Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms

Ride-hailing platforms are characterized by high-frequency, behavior-driven environments. Although survival analysis has been applied to recurrent events in other domains, its use in modeling ride-hailing driver behavior remains largely unexplored. This study formulates idle behavior as a recurrent survival process using large-scale platform data and proposes a Transformer-based framework that captures long-term temporal dependencies with causal masking and incorporates driver-specific embeddings to model latent heterogeneity. Results on Toronto ride-hailing data demonstrate that the proposed Frailty-Aware Cox Transformer (FACT) achieves the highest time-dependent C-indices and lowest Brier Scores, outperforming classical and deep learning survival models. This approach enables more accurate risk estimation, supports platform retention strategies, and provides policy-relevant insights.

cs.LG↗

arXiv2025

Pronounced scale-dependent charge carrier density in graphene quantum Hall devices

The miniaturization of quantum Hall resistance standards (QHRS) using epitaxial graphene on silicon carbide necessitates understanding how device dimensions impact performance. This study reveals a pronounced scale-dependent carrier density in graphene Hall devices: under electron doping, carrier density decreases with increasing channel width (Wd), while the opposite occurs under hole doping. This phenomenon, most significant for Wd less than 400 um, directly influences the onset of magnetic field required for quantization. Fermi velocity measurements and angle-resolved photoemission spectroscopy (ARPES) analysis indicate that band structure modifications and electron-electron interactions underlie this size dependence. Utilizing machine learning with limited data, we optimized the device geometry, identifying a channel width of ~360 um as the optimal balance between resistance uncertainty and on-chip integration density. This work provides key insights for designing high-performance, miniaturized graphene-based QHRS arrays.

cond-mat.mes-hall↗

arXiv2025

STORE: Semantic Tokenization, Orthogonal Rotation and Efficient Attention for Scaling Up Ranking Models

Ranking models have become an important part of modern personalized recommendation systems. However, significant challenges persist in handling high-cardinality, heterogeneous, and sparse feature spaces, particularly regarding model scalability and efficiency. We identify two key bottlenecks: (i) Representation Bottleneck: Driven by the high cardinality and dynamic nature of features, model capacity is forced into sparse-activated embedding layers, leading to low-rank representations. This, in turn, triggers phenomena like "One-Epoch" and "Interaction-Collapse," ultimately hindering model scalability.(ii) Computational Bottleneck: Integrating all heterogeneous features into a unified model triggers an explosion in the number of feature tokens, rendering traditional attention mechanisms computationally demanding and susceptible to attention dispersion. To dismantle these barriers, we introduce STORE, a unified and scalable token-based ranking framework built upon three core innovations: (1) Semantic Tokenization fundamentally tackles feature heterogeneity and sparsity by decomposing high-cardinality sparse features into a compact set of stable semantic tokens; and (2) Orthogonal Rotation Transformation is employed to rotate the subspace spanned by low-cardinality static features, which facilitates more efficient and effective feature interactions; and (3) Efficient attention that filters low-contributing tokens to improve computional efficiency while preserving model accuracy. Across extensive offline experiments and online A/B tests, our framework consistently improves prediction accuracy(online CTR by 2.71%, AUC by 1.195%) and training effeciency (1.84 throughput).

cs.IR↗

arXiv2025

DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection

Recent salient object detection (SOD) methods aim to improve performance in four key directions: semantic enhancement, boundary refinement, auxiliary task supervision, and multi-modal fusion. In pursuit of continuous gains, these approaches have evolved toward increasingly sophisticated architectures with multi-stage pipelines, specialized fusion modules, edge-guided learning, and elaborate attention mechanisms. However, this complexity paradoxically introduces feature redundancy and cross-component interference that obscure salient cues, ultimately reaching performance bottlenecks. In contrast, human vision achieves efficient salient object identification without such architectural complexity. This contrast raises a fundamental question: can we design a biologically grounded yet architecturally simple SOD framework that dispenses with most of this engineering complexity, while achieving state-of-the-art accuracy, computational efficiency, and interpretability? In this work, we answer this question affirmatively by introducing DualGazeNet, a biologically inspired pure Transformer framework that models the dual biological principles of robust representation learning and magnocellular-parvocellular dual-pathway processing with cortical attention modulation in the human visual system. Extensive experiments on five RGB SOD benchmarks show that DualGazeNet consistently surpasses 25 state-of-the-art CNN- and Transformer-based methods. On average, DualGazeNet achieves about 60\% higher inference speed and 53.4\% fewer FLOPs than four Transformer-based baselines of similar capacity (VST++, MDSAM, Sam2unet, and BiRefNet). Moreover, DualGazeNet exhibits strong cross-domain generalization, achieving leading or highly competitive performance on camouflaged and underwater SOD benchmarks without relying on additional modalities.

