Searcharxiv⌕ Search

arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 181 records · Page 10Linked to original sources
arXiv2026

Revisiting self-seeding mechanism by generating vector ultraviolet N$_2^{+}$ lasing

An intense femtosecond laser pulse can generate ultraviolet air lasing, offering a promising remote light source. A long-standing hypothesis is whether it is seeded by a self-generated spectral component, such as the second harmonic that is inevitably produced by the plasma gradient. Here, we report the generation of both radially and azimuthally polarized N$_2^+$ lasing driven by a single 800-nm cylindrical vector beam. Meanwhile, the same vector pump was applied to drive the generation of vector second harmonics in plasma. The radially polarized pump produces radially polarized second harmonics while the azimuthally polarized pump yields no second harmonic generation owing to the radial direction of plasma gradient. The absence of the azimuthally polarized second harmonic rules out the hypothesis of self-seeding by second harmonics, as both radially and azimuthally polarized N$_2^+$ lasing are observed with comparable intensities. By characterizing the spatial phase distribution of vector 391-nm lasing, we concluded that its phase is synchronized with the pump. These results suggest that amplified spontaneous emissions are the origin of N$_2^+$ lasing under the most common condition of low gas pressure, which was effectively demonstrated by theoretical simulations. Our work provides a promising method for remotely generating vector ultraviolet light sources.

physics.atom-ph↗
arXiv2026

Semantics-Aware Denoising: A PLM-Guided Sample Reweighting Strategy for Robust Recommendation

Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems. However, click interactions inherently contain substantial noise, including accidental clicks, clickbait-induced interactions, and exploratory browsing behaviors that do not reflect genuine user preferences. Training recommendation models with such noisy positive samples leads to degraded prediction accuracy and unreliable recommendations. In this paper, we propose SAID (Semantics-Aware Implicit Denoising), a simple yet effective framework that leverages semantic consistency between user interests and item content to identify and downweight potentially noisy interactions. Our approach constructs textual user interest profiles from historical behaviors and computes semantic similarity with target item descriptions using pre-trained language model (PLM) based text encoders. The similarity scores are then transformed into sample weights that modulate the training loss, effectively reducing the impact of semantically inconsistent clicks. Unlike existing denoising methods that require complex auxiliary networks or multi-stage training procedures, SAID only modifies the loss function while keeping the backbone recommendation model unchanged. Extensive experiments on two real-world datasets demonstrate that SAID consistently improves recommendation performance, achieving up to 2.2% relative improvement in AUC over strong baselines, with particularly notable robustness under high noise conditions.

cs.IR↗
arXiv2026

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches often rely on pretrained encoders, semantic distillation, or heterogeneous CNN-based architectures. These designs introduce fixed inductive biases that limit reconstruction fidelity and hinder effective scaling. In this paper, we argue that discrete audio tokenization should be learned fully end-to-end using a homogeneous and scalable architecture. To this end, we first propose CAT (Causal Audio Tokenizer with Transformer), a purely Transformer-based architecture that jointly optimizes the encoder, quantizer, and decoder from scratch for high-fidelity reconstruction. Building on the CAT architecture, we develop MOSS-Audio-Tokenizer, a large-scale audio tokenizer featuring 1.6 billion parameters, pre-trained on 3 million hours of diverse, general audio data. We show that this simple, fully end-to-end approach built from homogeneous, causal Transformer blocks scales gracefully and supports high-fidelity reconstruction across diverse audio domains. Across speech, sound, and music, MOSS-Audio-Tokenizer consistently outperforms prior codecs over a wide range of bitrates, while exhibiting predictable improvements with increased scale. Notably, leveraging the discrete tokens from our model, we develop the first purely autoregressive TTS model that surpasses prior non-autoregressive and cascaded systems. Furthermore, MOSS-Audio-Tokenizer enables competitive ASR performance without auxiliary encoders. Our findings position the CAT architecture as a unified, scalable interface for the next generation of native audio foundation models.

