arXiv subjects

Yicheng Wang

Publications and source records attributed to Yicheng Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Wafer-scale integration of single nanodiamonds via electrostatic-trapping

Nanodiamonds (NDs) are key materials for building nanoscale quantum sensing, imaging and communication devices. Scalable configuration of single NDs on heterogeneous platforms, forming photonic quantum source arrays, will be an essential solution towards realizing next-generation practical and industrial quantum devices. However, NDs are challenging to manipulate because their size, shape and surface chemistry vary substantially. Here, we show a simple method based on electrostatic-trapping to rapidly and reliably pattern single ND arrays on arbitrary substrates at scale. Our method, which uses carefully engineered microscale hole templates and electrostatic force, captures single NDs across 8-inch wafers with 82.5% yields within 5 min. Systematic experimental and theoretical studies show the number of deposited NDs primarily depends on the diameter of the hole trap. The method is compatible with mature CMOS technologies, enabling the mass production of scalable and integrable quantum devices. This advancement is expected to accelerate the commercialization and industrial adoption of ND-based technologies.

physics.optics↗

arXiv2025

Self-Powered, Ultra-thin, Flexible, and Scalable Ultraviolet Detector Utilizing Diamond-MoS$_2$ Heterojunction

The escalating demand for ultraviolet (UV) sensing in space exploration, environmental monitoring, and agricultural productivity necessitates detectors that are both environmentally and mechanically resilient. Diamond, featuring its high bandgap and UV absorption, exceptional mechanical/chemical robustness, and excellent thermal stability, emerges as a highly promising material for next-generation UV detection in various scenarios. However, conventional diamond-based UV detectors are constrained by rigid bulk architectures and reliance on external power supplies, hindering their integration with curved and flexible platforms and complicating device scalability due to auxiliary power requirements. To tackle these challenges, herein, we firstly demonstrated a large-scale, self-powered, and flexible diamond UV detector by heterogeneously integrating a MoS$_2$ monolayer with an ultrathin, freestanding diamond membrane. The fabricated device operates at zero external bias, and simultaneously exhibits a high responsivity of 94 mA W$^{-1}$ at 220 nm, and detectivity of 5.88 x 109 Jones. Notably, mechanical bending enables strain-induced bandgap modulation of the diamond membrane, allowing dynamically tunable photoresponse-a capability absent in rigid diamond counterparts. To validate its practicality and scalability, a proof-of-concept UV imager with 3x3 pixels was demonstrated. This newly developed configuration will undoubtedly open up new routes toward scalable, integrable, flexible, and cost-effective UV sensing solutions for emerging technologies

physics.ins-det↗

arXiv2025

Laser-driven few-cycle Terahertz sources with high average power

Ultrafast laser-driven terahertz sources are gaining in popularity in an increasingly wide range of scientific and technological applications. However, many fields continue to be severely limited by the typically low average power of these sources, which restricts speed, signal-to-noise ratio, and dynamic range in numerous measurements. Conversely, the past two decades have seen spectacular progress in high average power ultrafast laser technology based on Ytterbium lasers, rendering hundreds of watts to kilowatts of average power available to this community to drive THz sources. This has opened the young field of high-average-power laserdriven THz time-domain spectroscopy, which holds the potential to revolutionize the applications of THz time-domain systems. In this perspective article, we discuss this young field and emphasize recent advancements in broadband terahertz sources utilizing high-power Yb-based ultrafast lasers as drivers, which are nearing watt-level average power. We discuss various approaches explored thus far, current challenges, prospects for scaling, and future research areas that will accelerate their implementation in applications.

physics.optics↗

arXiv2025

Exclusive Style Removal for Cross Domain Novel Class Discovery

As a promising field in open-world learning, \textit{Novel Class Discovery} (NCD) is usually a task to cluster unseen novel classes in an unlabeled set based on the prior knowledge of labeled data within the same domain. However, the performance of existing NCD methods could be severely compromised when novel classes are sampled from a different distribution with the labeled ones. In this paper, we explore and establish the solvability of NCD with cross domain setting under the necessary condition that the style information needs to be removed. Based on the theoretical analysis, we introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features, thereby facilitating inference. Moreover, this module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions compared to the labeled set. Additionally, recognizing the non-negligible influence of different backbones and pre-training strategies on the performance of the NCD methods, we build a fair benchmark for future NCD research. Extensive experiments on three common datasets demonstrate the effectiveness of our proposed style removal strategy.

