SearcharxivSearch

arXiv subjects

Dongkyu Kim

Publications and source records attributed to Dongkyu Kim.

At least 19 recordsLinked to original sources

Robust Generation of Topological Biphoton Mode via Adiabatic Passage

Topological waveguide arrays support robust mode propagation in the presence of fabrication imperfections, providing a significant advantage for on-chip quantum information processing. However, this robustness does not fully extend to nonlinear biphoton generation. Structural disorder can enhance the excitation of non-topological biphoton modes during nonlinear interactions, which degrades the quantum properties of the generated state. To overcome this limitation, we propose an adiabatic passage that connects an isolated site to a topological defect array. By initiating the nonlinear process in a strongly isolated regime, nonlinear coupling to unwanted modes is effectively suppressed, thereby preserving the Schmidt number of the generated state. The subsequent adiabatic connection facilitates the high fidelity transfer of the generated biphoton into the topological biphoton mode. Our numerical simulations demonstrate that, unlike conventional topological structures, the adiabatic scheme maintains both high biphoton fidelity and a unit Schmidt number in the presence of waveguide gap disorder. Furthermore, we show that this robustness extends to path entangled NOON states, achieving a near-unity quantum interference visibility. Our approach provides a practical design strategy for disorder-tolerant integrated quantum photonic devices.

quant-ph

Quantum key distribution over a 2 km free-space channel with a high secure key rate

Free-space quantum key distribution (QKD) provides crucial advantages, including mobility and deployment flexibility, for securing next-generation communication networks. However, practical free-space implementations face major challenges, such as muilti-photon vulnerabilities, spatial mode mismatch, and atmospheric turbulence-induced beam fluctuations. In this work, we experimentally demonstrate a free-space decoy-state BB84 QKD system operating at a 100 MHz repetition rate with a 2.5 ns pulse width over a 2 km outdoor channel. By employing an active beam-wander correction based on fast-steering mirrors (FSMs) and position sensitive detectors (PSDs) con?figuration, our system achieves a secure key rate of 164.8 kbps under a quantum bit error rate (QBER) of approximately 3.3 %. This demonstration provides a practical framework for deploying high-rate, long-distance free-space quantum communication in realistic turbulence environments.

quant-ph

Spectrally engineered collinear type-0 SPDC source with enhanced spectral brightness for entanglement distribution

Entangled photon sources with high spectral brightness are important resources for photonic quantum information processing, particularly in quantum communication and quantum networking where usable photon flux of entangled photons is often constrained by channel loss and source inefficiency. Here, we demonstrate a spectrally engineered type-0 spontaneous parametric down-conversion (SPDC) source with enhanced spectral brightness for entanglement distribution. By pumping a 30-mm ppKTP crystal with an ultra-narrowband laser slightly detuned from degeneracy, photon-pair generation is concentrated into a narrow spectral bandwidth while retaining the strong nonlinear interaction of type-0 phase matching. The source produces a coincidence rate of 44.6 kHz corresponding to a detected spectral brightness of 0.507 MHz/mW/nm. We further integrate the source into a Sagnac interferometer to generate polarization-entangled photon pairs and demonstrate entanglement distribution through a 2.56 km free-space round-trip channel. Our results show that spectral engineering provides a practical route to compact, spectrally bright entangled-photon sources for quantum communication applications.

quant-ph

RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking binary ($\pm$1) layers, but is plagued by pathological feature co-adaptation. We identify a key failure mode, which we term inter-path adaptation: during quantization-aware training (QAT), parallel residual binary paths learn redundant features, degrading the error-compensation structure and limiting the expressive capacity of the model. While prior work relies on heuristic workarounds (e.g., path freezing) that constrain the solution space, we propose RaBiT, a novel quantization framework that resolves co-adaptation by algorithmically enforcing a residual hierarchy. Its core mechanism sequentially derives each binary path from a single shared full-precision weight, which ensures that every path corrects the error of the preceding one. This process is stabilized by a robust initialization that prioritizes functional preservation over mere weight approximation. RaBiT redefines the 2-bit accuracy-efficiency frontier: it achieves state-of-the-art performance, rivals even hardware-intensive Vector Quantization (VQ) methods, and delivers a $4.49\times$ inference speed-up over full-precision models on an RTX 4090. Code is available at https://github.com/SamsungLabs/RaBiT.