cs.SD↗
arXiv2026

Exploring Multiple High-Scoring Subspaces in Generative Flow Networks

As a probabilistic sampling framework, Generative Flow Networks (GFlowNets) show strong potential for constructing complex combinatorial objects through the sequential composition of elementary components. However, existing GFlowNets often suffer from excessive exploration over vast state spaces, leading to over-sampling of low-reward regions and convergence to suboptimal distributions. Effectively biasing GFlowNets toward high-reward solutions remains a non-trivial challenge. In this paper, we propose CMAB-GFN, which integrates a combinatorial multi-armed bandit (CMAB) framework with GFlowNet policies. The CMAB component prunes low-quality actions, yielding compact high-scoring subspaces for exploration. Restricting GFNs to these compact high-scoring subspaces accelerates the discovery of high-value candidates, while the exploration of different subspaces ensures that diversity is not sacrificed. Experimental results on multiple tasks demonstrate that CMAB-GFN generates higher-reward candidates than existing approaches.

cs.LG↗
arXiv2026

Pivoting as an Adaptive Strategy to Geopolitical Tensions in U.S. Science

Geopolitical tensions increasingly reshape the structure and openness of global science, yet we still lack a clear understanding of how successfully scientists adapt their work under such pressures. Using millions of funding and publication datasets across the past ten years, we investigate how U.S. China geopolitical tensions reshaped individual research activities of U.S. based scientists, particularly those collaborating with Chinese peers. We find that although U.S. China geopolitical tensions significantly reduce funding opportunities, many scientists actively respond by pivoting their research portfolios toward alternative topics, and this adaptive reorientation partially mitigates funding losses. Crucially, the effectiveness of this adaptive strategy is highly unequal: for scientists in high risk domains, those of Asian descent, and early-career scientists, pivoting offers only limited protection against funding loss. Our results demonstrate that geopolitical tensions reshape science through shifts in scientists' strategic decisions about their research focus. Understanding this adaptive but uneven reconfiguration is essential for science policies to strengthen the resilience and inclusiveness of the scientific enterprise.

physics.soc-ph↗
arXiv2026

Two-Scale Analysis of the Electrostatics of Dielectric Crystals: Emergence of Polarization Density and Boundary Charges

Ionic crystals, such as solid electrolytes and complex oxides, are central to modern technologies for energy storage, sensing, actuation, and other functional applications. An important fundamental issue in the atomic and quantum-scale modeling of these materials is defining the macroscopic polarization. In a periodic crystal, the usual definition of the polarization as the first moment of the charge density in a unit cell is found to depend qualitatively - allowing even a change in the sign - and quantitatively on the choice of unit cell. We examine this issue using a rigorous approach based on the framework of 2-scale convergence. By examining the continuum limit of when the lattice spacing is much smaller than the characteristic dimensions of the body, we show that the 2-scale limit provides both a bulk polarization as well as a surface charge density supported on the boundary of the body. Further, different choices of the periodic unit cell of the body lead to correspondingly different partial unit cells at the boundary; these choices give to different bulk polarization and surface charges but compensate such that the electric field and energy are independent of the choice of unit cell.

cond-mat.mtrl-sci↗
arXiv2026

Galaxy Light profile neural Networks (GaLNets). II. Bulge-Disc decomposition in optical space-based observations

Bulge-disk (B-D) decomposition is an effective diagnostic to characterize the galaxy morphology and understand its evolution across time. So far, high-quality data have allowed detailed B-D decomposition to redshift below 0.5, with limited excursions over small volumes at higher redshifts. Next-generation large sky space surveys in optical, e.g. from the China Space Station Telescope (CSST), and near-infrared, e.g. from the space EUCLID mission, will produce a gigantic leap in these studies as they will provide deep, high-quality photometric images over more than 15000 deg2 of the sky, including billions of galaxies. Here, we extend the use of the Galaxy Light profile neural Network (GaLNet) to predict 2-Sérsic model parameters, specifically from CSST data. We simulate point-spread function (PSF) convolved galaxies, with realistic B-D parameter distributions, on CSST mock observations to train the new GaLNet and predict the structural parameters (e.g. magnitude, effective radius, Sersic index, axis ratio, etc.) of both bulge and disk components. We find that the GaLNet can achieve very good accuracy for most of the B-D parameters down to an $r$-band magnitude of 23.5 and redshift $\sim$1. The best accuracy is obtained for magnitudes, implying accurate bulge-to-total (B/T) estimates. To further forecast the CSST performances, we also discuss the results of the 1-Sérsic GaLNet and show that CSST half-depth data will allow us to derive accurate 1-component models up to $r\sim$24 and redshift z$\sim$1.7.