cs.CV↗

arXiv2025

New cosmological constraints on the evolution of dark matter energy density

We constrain the evolution of dark matter energy density over time, specifically focusing on deviation from the standard model represented by the equation $ρ_{m}\propto(1+z)^{3-\varepsilon}$, where $\varepsilon$ is a constant parameter. Utilizing a diverse array of observational datasets, including baryon acoustic oscillations (BAO) data from the first release of the Dark Energy Spectroscopic Instrument (DESI), distance priors derived from cosmic microwave background (CMB) observations by the Planck satellite, Hubble rate data obtained through the cosmic chronometers (CC) method, type Ia supernova (SNIa) data from the Panthon sample, and the data from the redshift space distortion (RSD) measurements ($fσ_8$), we derive stringent constraints on the deviation parameter. We find that for the model under consideration, the deviation parameter is constrained to be $\varepsilon = -0.0073^{+0.0029}_{-0.0033}$, indicating a deviation of approximately $2.4σ$ from the scenario where dark matter and vacuum dark energy do not interact. When compared with previous studies and alternative analyses, our findings provide corroborative evidence for an interaction between dark matter and vacuum dark energy, particularly in light of the release of BAO data from DESI.

astro-ph.CO↗

arXiv2025

Energy scaling of Kerr-lens modelocked Ho:YAG thin-disk oscillators to the microjoule level

We demonstrate peak power and pulse energy scaling of Kerr-lens modelocking (KLM) Ho:YAG thin-disk lasers (TDLs) emitting at 2.1-μm wavelength. We compare different laser configurations to reach a maximum pulse energy of 1.7 μJ at an output power of 29 W with a pulse duration of 434 fs, corresponding to a peak power of 3.7 MW. This represents a 5-fold increase in pulse energy and 4-fold increase in peak power compared to previous KLM Ho:YAG TDLs, thus reaching record high peak power for 2.1-μm mode-locked oscillators. We discuss current limitations at this wavelength and guidelines for future work towards higher power and pulse energies.

physics.optics↗

arXiv2025

Cosmological constraints on two vacuum decay models

We constrain two vacuum decay models ($Λ(t)$CDM, proposed by the authors of~\cite{Brito:2024bhh}) utilizing the baryon acoustic oscillations (BAO) data released by the Dark Energy Spectroscopic Instrument (DESI), distance prior from the cosmic microwave background (CMB) observed by the Planck satellite, Hubble rate data obtained via the cosmic chronometers (CC) method and type Ia supernova (SNIa) data. The interaction terms between dark matter and dark energy are defined as $Q=3\varepsilon Hρ_Λ$ for model I and $3\varepsilon aHρ_Λ$ for model II. We find that the decay parameter is constrained to be $\varepsilon=0.0094^{+0.0037}_{-0.0033}$ for model I and $\varepsilon=0.0119\pm{0.0045}$ for model II, respectively, indicating a potential interaction between dark matter and dark energy at the $2σ$ confidence level. The current Hubble parameter values are estimated to be $H_{0}=70.30\pm{0.67}$ for model I and $H_{0}=70.28\pm{0.64}$ for model II. These values of $H_0$ fall between those derived from the Planck and SH0ES data, suggesting that these two vacuum decay models could provide a potential solution to alleviate the Hubble tension problem.

astro-ph.CO↗

arXiv2025

DHP Benchmark: Are LLMs Good NLG Evaluators?

Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks; this is often referred to as ``LLM-as-a-judge'' paradigm. However, the capabilities of LLMs in evaluating NLG quality remain underexplored. Current studies depend on human assessments and simple metrics that fail to capture the discernment of LLMs across diverse NLG tasks. To address this gap, we propose the Discernment of Hierarchical Perturbation (DHP) benchmarking framework, which provides quantitative discernment scores for LLMs. This framework leverages hierarchically perturbed text data and statistical tests to systematically measure the NLG evaluation capabilities of LLMs. We re-established six evaluation datasets for this benchmark, covering four NLG tasks: Summarization, Story Completion, Question Answering, and Translation. Our comprehensive benchmarking of five major LLM families provides critical insight into their strengths and limitations as NLG evaluators. Our dataset is available at https://huggingface.co/datasets/YCWANGVINCE/DHP_Benchmark.

cs.CL↗

arXiv2025

Universal Wong formula for capture cross sections from light to super-heavy systems

A universal Wong formula is proposed with refined model parameters for a systematic description of the capture cross sections for heavy-ion fusion reactions from C+C to Ni+U, in which the barrier parameters and the barrier distribution are determined by the entrance-channel nucleus-nucleus potential based on the Skyrme energy density functional. With introducing a constraint to the width of the barrier distribution and a pocket-depth dependent barrier radius, the capture excitation functions for a number of fusion reactions involving different nuclear structure effects are remarkably well reproduced, particularly for the reactions between light nuclei and those forming super-heavy nuclei. The systematic decreasing behavior of the geometric radii with the depth of capture pocket due to the influence of deep inelastic scattering is clearly observed in the TDHF calculations for super-heavy systems. The predicted capture cross sections for $^{54}$Cr + $^{238}$U at above barrier energies are evidently smaller than the corresponding results of more asymmetric projectile-target combination $^{50}$Ti + $^{242}$Pu due to the shallower capture pocket in Cr+U.