cs.AI

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit) levels, as they either require large amounts of data and compute or incur additional storage. In this work, we propose NanoQuant, the first post-training quantization (PTQ) method to compress LLMs to both binary and sub-1-bit levels. NanoQuant formulates quantization as a low-rank binary factorization problem, and compresses full-precision weights to low-rank binary matrices and scales. Specifically, it utilizes an efficient alternating direction method of multipliers (ADMM) solver to precisely initialize latent binary matrices and scales, and then tunes the initialized parameters through a block and model reconstruction process. Consequently, NanoQuant establishes a new Pareto frontier in low-memory post-training quantization, and enables sub-1-bit compression. NanoQuant makes large-scale deployment feasible on consumer hardware. For example, it compresses Llama2-70B by 25.8$\times$ in just 13 hours on a single H100, enabling a 70B model to operate on a consumer 8 GB GPU. Code is available at https://github.com/SamsungLabs/NanoQuant.

cs.LG

LittleBit: Ultra Low-Bit Quantization via Latent Factorization

The deployment of large language models (LLMs) is frequently hindered by prohibitive memory and computational requirements. While quantization mitigates these bottlenecks, maintaining model fidelity in the sub-1-bit regime remains a persistent challenge. In this paper, we introduce LittleBit, a novel framework for extreme LLM compression. We target quantization rates as low as $0.1$ bits per weight (BPW), achieving a memory reduction of approximately $31\times$, which effectively compresses Llama2-13B to under $0.9$ GB. We represent weights via low-rank latent matrix factorization and subsequently binarize the resulting factors. To counteract the information loss inherent to such drastic precision reduction, we integrate a multi-scale compensation mechanism that learns importance parameters across row, column, and latent dimensions. Two primary contributions enable effective training: Dual Sign-Value-Independent Decomposition (Dual-SVID) for quantization-aware training (QAT) initialization, and Residual Compensation to minimize approximation errors. Extensive experiments confirm the superiority of LittleBit in the sub-1-bit domain; for instance, our method at $0.1$ BPW surpasses the performance of leading techniques operating at $0.7$ BPW on Llama2-7B. We establish a new size-performance trade-off -- unlocking a potential $11.6\times$ inference speedup relative to FP16 -- and render powerful LLMs practical for resource-constrained environments. Our code is available at https://github.com/SamsungLabs/LittleBit.

cs.LG

Optimizing brightness of SPDC source in Laguerre-Gaussian modes using type-0 periodically-poled nonlinear crystal

Photon pairs generated via spontaneous parametric down-conversion (SPDC) can exhibit entanglement in the Laguerre-Gaussian (LG) mode basis, which enables high-dimensional free-space quantum communication by exploiting the high-dimensional space spanned by the LG modes. For such free-space quantum communication, the brightness of the quantum light source plays an important role due to the atmospheric turbulence and photon loss. A variety of studies have analyzed the SPDC brightness by decomposing biphoton states into LG modes, but they have often relied on a degenerate state, a narrow spectral bandwidth approximation, or a thin crystal approximation. However, these approaches are unsuitable for non-degenerate type-0 SPDC with a periodicallypoled nonlinear crystal, which offers higher brightness due to its superior nonlinear coefficients. In this study, we examine the spectrum of photon pairs in specific LG modes generated by a type-0 ppKTP crystal whileavoiding the constraints imposed by the aforementioned assumptions. In addition, we investigate the optimal focal parameters of the pump, signal, and idler to maximize the brightness for a given LG mode. Our findings show that it is not feasible to simultaneously optimize the brightness for different LG modes with a single pump focal parameter. The results of this study provide a comprehensive framework for developing highbrightness quantum light sources and contribute to the advancement of high-dimensional free-space quantum communication.

quant-ph

AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline

Using LLMs (Large Language Models) in conjunction with external documents has made RAG (Retrieval-Augmented Generation) an essential technology. Numerous techniques and modules for RAG are being researched, but their performance can vary across different datasets. Finding RAG modules that perform well on specific datasets is challenging. In this paper, we propose the AutoRAG framework, which automatically identifies suitable RAG modules for a given dataset. AutoRAG explores and approximates the optimal combination of RAG modules for the dataset. Additionally, we share the results of optimizing a dataset using AutoRAG. All experimental results and data are publicly available and can be accessed through our GitHub repository https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper .

cs.CL

Ultrabright fiber-coupled ploarization-entangled photon source with spectral brightness surpassing 2.0 MHz/mW/nm

