Searcharxiv⌕ Search

arXiv subjects

Yuwei Huang

Publications and source records attributed to Yuwei Huang.

18 recordsLinked to original sources
arXiv2026

Detection of Doppler velocity differences between ions and neutrals in an erupting prominence

We performed a spectroscopic observation of an erupting prominence occurred on the solar limb on 2015 May 8th in He I 706.5 nm, O I 777.2 nm triplet and Ca II 849.8 nm lines to investigate differences in the Doppler velocity between ions and neutrals in a plasma strongly accelerated by the Lorentz force. We found that the ion-neutral velocity difference between Ca II and He I reached an order of 15 km s-1. On the other hand, the velocity difference between Ca II and O I was significantly smaller than that between Ca II and He I. This result can be interpreted as the formation of O I 777.2 nm lines in the erupting prominence is mainly contributed by the recombination from O II ions through charge transfer with hydrogen atoms, resulting in a behavior close to ions. According to an order estimate of the collisional friction among He I atoms and protons, the observed velocity difference between Ca II and He I implies the acceleration of the eruption reaching about 150 times of solar gravity. We propose a new method to evaluate the ionization degree of hydrogen from the velocity differences observed in Ca II, He I and O I lines.

astro-ph.SR↗
arXiv2026

Source localization realizes single frame super-resolution for fluorescence imaging

Existing super-resolution microscopy is often constrained by inherent trade-offs between resolution, acquisition speed, phototoxicity, and hardware complexity. Computational post-processing approaches offer a promising alternative, but they typically suffer from linearity distortion, high computational cost, reliance on pre-training data, or reconstruction artifacts. Here, we present Source Localization (SoLo), a novel single-frame super-resolution algorithm for fluorescence imaging without these limitations. Built on the principle of inferring fluorescent source positions via sampling-detection strategy, SoLo achieves non-iterative, parallelizable computation, enabling real-time live-cell imaging with high spatiotemporal resolution. The intensity linearity preservation of SoLo makes it compatible with quantitative analysis such as calcium imaging and fluorescence resonance energy transfer. We further extended this framework to 3D-SoLo for volumetric imaging and nonlinear SoLo (NL-SoLo) for high-density fluorescence fluctuation imaging. With its ease of parameter tuning and compatibility with existing imaging systems, SoLo offers an accessible solution for ordinary labs, enabling diverse biomedical imaging applications.

physics.optics↗
arXiv2025

Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE

We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this size exposes critical inefficiencies-zero-variance prompts that waste rollouts, unstable importance sampling over long horizons, advantage inversion from standard reward models, and systemic bottlenecks in rollout processing. To overcome these challenges, we introduce several unified innovations: (1) Multi-Stage Zero-Variance Elimination, which filters out non-informative prompts and stabilizes group-based policy optimization (e.g. GRPO) by removing wasted rollouts; (2) ESPO, an entropy-adaptive optimization method that balances token-level and sequence-level importance sampling to maintain stable learning dynamics; (3) a Router Replay strategy that aligns training-time MoE router decisions with inference-time behavior to mitigate train-infer discrepancies, coupled with a reward model adjustment to prevent advantage inversion; (4) a high-throughput RL system with FP8-precision rollouts, overlapped reward computation, and length-aware scheduling to eliminate performance bottlenecks. Together, these contributions form a cohesive pipeline that makes RL on hundred-billion-scale MoE models stable and efficient. The resulting model delivers strong performance across both internal and public evaluations.

cs.AI↗
arXiv2025

ESPO: Entropy Importance Sampling Policy Optimization

Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving performance at scale often introduces a fundamental trade-off between training stability and training efficiency. Token-level optimization applies fine-grained updates at the individual units, but is prone to high variance in gradient estimation, which can result in unstable training dynamics. In contrast, Sequence-level optimization often relies on aggressive clipping mechanisms to ensure stable updates. However, such design may discard a large fraction of valid training samples, leading to inefficient gradient utilization and reduced training efficiency. We refer to this phenomenon as gradient underutilization. In this work, we propose Entropy Importance Sampling Policy Optimization (ESPO), a novel framework that aims to combine fine-grained updates with stable training. ESPO decomposes sequences into groups based on predictive entropy, enabling (1) Entropy Grouping Importance Sampling to capture intra-sequence heterogeneity, and (2) Entropy Adaptive Clipping to dynamically allocate trust regions based on model uncertainty. Extensive experiments on mathematical reasoning benchmarks demonstrate that ESPO not only accelerates convergence but also achieves state-of-the-art performance, notably improving accuracy on the challenging mathematical benchmarks.

