arXiv subjects

Xin Ji

Publications and source records attributed to Xin Ji.

At least 19 recordsLinked to original sources

arXiv2026

Comparative analysis of missing data imputation methods for CSST survey: Impact on photometric redshift estimation performance

Improving the accuracy of photometric redshifts (photo-$z$) is essential for reliable statistical studies of cosmology and galaxy evolution. However, missing photometric bands are a common observational challenge that can significantly degrade photo-$z$ estimation accuracy. In this work, we present a systematic evaluation of data imputation methods aimed at improving photo-$z$ performance. We benchmark a range of representative machine learning (ML) and deep learning (DL) architectures, identifying k-nearest neighbors (KNN) and the attention-based SAITS model as the leading performers. These models are then applied to China Space Station Survey Telescope (CSST) mock data to assess their performance under realistic observational conditions. Our results show that KNN yields the highest accuracy under idealized missing completely at random (MCAR) conditions with complete training sets, whereas robustness tests reveal that SAITS significantly outperforms KNN when training data is incomplete or when applied to realistic mixed-mechanism scenarios. We find that domain consistency between training and testing missingness patterns is a prerequisite for optimal performance, highlighting the risks of domain shift in supervised regression tasks. Furthermore, our analysis demonstrates that while general imputation models are highly effective for MCAR and missing at random (MAR) data, they are detrimental when applied to missing not at random (MNAR) data arising from flux limits, as statistical models fail to capture the physical information inherent in these non-detections. Consequently, we advocate for more sophisticated architectures capable of disentangling stochastic missingness from physical non-detections to address these distinct mechanisms individually.

astro-ph.GA↗

arXiv2025

Forecast-Then-Optimize Deep Learning Methods

Time series forecasting underpins vital decision-making across various sectors, yet raw predictions from sophisticated models often harbor systematic errors and biases. We examine the Forecast-Then-Optimize (FTO) framework, pioneering its systematic synopsis. Unlike conventional Predict-Then-Optimize (PTO) methods, FTO explicitly refines forecasts through optimization techniques such as ensemble methods, meta-learners, and uncertainty adjustments. Furthermore, deep learning and large language models have established superiority over traditional parametric forecasting models for most enterprise applications. This paper surveys significant advancements from 2016 to 2025, analyzing mainstream deep learning FTO architectures. Focusing on real-world applications in operations management, we demonstrate FTO's crucial role in enhancing predictive accuracy, robustness, and decision efficacy. Our study establishes foundational guidelines for future forecasting methodologies, bridging theory and operational practicality.

cs.LG↗

arXiv2025

Multiple stellar populations at less evolved stages. IV. evidence of helium enrichments in four Magellanic globular clusters

Most globular clusters in the local group show multiple stellar populations, a pattern defined by variations of several light elements, with some also displaying dispersions in heavy elements. Since helium is the most immediate product of hydrogen burning, almost all models suggest that second-generation stars should show different levels of helium enrichment than first-generation stars. Therefore, investigating helium enrichment in stellar populations of globular clusters can constrain different theoretical models. Using the deep photometry carried out by the {\sl Hubble} Space Telescope, we have analyzed the morphologies of the main sequences of four Large Magellanic Cloud globular clusters, Hodge 11, NGC 1841, NGC 2210, and NGC 2257. We aim to constrain the helium distributions among their main sequence stars. We found a clear broadening of main sequences in all four clusters. After excluding the effects of photometric errors, differential reddening, unresolved binaries, and metallicity dispersions, this broadening would suggest a substantial helium enrichment in their star populations, ranging from $\delta{Y}=0.08$ to $\delta{Y}\geq0.12$, depending on the presumed helium distributions. Helium-enriched stars are comparable in number to normal stars within these clusters, and may even dominate, comprising approximately $\sim$40\% to over 80\% of the total stellar population. However, given the great distance of the Large Magellanic Cloud, it is difficult to rule out the significant impact of crowding, so our results may only represent an upper limit.