nucl-th↗

arXiv2025

High peak-power 2.1-μm femtosecond Holmium amplifier at 100 kHz

High-power ultrafast laser sources in the short-wave infrared region are of great interest for numerous applications, including secondary sources of radiation and processing of materials commonly opaque in the near-infrared region. In this wavelength region, direct laser amplification around 2.1-μm wavelength within the atmospheric transparency window is particularly attractive for realizing compact and efficient high-power lasers. However, this wavelength region was widely underrepresented in femtosecond laser technology so far. Here, we report on a 2.1-μm laser system delivering 97-fs pulses with an unprecedented combination of high peak power of 525 MW and high repetition rate of 100 kHz. The amplifier system consists of a mode-locked oscillator seeding a regenerative amplifier (RA) using the novel broadband material Holmium (Ho)-doped CaAlGdO4 (CALGO), operating in the chirped pulse amplification (CPA) scheme and a nonlinear compression stage based on a Herriott-type multi-pass cell (MPC) with bulk material. We demonstrate the potential of this unique laser system by generating a micro plasma in ambient air, demonstrating its high intensity for future plasma-driven secondary sources. This system bridges the gap between conventional 1-to-10 kHz amplifiers and high-power MHz laser oscillators in this attractive wavelength range.

physics.optics↗

arXiv2025

Ytterbium-laser-driven THz generation in thin lithium niobate at 1.9 kW average power in a passive enhancement cavity

Single-cycle, high-power, high-repetition-rate THz pulse sources are becoming the cornerstone of several scientific and industrial applications. A promising and versatile method for high-power THz generation is optical rectification in nonlinear crystals pumped by powerful near-infrared ultrafast laser systems. In this context, ytterbium-based laser sources are particularly advantageous in terms of power scalability and technology establishment. However, as the repetition rate increases toward hundreds of MHz, the conversion efficiency typically decreases, as most laser systems do not reach sufficiently high average power to correspondingly enhance the peak power to drive the nonlinear conversion process efficiently. An alternative approach to achieving sufficiently high average power at high repetition rate is based on passive enhancement cavities, which boost the pulse energy of standard watt-level ytterbium lasers by orders of magnitude. We present the first demonstration of optical rectification in a passive enhancement cavity at multi-kW levels, achieved by a 240-fold power enhancement. By irradiating a 50-$μ$m thin lithium niobate plate with 1.9-kW average power inside the enhancement cavity, we generate milliwatt-level THz pulses with 2-THz bandwidth and 93-MHz repetition rate, mostly limited by the driving pulse duration. To the best of our knowledge, this represents the highest driving average power used for OR. This methodology represents a promising new step towards high-repetition-rate and high average power single-cycle THz sources using widely available multi-watt level Yb lasers.

physics.optics↗

arXiv2024

A versatile method for nano-fabrication on diamond film: flexible diamond metasurfaces as a demonstration

Diamond exhibits superb performance across a wide range of applications due to its enormous outstanding properties in electronic, photonic and quantum fields. Yet heterogeneous integration of diamond for on-chip functionalities, like 2D materials, remains challenging due to the hard acquisition of scalable, transferable and ultrathin diamond samples. Recently, the edge-exposed exfoliation has been demonstrated as an effective way to produce wafer-scale, freestanding and ultrathin diamond films. However, the incompatibility of the newly developed diamond film with conventional nano-fabrication methods makes it difficult to fabricate diamond film into practical devices. Herein, we demonstrate the mask-transferring by sugar as a versatile method for pattern-definition on diamond films, which shows excellent geometrical resolution and accuracy comparing to conventional approaches. Additionally, based on this method, the flexible all-diamond metasurfaces functioning as structural colors have been achieved, which indicates its huge potential for fabricating more diamond-related devices.

physics.optics↗

arXiv2024

GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning

In various video-language learning tasks, the challenge of achieving cross-modality alignment with multi-grained data persists. We propose a method to tackle this challenge from two crucial perspectives: data and modeling. Given the absence of a multi-grained video-text pretraining dataset, we introduce a Granularity EXpansion (GEX) method with Integration and Compression operations to expand the granularity of a single-grained dataset. To better model multi-grained data, we introduce an Iterative Approximation Module (IAM), which embeds multi-grained videos and texts into a unified, low-dimensional semantic space while preserving essential information for cross-modal alignment. Furthermore, GEXIA is highly scalable with no restrictions on the number of video-text granularities for alignment. We evaluate our work on three categories of video tasks across seven benchmark datasets, showcasing state-of-the-art or comparable performance. Remarkably, our model excels in tasks involving long-form video understanding, even though the pretraining dataset only contains short video clips.