cs.LG↗
arXiv2025

Compass-Thinker-7B Technical Report

Recent R1-Zero-like research further demonstrates that reasoning extension has given large language models (LLMs) unprecedented reasoning capabilities, and Reinforcement Learning is the core technology to elicit its complex reasoning. However, conducting RL experiments directly on hyperscale models involves high computational costs and resource demands, posing significant risks. We propose the Compass-Thinker-7B model, which aims to explore the potential of Reinforcement Learning with less computational resources and costs, and provides insights for further research into RL recipes for larger models. Compass-Thinker-7B is trained from an open source model through a specially designed Reinforcement Learning Pipeline. We curate a dataset of 30k verifiable mathematics problems for the Reinforcement Learning Pipeline. By configuring data and training settings with different difficulty distributions for different stages, the potential of the model is gradually released and the training efficiency is improved. Extensive evaluations show that Compass-Thinker-7B possesses exceptional reasoning potential, and achieves superior performance on mathematics compared to the same-sized RL model. Especially in the challenging AIME2024 evaluation, Compass-Thinker-7B achieves 40% accuracy.

cs.AI↗
arXiv2024

High SNR 3D Imaging from Millimeter-scale Thick Tissues to Cellular Dynamics via Structured Illumination Microscopy

Three-dimensional (3D) fluorescence imaging provides a vital approach for study of biological tissues with intricate structures, and optical sectioning structured illumination microscopy (OS-SIM) stands out for its high imaging speed, low phototoxicity and high spatial resolution. However, OS-SIM faces the problem of low signal-to-noise ratio (SNR) when using traditional decoding algorithms, especially in thick tissues. Here we propose a Hilbert-transform decoding and space domain based high-low (HT-SHiLo) algorithm for noise suppression in OS-SIM. We demonstrate HT-SHiLo algorithm can significantly improve the SNR of optical sectioning images at rapid processing speed, and double the imaging depth in thick tissues. With our OS-SIM system, we achieve high quality 3D images of various biological samples including mouse brains, Drosophila clock neurons, organoids, and live cells. We anticipate that this approach will render OS-SIM a powerful technique for research of cellular organelles or thick tissues in 3D morphology.

physics.optics↗
arXiv2024

Integrating Base Station with Intelligent Surface for 6G Wireless Networks: Architectures, Design Issues, and Future Directions

Intelligent surface (IS) is envisioned as a promising technology for the sixth-generation (6G) wireless networks, which can effectively reconfigure the wireless propagation environment via dynamically controllable signal reflection/transmission. In particular, integrating passive intelligent surface (IS) into the base station (BS) is a novel solution to enhance the wireless network throughput and coverage both cost-effectively and energyefficiently. In this article, we provide an overview of IS-integrated BSs for wireless networks, including their motivations, practical architectures, and main design issues. Moreover, numerical results are presented to compare the performance of different IS-integrated BS architectures as well as the conventional BS without IS. Finally, promising directions are pointed out to stimulate future research on IS-BS/terminal integration in wireless networks.

eess.SP↗
arXiv2024

Terahertz Metamaterial Renormalization of Superconducting Josephson Plasmons in La$_{1.85}$Sr$_{0.15}$CuO$_4$