astro-ph.GA↗

arXiv2025

Progress of the TianQin project

TianQin is a future space-based gravitational wave observatory targeting the frequency window of $10^{-4}$ Hz $\sim 1$ Hz. A large variety of gravitational wave sources are expected in this frequency band, including the merger of massive black hole binaries, the inspiral of extreme/intermediate mass ratio systems, stellar-mass black hole binaries, Galactic compact binaries, and so on. TianQin will consist of three Earth orbiting satellites on nearly identical orbits with orbital radii of about $10^5$ km. The satellites will form a normal triangle constellation whose plane is nearly perpendicular to the ecliptic plane. The TianQin project has been progressing smoothly following the ``0123" technology roadmap. In step ``0", the TianQin laser ranging station has been constructed and it has successfully ranged to all the five retro-reflectors on the Moon. In step ``1", the drag-free control technology has been tested and demonstrated using the TianQin-1 satellite. In step ``2", the inter-satellite laser interferometry technology will be tested using the pair of TianQin-2 satellites. The TianQin-2 mission has been officially approved and the satellites will be launched around 2026. In step ``3", i.e., the TianQin-3 mission, three identical satellites will be launched around 2035 to form the space-based gravitational wave detector, TianQin, and to start gravitational wave detection in space.

gr-qc↗

arXiv2024

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching

Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. Many of these tasks are performed in large batches or even offline, and the performance indicator for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix between requests. The KV context that are about to be reused may be prematurely evicted with the implicit cache management. Besides, the streaming oriented systems do not leverage the request-batch information and can not mix the decoding tokens with the prefill chunks to the best for the batched scenarios, and thus fails to saturate the GPU. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks, and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Extensive evaluation shows that BatchLLM outperforms vLLM and SGLang by $1.3\times$ to $10.8\times$ on a set of microbenchmarks and a typical industry workload under different hardware environments. Code is available at https://github.com/microsoft/MixLLM/tree/batchllm_vllm_064.

cs.CL↗

arXiv2024

Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework's superior performance, marking significant advancements over baselines.

cs.AI↗

arXiv2023

Multiple stellar populations at less evolved stages-III: a possible helium spread in NGC 2210

Helium variations are common features of globular clusters (GCs) with multiple stellar populations. All the formation scenarios predict that secondary population stars are enhanced in helium but the exact helium content depends on the polluters. Therefore, searching for helium variations in a star cluster is a straightforward method to understand if it hosts multiple populations or not, and constrain the formation scenario. Although this topic has been well explored for Galactic GCs, GCs beyond the Milky Way are challenging to study because of their large distances. This work studies the helium distribution of GK-type main sequence dwarfs in an old ($\sim$12.5 Gyr) GC in the Large Magellanic Cloud, NGC 2210, using the deep photometry observed by the {\sl Hubble Space Telescope}. We compare the observed morphology of the MS with that of synthetic populations with different helium distributions. We confirm that NGC 2210 dwarfs have a helium spread, with an internal dispersion of $δ{Y}\sim$0.06--0.07. The fraction of helium enriched stars depends on the $δ{Y}$ distribution. A continuous $δ{Y}$ distribution would indicate that more than half of MS stars are helium enriched ($\sim$55\%). If the $δ{Y}$ distribution is discrete (bimodal), a fraction of $\sim$30\% enriched stars is able to explain the observed morphology of the MS. We also find that the He-enriched population stars are more centrally concentrated than He-normal stars.

astro-ph.SR↗

arXiv2021

The Spectroscopic Binaries from LAMOST Medium-Resolution Survey (MRS). I. Searching for Double-lined Spectroscopic Binaries (SB2s) with Convolutional Neural Network

We developed a convolutional neural network (CNN) model to distinguish the double-lined spectroscopic binaries (SB2s) from others based on single exposure medium-resolution spectra ($R\sim 7,500$). The training set consists of a large set of mock spectra of single stars and binaries synthesized based on the MIST stellar evolutionary model and ATLAS9 atmospheric model. Our model reaches a novel theoretic false positive rate by adding a proper penalty on the negative sample (e.g., 0.12\% and 0.16\% for the blue/red arm when the penalty parameter $Λ=16$). Tests show that the performance is as expected and favors FGK-type Main-sequence binaries with high mass ratio ($q \geq 0.7$) and large radial velocity separation ($Δv \geq 50\,\mathrm{km\,s^{-1}}$). Although the real false positive rate can not be estimated reliably, validating on eclipsing binaries identified from Kepler light curves indicates that our model predicts low binary probabilities at eclipsing phases (0, 0.5, and 1.0) as expected. The color-magnitude diagram also helps illustrate its feasibility and capability of identifying FGK MS binaries from spectra. We conclude that this model is reasonably reliable and can provide an automatic approach to identify SB2s with period $\lesssim 10$ days. This work yields a catalog of binary probabilities for over 5 million spectra of 1 million sources from the LAMOST medium-resolution survey (MRS), and a catalog of 2198 SB2 candidates whose physical properties will be analyzed in our following-up paper. Data products are made publicly available at the journal as well as our Github website.