We present an ultrabright polarization-entangled photon source that is optimally coupled into single-mode fibers (SMFs). This study theoretically and experimentally examines the characteristics of spontaneous parametric down-conversion (SPDC) photons, including their spectrum, bandwidth, emission angle, and intensity, as functions of crystal length, temperature and beam waist condition. Notably, we measure the collinear spatial modes of photon-pairs and collection optics under various beam waist conditions and analyze them using a collinear Gaussian approximation model. By employing a simple mode-matching optical setup, we optimize the SMF coupling and heralding efficiencies of the photon-pairs. Consequently, we achieve a spectral brightness exceeding 2.0 MHz/mW/nm from a fiber-coupled entangled photon source, utilizing a 30-mm ppKTP crystal inside a polarization Sagnac interferometer. This represents the highest spectral brightness of SPDC photons generated using a CW laser pumped bulk crystal to date. Polarization entanglement was verified by a quantum state tomography and a polarization-correlation measurement. The fidelity of the entangled state is measured to be 97.8 % and the Bell-CHSH value S = 2.782 +- 0.04. The results obtained here provide practical insights for designing high-performance SPDC sources for satellite-based communication and long-distance optical links with extremely high-photon loss.

quant-ph

Neural-network quantum state study of the long-range antiferromagnetic Ising chain

We investigate quantum phase transitions in the transverse field Ising chain with algebraically decaying long-range (LR) antiferromagnetic interactions using the variational Monte Carlo method with the restricted Boltzmann machine employed as a trial wave function ansatz. First, we measure the critical exponents and the central charge through the finite-size scaling analysis, verifying the contrasting observations in the previous tensor network studies. The correlation function exponent and the central charge deviate from the short-range (SR) Ising values at a small decay exponent $α_\mathrm{LR}$, while the other critical exponents examined are very close to the SR Ising exponents regardless of $α_\mathrm{LR}$ examined. However, in the further test of the critical Binder ratio, we find that the universal ratio of the SR limit does not hold for $α_\mathrm{LR} < 2$, implying a deviation in the criticality. On the other hand, we find evidence of the conformal invariance breakdown in the conformal field theory (CFT) test of the correlation function. The deviation from the CFT description becomes more pronounced as $α_\mathrm{LR}$ decreases, although a precise breakdown threshold is yet to be determined.

cond-mat.stat-mech

Highly-enhanced active beam-wander-correction for free-space quantum communications

In practical applications to free-space quantum communications, the utilization of active beam coupling and stabilization techniques offers notable advantages, particularly when dealing with limited detecting areas or coupling into single-mode fibers(SMFs) to mitigate background noise. In this work, we introduce highly-enhanced active beam-wander-correction technique, specifically tailored to efficiently couple and stabilize beams into SMFs, particularly in scenarios where initial optical alignment with the SMF is misaligned. To achieve this objective, we implement a SMF auto-coupling algorithm and a decoupled stabilization method, effectively and reliably correcting beam wander caused by atmospheric turbulence effects. The performance of the proposed technique is thoroughly validated through quantitative measurements of the temporal variation in coupling efficiency(coincidence counts) of a laser beam(entangled photons). The results show significant improvements in both mean values and standard deviations of the coupling efficiency, even in the presence of 2.6 km atmospheric turbulence effects. When utilizing a laser source, the coupling efficiency demonstrates a remarkable mean value increase of over 50 %, accompanied by a substantial 4.4-fold improvement in the standard deviation. For the entangled photon source, a fine mean value increase of 14 % and an approximate 2-fold improvement in the standard deviation are observed. Furthermore,the proposed technique successfully restores the fidelity of the polarization-entangled state, which has been compromised by atmospheric effects in the free-space channel, to a level close to the fidelity measured directly from the source. Our work will be helpful in designing spatial light-fiber coupling system not only for free-space quantum communications but also for high-speed laser communications.

quant-ph

Quantum-correlation-based free-space optical link with an active reflector

We present a quantum-correlation-based free-space optical(FSO) link over 250 m using an outdoor active reflector 125 m from the transceiver station. The performance of free-space optical communication can be significantly degraded by atmospheric turbulence effects, such as beam wander and signal fluctuations. We used a 660 nm tracking laser to reduce atmospheric effects, by analyzing the fast beam wander and slow temporal beam drift, using this information to correct the quantum channel alignment of the 810 nm signal photons. In this work, the active reflector consisted of a mirror, a 6-axis hexapod stage, and a long-range wireless bridge. The slow drift of the beam path due to outdoor temperature changes was steered and controlled using wireless optical feedback between the receiver units and the active reflector. Our work provides useful knowledge for improved control of beam paths in outdoor conditions, which can be developed to ensure high quality quantum information transfer in real-world scenarios, such as an unmanned FSO link for urban quantum communication or retro-reflective quantum communication links.