astro-ph.GA↗
arXiv2026

DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model

All-in-One image restoration aims to address multiple image degradation problems using a single model, offering a more practical and versatile solution compared to designing dedicated models for each degradation type. Existing approaches typically rely on Degradation-specific models or coarse-grained degradation prompts to guide image restoration. However, they lack fine-grained modeling of degradation information and face limitations in balancing multi-task conflicts. To overcome these limitations, we propose DPMambaIR, a novel All-in-One image restoration framework that introduces a fine-grained degradation extractor and a Degradation-Aware Prompt State Space Model (DP-SSM). The DP-SSM leverages the fine-grained degradation features captured by the extractor as dynamic prompts, which are then incorporated into the state space modeling process. This enhances the model's adaptability to diverse degradation types, while a complementary High-Frequency Enhancement Block (HEB) recovers local high-frequency details. Extensive experiments on a mixed dataset containing seven degradation types show that DPMambaIR achieves the best performance, with 27.69dB and 0.893 in PSNR and SSIM, respectively. These results highlight the potential and superiority of DPMambaIR as a unified solution for All-in-One image restoration.

cs.CV↗
arXiv2026

Thinking inside the Convolution for Image Inpainting: Reconstructing Texture via Structure under Global and Local Side

Image inpainting has earned substantial progress, owing to the encoder-and-decoder pipeline, which is benefited from the Convolutional Neural Networks (CNNs) with convolutional downsampling to inpaint the masked regions semantically from the known regions within the encoder, coupled with an upsampling process from the decoder for final inpainting output. Recent studies intuitively identify the high-frequency structure and low-frequency texture to be extracted by CNNs from the encoder, and subsequently for a desirable upsampling recovery. However, the existing arts inevitably overlook the information loss for both structure and texture feature maps during the convolutional downsampling process, hence suffer from a non-ideal upsampling output. In this paper, we systematically answer whether and how the structure and texture feature map can mutually help to alleviate the information loss during the convolutional downsampling. Given the structure and texture feature maps, we adopt the statistical normalization and denormalization strategy for the reconstruction guidance during the convolutional downsampling process. The extensive experimental results validate its advantages to the state-of-the-arts over the images from low-to-high resolutions including 256*256 and 512*512, especially holds by substituting all the encoders by ours. Our code is available at https://github.com/htyjers/ConvInpaint-TSGL

cs.CV↗
arXiv2026

To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series

The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass. While efficient, this rigid coupling of output and evaluation horizons necessitates computationally prohibitive re-training for every target horizon. In this work, we uncover a counter-intuitive optimization anomaly: models trained on short horizons-when coupled with our proposed Evolutionary Forecasting (EF) paradigm-significantly outperform those trained directly on long horizons. We attribute this success to the mitigation of a fundamental optimization pathology inherent in DF, where conflicting gradients from distant futures cripple the learning of local dynamics. We establish EF as a unified generative framework, proving that DF is merely a degenerate special case of EF. Extensive experiments demonstrate that a singular EF model surpasses task-specific DF ensembles across standard benchmarks and exhibits robust asymptotic stability in extreme extrapolation. This work propels a paradigm shift in LTSF: moving from passive Static Mapping to autonomous Evolutionary Reasoning.

cs.LG↗
arXiv2026

Planning-Augmented Sampling with Early Guidance for High-Reward Discovery

Generative Flow Networks (GFlowNets) enable structured generation with inherent diversity, but existing sampling strategies often rely on weak guided exploration, slowing early discovery of high-reward candidates. In tasks such as molecular design, rapid and consistent generation of high-reward solutions can outweigh faithful distribution matching. We propose a planning-augmented framework in which Monte Carlo Tree Search using polynomial upper confidence bounds provides online value estimates, and a controllable soft-greedy mechanism integrates these planning signals into the GFlowNets forward policy. This design fosters early exploration of high-reward trajectories and gradually shifts to policy-driven exploitation as experience accumulates. Empirical results show that our method accelerates early high-reward discovery, sustains top-quality sample generation, and preserves diversity across representative tasks. All implementations are available at https://github.com/ZRNB/PLUS.