astro-ph.SR↗

arXiv2020

When does the onset of multiple stellar populations in star clusters occur-III: No evidence of significant chemical variations in main-sequence stars of NGC 419

Recent studies have revealed that the onset age for the presence of multiple stellar populations (MPs) in star clusters seems to correspond to the disappearance of the extended main-sequence turnoff (eMSTO) in young clusters, a pattern associated with stellar rotations. A speculative suggestion is that MPs might be caused by the magnetic brake, a stellar evolutionary effect linked to the rotation. In this work, we use the young massive cluster NGC 419 as a testbed. We examined if its magnetically baked MS stars would exhibit MPs. Using the deep ultraviolet and visible images observed through the Hubble Space Telescope, combined with a specific color index that is sensitive to the nitrogen (N) abundance, we examined if its late G- and K-type MS stars are affected by N variation. Our analysis reports that the morphology of its GK-type MS is most likely an SSP, and only a negligible probability that indicates a N variation up to 0.4 dex is present. We conclude that there is no significant N variation among its GK-type MS stars. The absence of a significant chemical variation among the late-type MS stars indicates that MPs might not be a specific pattern of magnetically braked stars.

astro-ph.SR↗

arXiv2017

Cross-Domain Image Retrieval with Attention Modeling

With the proliferation of e-commerce websites and the ubiquitousness of smart phones, cross-domain image retrieval using images taken by smart phones as queries to search products on e-commerce websites is emerging as a popular application. One challenge of this task is to locate the attention of both the query and database images. In particular, database images, e.g. of fashion products, on e-commerce websites are typically displayed with other accessories, and the images taken by users contain noisy background and large variations in orientation and lighting. Consequently, their attention is difficult to locate. In this paper, we exploit the rich tag information available on the e-commerce websites to locate the attention of database images. For query images, we use each candidate image in the database as the context to locate the query attention. Novel deep convolutional neural network architectures, namely TagYNet and CtxYNet, are proposed to learn the attention weights and then extract effective representations of the images. Experimental results on public datasets confirm that our approaches have significant improvement over the existing methods in terms of the retrieval accuracy and efficiency.

cs.MM↗

arXiv2016

Transitionless-based shortcuts for rapidly generating two-atom 3D entanglement

An experimentally feasible scheme is proposed for rapidly generating two-atom three-dimensional (3D) entanglement with one step. As one technique of shortcuts to adiabaticity, transitionless quantum driving is applied to speed up the adiabatic generation of two-atom 3D entanglement. Apart from the rapid rate, the scheme has much higher experimental feasibility than the recent research (Quant. Inf. Process. DOI: 10.1007/s11128-016-1453-2, 2016). Besides, numerical simulations indicate the scheme has strong robustness against parameter deviations and decoherence.

quant-ph↗

arXiv2016

Fast adiabatic quantum state transfer and entanglement generation between two atoms via dressed states

Recently, a new method, which can significantly speed up adiabatic quantum state transfer by using dressed states, was proposed by Baksic \emph{et~al.} [Phys. Rev. Lett. \textbf{116}, 230503 (2016)]. Assisted by quantum Zeno dynamics, we develop this dressed-state method to achieve shortcuts to complete and fractional stimulated Raman adiabatic passage for speeding up adiabatic two-atom quantum state transfer and maximum entanglement generation, respectively. By means of some numerical simulations, we determine the parameters used in the scheme which can guarantee the feasibility and efficiency both in theory and experiment. Besides, we give strict numerical simulations to discuss the scheme's robustness, and the results show the scheme is robust against the variations in the parameters, atomic spontaneous emissions and the photon leakages from the cavity.