quant-ph

Observable bound for Gaussian illumination

We propose observable bounds for Gaussian illumination to maximize the signal-to-noise ratio, which minimizes the discrimination error between the presence and absence of a low-reflectivity target using Gaussian states. The observable bounds are achieved with mode-by-mode measurements. In the quantum regime using a two-mode squeezed vacuum state, our observable receiver outperforms the other feasible receivers whereas it cannot approach the quantum Chernoff bound. The corresponding observable cannot be implemented with heterodyne detections due to the additional vacuum noise. In the classical regime using a thermal state, a receiver implemented with a photon number difference measurement approaches its bound regardless of the signal mean photon number, while it asymptotically approaches the classical bound in the limit of a huge idler mean photon number.

quant-ph

Noise-robust single-pixel imaging in photon counting regime with a pulsed source

We present a method to classically enhance noise-robustness of single-pixel imaging in photon counting regime with a pulsed source. By using time-domain cross-correlations between temporal profiles of a pulsed source and received signals, our scheme classically imitates the noise rejection concept of quantum imaging. Under a strong noise environment in which the background noise intensity is up to 120 times higher than the signal one, we compare three different images obtained by conventional, quantum-enhanced, and classically enhanced schemes. The results show that the classically enhanced scheme can be remarkably robust against noise in image formation, which is comparable to the quantum scheme.

quant-ph

Heralded single-pixel imaging with high loss-resistance and noise-robustness

Imaging with non-classically correlated photon-pairs takes advantages over classical limits in terms of sensitivity and signal-to-noise ratio. However, it is still a challenge to achieve a strong resilience to background noise and losses for practical applications. In this work, we present heralded single-pixel imaging that is remarkably robust against bright background noise and severe signal losses. Using a strong temporal correlation between a photon-pair and joint measurement-based imaging method, we achieve the suppression of noise up to 1000 times larger than the signal and also demonstrate the correlation-induced SNR enhancement factor of over 200 against 70 times larger noise and a 90% signal loss compared to non-time-gated classical imaging. Our work enables correlated imaging with a highly scalable photon capacity.

quant-ph

Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition

We investigate the connection between the supervised learning of the binary phase classification in the ferromagnetic Ising model and the standard finite-size-scaling theory of the second-order phase transition. Proposing a minimal one-free-parameter neural network model, we analytically formulate the supervised learning problem for the canonical ensemble being used as a training data set. We show that just one free parameter is capable enough to describe the data-driven emergence of the universal finite-size-scaling function in the network output that is observed in a large neural network, theoretically validating its critical point prediction for unseen test data from different underlying lattices yet in the same universality class of the Ising criticality. We also numerically demonstrate the interpretation with the proposed one-parameter model by providing an example of finding a critical point with the learning of the Landau mean-field free energy being applied to the real data set from the uncorrelated random scale-free graph with a large degree exponent.

cond-mat.stat-mech

Surviving Entanglement in Optic-Microwave Conversion by Electro-Optomechanical System

In recent development of quantum technologies, a frequency conversion of quantum signals has been studied widely. We investigate the optic-microwave entanglement that is generated by applying an electro-optomechanical frequency conversion scheme to one mode in an optical two-mode squeezed vacuum state. We quantify entanglement of the converted two-mode Gaussian state, where surviving entanglement of the state is analyzed with respect to the parameters of the electro-optomechanical system. Furthermore, we show that there exists an upper bound for the entanglement that survives after the conversion of highly entangled optical states. Our study provides a theoretical platform for a practical quantum illumination system.

quant-ph

Coherent multi-mode conversion from microwave to optical wave via a magnon-cavity hybrid system

Coherent conversion from microwave to optical wave opens new research avenues towards long distant quantum network covering quantum communication, computing, and sensing out of the laboratory. Especially multi-mode enabled system is essential for practical applications. Here we experimentally demonstrate coherent multi-mode conversion from the microwave to optical wave via collective spin excitation in a single crystal yttrium iron garnet (YIG, Y3Fe5O12) which is strongly coupled to a microwave cavity mode in a three-dimensional rectangular cavity. Expanding collective spin excitation mode of our magnon-cavity hybrid system from Kittel to multi magnetostatic modes, we verify that the size of YIG sphere predominantly plays a crucial role for the microwave-to-optical multi-mode conversion efficiency at resonant conditions. We also find that the coupling strength between multi magnetostatic modes and a cavity mode is manipulated by the position of a YIG inside the cavity. It is expected to be valuable for designing a magnon hybrid system that can be used for coherent conversion between microwave and optical photons.

quant-ph