We investigate light-matter coupling in the cuprate superconductor La$_{1.85}$Sr$_{0.15}$Cu0$_4$ (LSCO), accomplished by adhering metamaterial resonator arrays (MRAs) to a c-axis oriented single crystal. The resonators couple to the Josephson Plasma Mode (JPM) which manifests as a plasma edge in the terahertz reflectivity in the superconducting state. Terahertz reflectivity measurements at 10K reveal a renormalization of the JPM frequency, $\omega_{jpm}$, from 1.7 THz for the bare crystal to $\sim$1 THz with the MRAs. With increasing temperature, the modified $\omega_{jpm}$ redshifts as expected for decreasing superfluid density, vanishing above T$_{c}$. The modification of the electrodynamic response arises from resonator induced screening of the longitudinal polariton response, reminiscent of plasmon-phonon coupling in doped semiconductors. Modeling reveals that the electrodynamic response is fully interpretable using classical electromagnetism. Future studies will have to contend with the large effects we observe which could obscure subtle changes that may indicate cavity-based manipulation of superconductivity. Finally, we note that our MRA/LSCO structure is a tunable epsilon-near-zero (ENZ) metamaterial that exhibits a nonlinear response arising from the c-axis Josephson tunneling coupled with the local fields of the resonators.

cond-mat.supr-con↗
arXiv2023

Passive Reflection Codebook Design for IRS-Integrated Access Point

Intelligent reflecting surface (IRS) has emerged as a promising technique to extend the wireless signal coverage of access point (AP) and improve the communication performance cost-effectively. In order to reduce the path-loss of the cascaded user-IRS-AP channels, the IRS-integrated AP architecture has been proposed to deploy the IRSs and the antenna array of the AP within the same antenna radome. To reduce the pilot overhead for estimating all IRS-involved channels, in this paper, we propose a novel codebook-based IRS reflection design for the IRS-integrated AP to enhance the coverage performance in a given area. In particular, the codebook consisting of a small number of codewords is designed offline by employing an efficient sector division strategy based on the azimuth angle. To ensure the performance of each sector, we optimize its corresponding codeword for IRS reflection pattern to maximize the sector-min-average-effective-channel-power (SMAECP) by applying the alternating optimization (AO) and semidefinite relaxation (SDR) methods. With the designed codebook, the AP performs the IRS reflection training by sequentially applying all codewords and selects the one achieving the best communication performance for data transmission. Numerical results show that our proposed codebook design can enhance the average channel power of the whole coverage area, as compared to the system without IRS. Moreover, our proposed codebook-based IRS reflection design is shown to achieve significant performance gain over other benchmark schemes in both single-user and multi-user transmissions.

cs.IT↗
arXiv2022

PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization

In this paper, we present an open-source pure-Python library called PyPop7 for black-box optimization (BBO). As population-based methods (e.g., evolutionary algorithms, swarm intelligence, and pattern search) become increasingly popular for BBO, the design goal of PyPop7 is to provide a unified API and elegant implementations for them, particularly in challenging high-dimensional scenarios. Since these population-based methods easily suffer from the notorious curse of dimensionality owing to random sampling as one of core operations for most of them, recently various improvements and enhancements have been proposed to alleviate this issue more or less mainly via exploiting possible problem structures: such as, decomposition of search distribution or space, low-memory approximation, low-rank metric learning, variance reduction, ensemble of random subspaces, model self-adaptation, and fitness smoothing. These novel sampling strategies could better exploit different problem structures in high-dimensional search space and therefore they often result in faster rates of convergence and/or better qualities of solution for large-scale BBO. Now PyPop7 has covered many of these important advances on a set of well-established BBO algorithm families and also provided an open-access interface to adding the latest or missed black-box optimizers for further functionality extensions. Its well-designed source code (under GPL-3.0 license) and full-fledged online documents (under CC-BY 4.0 license) have been freely available at \url{https://github.com/Evolutionary-Intelligence/pypop} and \url{https://pypop.readthedocs.io}, respectively.

cs.NE↗
arXiv2022

Integrating Intelligent Reflecting Surface into Base Station: Architecture, Channel Model, and Passive Reflection Design