cs.CV↗

arXiv2024

High-power single-cycle THz emission from large-area photoconductive emitters at 400 kHz

We report high average power THz emission from a GaAs-based large-area photoconductive emitter, excited by a commercial Yb-laser amplifier without any compression schemes, doubled to the green. The LAE is pumped at 11.4 W of green average power (515 nm) and 310 fs pulse duration at 400-kHz repetition rate. We obtain a maximum THz power of 6.7 mW with a spectrum extended up to 3 THz. Using electro-optic sampling (EOS) for detection, we measure a high dynamic range of 107 dB in a measurement time of 70 s. To the best of our knowledge, this is the highest power THz source so far demonstrated by photoconductive emitters, based on a simple and robust, commercially available Yb-laser.

physics.optics↗

arXiv2024

Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy

Recently, sharpness-aware minimization (SAM) has attracted much attention because of its surprising effectiveness in improving generalization performance. However, compared to stochastic gradient descent (SGD), it is more prone to getting stuck at the saddle points, which as a result may lead to performance degradation. To address this issue, we propose a simple renormalization strategy, dubbed Stable SAM (SSAM), so that the gradient norm of the descent step maintains the same as that of the ascent step. Our strategy is easy to implement and flexible enough to integrate with SAM and its variants, almost at no computational cost. With elementary tools from convex optimization and learning theory, we also conduct a theoretical analysis of sharpness-aware training, revealing that compared to SGD, the effectiveness of SAM is only assured in a limited regime of learning rate. In contrast, we show how SSAM extends this regime of learning rate and then it can consistently perform better than SAM with the minor modification. Finally, we demonstrate the improved performance of SSAM on several representative data sets and tasks.

cs.LG↗

arXiv2024

A digital four-arm bridge for the comparison of resistance with capacitance

We have built and demonstrated a digital four-arm bridge for the comparison of resistance with capacitance. The digital four-arm bridge mimics the classical quad bridge in the digital domain with three balances: the source balance, the detector balance, as well as the main balance. Due to correlation, the required precision of the source voltages is only of the order of the square root of the ultimate bridge precision. For the comparison of a $100\,$k$Ω$ resistor with a $1\,$nF capacitor near 1592 Hz, the combined standard uncertainty $(k = 1)$ is $5\times 10^{-9}$.

physics.ins-det↗

arXiv2024

CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge

While large language models (LLMs) have demonstrated impressive capabilities across various natural language processing tasks by acquiring rich factual knowledge from their broad training data, their ability to synthesize and logically reason with this knowledge in complex ways remains underexplored. In this work, we present a systematic evaluation of state-of-the-art LLMs' complex logical reasoning abilities through a novel benchmark of automatically generated complex reasoning questions over general domain and biomedical knowledge graphs. Our extensive experiments, employing diverse in-context learning techniques, reveal that LLMs excel at reasoning over general world knowledge but face significant challenges with specialized domain-specific knowledge. We find that prompting with explicit Chain-of-Thought demonstrations can substantially improve LLM performance on complex logical reasoning tasks with diverse logical operations. Interestingly, our controlled evaluations uncover an asymmetry where LLMs display proficiency at set union operations, but struggle considerably with set intersections - a key building block of logical reasoning. To foster further work, we will publicly release our evaluation benchmark and code.

cs.CL↗

arXiv2024

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation

Abductive reasoning is the process of making educated guesses to provide explanations for observations. Although many applications require the use of knowledge for explanations, the utilization of abductive reasoning in conjunction with structured knowledge, such as a knowledge graph, remains largely unexplored. To fill this gap, this paper introduces the task of complex logical hypothesis generation, as an initial step towards abductive logical reasoning with KG. In this task, we aim to generate a complex logical hypothesis so that it can explain a set of observations. We find that the supervised trained generative model can generate logical hypotheses that are structurally closer to the reference hypothesis. However, when generalized to unseen observations, this training objective does not guarantee better hypothesis generation. To address this, we introduce the Reinforcement Learning from Knowledge Graph (RLF-KG) method, which minimizes differences between observations and conclusions drawn from generated hypotheses according to the KG. Experiments show that, with RLF-KG's assistance, the generated hypotheses provide better explanations, and achieve state-of-the-art results on three widely used KGs.

cs.AI↗