cs.LG↗
arXiv2026

QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting

Accurate forecasting of sequential data streams is a cornerstone of modern Web services, supporting applications such as traffic management, user behavior modeling, and online anomaly prevention. However, in many Web environments, new domains emerge rapidly and labeled history data is scarce, which makes zero-shot forecasting particularly challenging. Existing time-series pre-trained models (TSPMs) show promise but they lack the ability to dynamically incorporate external knowledge, while conventional retrieval-augmented generation (RAG) methods are rarely extended beyond text. In this work, we present \textbf{QuiZSF}, a retrieval-augmented forecasting framework that integrates search and forecasting for time series data. The framework performs search by retrieving structurally similar sequences from a large-scale time-series database, and it performs forecasting by integrating the retrieved knowledge into the target sequence. Specifically, QuiZSF introduces a \textbf{ChronoRAG Base}, a hierarchical tree-structured database that enables scalable and domain-aware retrieval, a \textbf{Multi-grained Series Interaction Learner} that captures fine- and coarse-grained dependencies between target and retrieved sequences, and a \textbf{Model Cooperation Coherer} that adapts retrieved knowledge to TSPMs. This design teaches models to actively perform search, align auxiliary information across modalities, and leverage it for more accurate forecasting. Extensive experiments on five public benchmarks demonstrate that QuiZSF consistently outperforms strong baselines, ranking first in up to \textbf{87.5\%} of zero-shot forecasting settings while maintaining high efficiency.

cs.LG↗
arXiv2026

Training LLMs with Fault Tolerant HSDP on 100,000 GPUs

Large-scale training systems typically use synchronous training, requiring all GPUs to be healthy simultaneously. In our experience training on O(100K) GPUs, synchronous training results in a low efficiency due to frequent failures and long recovery time. To address this problem, we propose a novel training paradigm, Fault Tolerant Hybrid-Shared Data Parallelism (FT-HSDP). FT-HSDP uses data parallel replicas as units of fault tolerance. When failures occur, only a single data-parallel replica containing the failed GPU or server is taken offline and restarted, while the other replicas continue training. To realize this idea at scale, FT-HSDP incorporates several techniques: 1) We introduce a Fault Tolerant All Reduce (FTAR) protocol for gradient exchange across data parallel replicas. FTAR relies on the CPU to drive the complex control logic for tasks like adding or removing participants dynamically, and relies on GPU to perform data transfer for best performance. 2) We introduce a non-blocking catch-up protocol, allowing a recovering replica to join training with minimal stall. Compared with fully synchronous training at O(100K) GPUs, FT-HSDP can reduce the stall time due to failure recovery from 10 minutes to 3 minutes, increasing effective training time from 44\% to 80\%. We further demonstrate that FT-HSDP's asynchronous recovery does not bring any meaning degradation to the accuracy of the result model.

cs.DC↗
arXiv2026

A General ReLearner: Empowering Spatiotemporal Prediction by Re-learning Input-label Residual

Prevailing spatiotemporal prediction models typically operate under a forward (unidirectional) learning paradigm, in which models extract spatiotemporal features from historical observation input and map them to target spatiotemporal space for future forecasting (label). However, these models frequently exhibit suboptimal performance when spatiotemporal discrepancies exist between inputs and labels, for instance, when nodes with similar time-series inputs manifest distinct future labels, or vice versa. To address this limitation, we propose explicitly incorporating label features during the training phase. Specifically, we introduce the Spatiotemporal Residual Theorem, which generalizes the conventional unidirectional spatiotemporal prediction paradigm into a bidirectional learning framework. Building upon this theoretical foundation, we design an universal module, termed ReLearner, which seamlessly augments Spatiotemporal Neural Networks (STNNs) with a bidirectional learning capability via an auxiliary inverse learning process. In this process, the model relearns the spatiotemporal feature residuals between input data and future data. The proposed ReLearner comprises two critical components: (1) a Residual Learning Module, designed to effectively disentangle spatiotemporal feature discrepancies between input and label representations; and (2) a Residual Smoothing Module, employed to smooth residual terms and facilitate stable convergence. Extensive experiments conducted on 11 real-world datasets across 14 backbone models demonstrate that ReLearner significantly enhances the predictive performance of existing STNNs.Our code is available on GitHub.