Existing works on IRS have mainly considered IRS being deployed in the environment to dynamically control the wireless channels between the BS and its served users. In contrast, we propose in this paper a new integrated IRS BS architecture by deploying IRSs inside the BS antenna radome. Since the distance between the integrated IRSs and BS antenna array is practically small, the path loss among them is significantly reduced and the real time control of the IRS reflection by the BS becomes easier to implement. However, the resultant near field channel model also becomes drastically different. Thus, we propose an element wise channel model for IRS to characterize the channel vector between each single antenna user and the antenna array of the BS, which includes the direct (without any IRS reflection) as well as the single and double IRS-reflection channel components. Then, we formulate a problem to optimize the reflection coefficients of all IRS reflecting elements for maximizing the uplink sum rate of the users. By considering two typical cases with/without perfect CSI at the BS, the formulated problem is solved efficiently by adopting the successive refinement method and iterative random phase algorithm (IRPA), respectively. Numerical results validate the substantial capacity gain of the integrated IRS BS architecture over the conventional multi antenna BS without integrated IRS. Moreover, the proposed algorithms significantly outperform other benchmark schemes in terms of sum rate, and the IRPA without CSI can approach the performance upper bound with perfect CSI as the training overhead increases.

cs.IT↗
arXiv2022

Complementary Vanadium Dioxide Metamaterials with Enhanced Modulation Amplitude at Terahertz Frequencies

One route to create tunable metamaterials is through integration with "on-demand" dynamic quantum materials, such as vanadium dioxide (VO2). This enables new modalities to create high performance devices for historically challenging applications. Indeed, dynamic materials have often been integrated with metamaterials to imbue artificial structures with some degree of tunability. Conversely, metamaterials can be used to enhance and extend the natural tuning range of dynamic materials. Utilizing a complementary split ring resonator array deposited on a VO2 film, we demonstrate enhanced terahertz transmission modulation upon traversing the insulator-to-metal transition (IMT) at ~340 K. Our complementary metamaterial increases the modulation amplitude of the original VO2 film from 42% to 68.3% at 0.47 THz upon crossing the IMT, corresponding to an enhancement of 62.4%. Moreover, temperature dependent transmission measurements reveal a redshift of the resonant frequency arising from a giant increase of the permittivity of the VO2 film. Maxwell-Garnett effective medium theory was employed to explain the permittivity change upon transitioning through the IMT. Our results highlight that symbiotic integration of metamaterial arrays with quantum materials provides a powerful approach to engineer emergent functionality.

physics.app-ph↗
arXiv2022

Empowering Base Stations with Co-Site Intelligent Reflecting Surfaces: User Association, Channel Estimation and Reflection Optimization

Intelligent reflecting surface (IRS) has emerged as a promising technique to enhance wireless communication performance cost effectively. The existing literature has mainly considered IRS being deployed near user terminals to improve their performance. However, this approach may incur a high cost if IRSs need to be densely deployed in the network to cater to random user locations. To avoid such high deployment cost, in this paper we consider a new IRS aided wireless network architecture, where IRSs are deployed in the vicinity of each base station (BS) to assist in its communications with distributed users regardless of their locations. Besides significantly enhancing IRSs' signal coverage, this scheme helps reduce the IRS associated channel estimation overhead as compared to conventional user-side IRSs, by exploiting the nearly static BS-IRS channels over short distance. For this scheme, we propose a new two stage transmission protocol to achieve IRS channel estimation and reflection optimization for uplink data transmission efficiently. In addition, we propose effective methods for solving the user IRS association problem based on long term channel knowledge and the selected user IRS BS cascaded channel estimation problem. Finally, all IRSs' passive reflections are jointly optimized with the BS's multi-antenna receive combining to maximize the minimum achievable rate among all users for data transmission. Numerical results show that the proposed co site IRS empowered BS scheme can achieve significant performance gains over the conventional BS without co site IRS and existing schemes for IRS channel estimation and reflection optimization, thus enabling an appealing low cost and high performance BS design for future wireless networks.

cs.IT↗
arXiv2020

Statistical Analysis of the Relation between Coronal Mass Ejections and Solar Energetic Particles