cs.CV↗

arXiv2025

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport

Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolation in weight space, which we show introduces significant distribution shift in the feature space and undermines task-specific knowledge. In this paper, we propose OTMF (Optimal Transport-based Masked Fusion), a novel model merging framework rooted in optimal transport theory to address the distribution shift that arises from naive parameter interpolation. Instead of directly aggregating features or weights, OTMF aligns the semantic geometry of task-specific models by discovering common masks applied to task vectors through optimal transport plans. These masks selectively extract transferable and task-agnostic components while preserving the unique structural identities of each task. To ensure scalability in real-world settings, OTMF further supports a continual fusion paradigm that incrementally integrates each new task vector without revisiting previous ones, maintaining a bounded memory footprint and enabling efficient fusion across a growing number of tasks. We conduct comprehensive experiments on multiple vision and language benchmarks, and results show that OTMF achieves state-of-the-art performance in terms of both accuracy and efficiency. These findings highlight the practical and theoretical value of our approach to model merging.

cs.LG↗

arXiv2025

Clustering-Enhanced Time- and Angle-Resolved Photoemission Study of LaTe$_3$: Absence of a Photoinduced Secondary CDW in the Electronic Structure

Optical control offers a compelling route for tailoring material properties on an ultrafast time scale. Ordered states such as charge density waves (CDWs) can be transiently melted by an ultrafast light excitation. This is also the case for the rare-earth tritelluride LaTe$_3$, a prototypical CDW compound. For this material it has recently been reported that the suppression of the primary CDW allows the transient formation of a second CDW, whose wave vector is orthogonal to the primary one. This creates the intriguing scenario where light enables switching between two distinct ordered phases of the material. While the second CDW has so far been observed by structural techniques, it remains an open question how the interplay of the two CDW phases is reflected in the material's electronic structure. We investigate this via time- and angle-resolved photoemission measurements of LaTe$_3$. The complex Fermi contour is probed using a FeSuMa analyzer, which records the photoemission intensity of the entire Fermi contour at once. The dynamics revealed by the FeSuMa analyzer are complemented by measurements using a conventional hemispherical electron analyzer. We combine conventional data analysis with $k$-means clustering, an unsupervised machine learning technique, demonstrating its strong potential for disentangling large datasets. While we do not find any features that cannot be explained by the melting and re-establishment of the primary CDW, distinct dynamics and coherent oscillations are observed in the different branches of the Fermi contour.

cond-mat.str-el↗

arXiv2025

TBGRecall: A Generative Retrieval Model for E-commerce Recommendation Scenarios

Recommendation systems are essential tools in modern e-commerce, facilitating personalized user experiences by suggesting relevant products. Recent advancements in generative models have demonstrated potential in enhancing recommendation systems; however, these models often exhibit limitations in optimizing retrieval tasks, primarily due to their reliance on autoregressive generation mechanisms. Conventional approaches introduce sequential dependencies that impede efficient retrieval, as they are inherently unsuitable for generating multiple items without positional constraints within a single request session. To address these limitations, we propose TBGRecall, a framework integrating Next Session Prediction (NSP), designed to enhance generative retrieval models for e-commerce applications. Our framework reformulation involves partitioning input samples into multi-session sequences, where each sequence comprises a session token followed by a set of item tokens, and then further incorporate multiple optimizations tailored to the generative task in retrieval scenarios. In terms of training methodology, our pipeline integrates limited historical data pre-training with stochastic partial incremental training, significantly improving training efficiency and emphasizing the superiority of data recency over sheer data volume. Our extensive experiments, conducted on public benchmarks alongside a large-scale industrial dataset from TaoBao, show TBGRecall outperforms the state-of-the-art recommendation methods, and exhibits a clear scaling law trend. Ultimately, NSP represents a significant advancement in the effectiveness of generative recommendation systems for e-commerce applications.

cs.IR↗