cs.LG↗
arXiv2026

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental rewards to learn stronger policies, such as GRPO-style optimization. However, applying on-policy RL to MAS remains underexplored and presents unique challenges. Algorithmically, standard GRPO grouping assumptions break down because prompts vary by role and by turn. System-wise, the training stack must support MAS-workflow rollouts and on-policy updates for both single-policy and multi-policy models. We propose AT-GRPO, which includes (i) an agent- and turn-wise grouped RL algorithm tailored to MAS and (ii) a training system that supports both single- and multi-policy regimes. Across game, planning, coding, and math tasks, AT-GRPO delivers substantial gains. On long-horizon planning, it increases accuracy from a 14.0 to 47.0 percent single-agent RL baseline to 96.0 to 99.5 percent. It also improves reasoning performance, with average gains of 3.87 to 7.62 percent on coding tasks and 9.0 to 17.93 percent on math. Code and environments are available at: https://github.com/pettingllms-ai/PettingLLMs.

cs.LG↗
arXiv2026

Learning Provably Correct Distributed Protocols Without Human Knowledge

Provably correct distributed protocols, which are a critical component of modern distributed systems, are highly challenging to design and have often required decades of human effort. These protocols allow multiple agents to coordinate to come to a common agreement in an environment with uncertainty and failures. We formulate protocol design as a search problem over strategies in a game with imperfect information, and the desired correctness conditions are specified in Satisfiability Modulo Theories (SMT). However, standard methods for solving multi-agent games fail to learn correct protocols in this setting, even when the number of agents is small. We propose a learning framework, GGMS, which integrates a specialized variant of Monte Carlo Tree Search with a transformer-based action encoder, a global depth-first search to break out of local minima, and repeated feedback from a model checker. Protocols output by GGMS are verified correct via exhaustive model checking for all executions within the bounded setting. We further prove that, under mild assumptions, the search process is complete: if a correct protocol exists, GGMS will eventually find it. In experiments, we show that GGMS can learn correct protocols for larger settings than existing methods.

cs.AI↗
arXiv2026

One latent to fit them all: a unified representation of baryonic feedback on matter distribution

Accurate and parsimonious quantification of baryonic feedback on matter distribution is of crucial importance for understanding both cosmology and galaxy formation from observational data. This is, however, challenging given the large discrepancy among different models of galaxy formation simulations, and their distinct subgrid physics parameterizations. Using 5,072 simulations from 4 different models covering broad ranges in their parameter spaces, we find a unified 2D latent representation. Compared to the simulations and other phenomenological models, our representation is independent of both time and cosmology, much lower-dimensional, and disentangled in its impacts on the matter power spectra. The common latent space facilitates the comparison of parameter spaces of different models and is readily interpretable by correlation with each. The two latent dimensions provide a complementary representation of baryonic effects, linking black hole and supernova feedback to distinct and interpretable impacts on both the matter power spectrum, and field, level. Our approach enables developing robust and economical analytic models for optimal gain of physical information from data, and is generalizable to other fields with significant modeling uncertainty.

astro-ph.CO↗
arXiv2026

AgentAsk: Multi-Agent Systems Need to Ask

Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message handoffs.In this work, we conduct a systematic empirical analysis of such failures and introduce an edge-level error taxonomy that identifies four dominant error types: Data Gap, Signal Corruption, Referential Drift, and Capability Gap, as primary sources of failure in multi-agent interactions. Building on this taxonomy, we propose AgentAsk, a lightweight clarification module designed to intervene at the edge level in MAS to prevent cascading errors. The module operates by strategically applying minimal clarifications at critical points within the system, improving the accuracy and efficiency of the overall task. AgentAsk is trained to balance the trade-offs between clarification cost, latency, and accuracy, while it is also architecture-agnostic and can be easily integrated into existing systems. Evaluated across five benchmarks, AgentAsk consistently improves accuracy by up to 4.69%, while keeping latency and extra costs below 10% compared to baseline MAS, showcasing its high efficiency and minimal overhead.

cs.AI↗