To improve the forecasting capability of impactful solar energetic particle (SEP) events, the relation between coronal mass ejections (CMEs) and SEP events needs to be better understood. Here we present a statistical study of SEP occurrences and timescales with respect to the CME source locations and speeds, considering all 257 fast ($v_{CME}$ $\ge$ 900 km/s) and wide (angular width $\ge$ 60$^{\circ}$) CMEs that occurred between December 2006 and October 2017. We associate them with SEP events at energies above 10 MeV. Examination of the source region of each CME reveals that CMEs more often accompany a SEP event if they originate from the longitude of E20-W100 relative to the observer. However, a SEP event could still be absent if the CME is $<$ 2000 km/s. For the associated CME-SEP pairs, we compute three timescales for each of the SEP events, following Kahler (2005, 2013); namely the timescale of the onset (TO), the rise time (TR), and the duration (TD). They are correlated with the longitude of the CME source region relative to the footpoint of the Parker spiral ($ΔΦ$) and $v_{CME}$. The TO tends to be short for $|ΔΦ|$ $<$ 60$^{\circ}$ . This trend is weaker for TR and TD. The SEP timescales are only weakly correlated with $v_{CME}$. Positive correlations of both TR and TD with $v_{CME}$ are seen in poorly connected (large $|ΔΦ|$) events. Additionally, TO appears to be negatively correlated with $v_{CME}$ for events with small $|ΔΦ|$.

astro-ph.SR↗
arXiv2020

Online Maneuver Design for UAV-Enabled NOMA Systems via Reinforcement Learning

This paper considers an unmanned aerial vehicle enabled-up link non-orthogonal multiple-access system, where multiple mobile users on the ground send independent messages to a unmanned aerial vehicle in the sky via non-orthogonal multiple-access transmission. Our objective is to design the unmanned aerial vehicle dynamic maneuver for maximizing the sum-rate throughput of all mobile ground users over a finite time horizon.

cs.IT↗
arXiv2019

Cognitive UAV Communication via Joint Maneuver and Power Control

This paper investigates a new scenario of spectrum sharing between unmanned aerial vehicle (UAV) and terrestrial wireless communication, in which a cognitive/secondary UAV transmitter communicates with a ground secondary receiver (SR), in the presence of a number of primary terrestrial communication links that operate over the same frequency band. We exploit the UAV's mobility in three-dimensional (3D) space to improve its cognitive communication performance while controlling the co-channel interference at the primary receivers (PRs), such that the received interference power at each PR is below a prescribed threshold termed as interference temperature (IT). First, we consider the quasi-stationary UAV scenario, where the UAV is placed at a static location during each communication period of interest. In this case, we jointly optimize the UAV's 3D placement and power control to maximize the SR's achievable rate, subject to the UAV's altitude and transmit power constraints, as well as a set of IT constraints at the PRs to protect their communications. Next, we consider the mobile UAV scenario, in which the UAV is dispatched to fly from an initial location to a final location within a given task period. We propose an efficient algorithm to maximize the SR's average achievable rate over this period by jointly optimizing the UAV's 3D trajectory and power control, subject to the additional constraints on UAV's maximum flying speed and initial/final locations. Finally, numerical results are provided to evaluate the performance of the proposed designs for different scenarios, as compared to various benchmark schemes. It is shown that in the quasi-stationary scenario the UAV should be placed at its minimum altitude while in the mobile scenario the UAV should adjust its altitude along with horizontal trajectory, so as to maximize the SR's achievable rate in both scenarios.

cs.IT↗
arXiv2018

Cognitive UAV Communication via Joint Trajectory and Power Control

This paper investigates a new spectrum sharing scenario between unmanned aerial vehicle (UAV) and terrestrial wireless communication systems. We consider that a cognitive/secondary UAV transmitter communicates with a ground secondary receiver (SR), in the presence of a number of primary terrestrial communication links that operate over the same frequency band. We exploit the UAV's controllable mobility via trajectory design, to improve the cognitive UAV communication performance while controlling the co-channel interference at each of the primary receivers (PRs). In particular, we maximize the average achievable rate from the UAV to the SR over a finite mission/communication period by jointly optimizing the UAV trajectory and transmit power allocation, subject to constraints on the UAV's maximum speed, initial/final locations, and average transmit power, as well as a set of interference temperature (IT) constraints imposed at each of the PRs for protecting their communications. However, the joint trajectory and power optimization problem is non-convex and thus difficult to be solved optimally. To tackle this problem, we propose an efficient algorithm that ensures to obtain a locally optimal solution by applying the techniques of alternating optimization and successive convex approximation (SCA). Numerical results show that our proposed joint UAV trajectory and power control scheme significantly enhances the achievable rate of the cognitive UAV communication system, as compared to benchmark schemes.

eess.SP↗