quant-ph↗

arXiv2016

Dressed-state scheme for a fast CNOT gate

A highly feasible dressed-state scheme, which greatly speeds up the adiabatic population transfer of a quantum system, is applied for implementing a fast CNOT gate in a cavity QED system. The cavity QED system consists of two identical five-level atoms which are respectively trapped in two optical cavities connected by a fiber. With the help of quantum Zeno dynamics, the CNOT gate is constructed by three steps with six pulses. Because the adiabatic condition is not necessary to be considered and all of the pulses are smoothly turned on and off, the scheme is fast and feasible in experiment. Numerical simulations indicate that the average fidelity for constructing the CNOT gate is quite high and the gate operation time is relatively short. Moreover, the effects on the fidelity of the atomic spontaneous emission and the photon leakages from the cavities are discussed by the master equation and the result shows the scheme is robust against the decoherence.

quant-ph↗

arXiv2016

Fast generations of tree-type three-dimensional entanglement via Lewis-Riesenfeld invariants and transitionless quantum driving

Recently, a novel three-dimensional entangled state called tree-type entanglement, which is likely to have applications for improving quantum communication security, was prepared via adiabatic passage by Song et al. [Phys. Rev. A 93, 062321 (2016)]. Here we propose two schemes for fast generations of tree-type three-dimensional entanglement among three spatially separated atoms via shortcuts to adiabatic passage. With the help of quantum Zeno dynamics, two kinds of different but equivalent methods, Lewis-Riesenfeld invariants and transitionless quantum driving, are applied to construct shortcuts to adiabatic passage. The comparisons between the two methods are discussed. The strict numerical simulations show that the tree-type three-dimensional entangled states can be fast prepared with quite high fidelities and the two schemes are both robust against the variations in the parameters, atomic spontaneous emissions and the cavity-fiber photon leakages.

quant-ph↗

arXiv2016

Fast generation of three-dimensional entanglement between two spatially separated atoms via invariant-based shortcut

A scheme is proposed for the fast generation of three-dimensional entanglement between two atoms trapped in two cavities connected by a fiber via invariant-based shortcut to adiabatic passage. With the help of quantum Zeno dynamics, the technique of invariant-based shortcut to adiabatic passage is applied for the generation of two-atom three-dimensional entanglement. The numerical simulation results show that, within a short time, the scheme has a high fidelity and is robust against the decoherence caused by the atomic spontaneous emission, photon leakage, and the variations in the parameters selected. Moreover, the scheme may be possible to be implemented with the current experimental technology.

quant-ph↗

arXiv2015

Generation of three-dimensional entanglement between two spatially separated atoms via shortcuts to adiabatic passage

We propose a scheme for generating three-dimensional entanglement between two atoms trapped in two spatially separated cavities reapectively via shortcuts to adi- abatic passage based on the approach of Lewis-Riesenfeld invariants in cavity quan- tum electronic dynamics. By combining Lewis-Riesenfeld invariants with quantum Zeno dynamics, we can generate three dimensional entanglement of the two atoms with high fidelity. The Numerical simulation results show that the scheme is ro- bust against the decoherences caused by the photon leakage and atomic spontaneous emission.

quant-ph↗

arXiv2015

Deterministic SWAP gate using shortcuts to adiabatic passage

We theoretically propose an alternative method to realize a deterministic SWAP gate using shortcuts to adiabatic passage based on the approach of Lewis- Riesenfeld invariants in cavity quantum electronic dynamics (QED). By combining Lewis-Riesenfeld invariants with quantum Zeno dynamics, the SWAP gate can be achieved deterministically. The strict numerical results show that our scheme is a fast and robust approach to achieve SWAP gate.

quant-ph↗

arXiv2014

Generation of genuine $χ$-type four-particle entangled state of superconducting artificial atoms with broken symmetry

We propose a scheme for generating a genuine $χ$-type four-particle entangled state of superconducting artificial atoms with broken symmetry by using one-dimensional transmission line resonator as a data bus. The $Δ$-type three-level artificial atom we use in the scheme is different from natural atom and has cyclic transitions. After suitable interaction time and simple operations, the desired entangled state can be obtained. Since artificial atomic excited states and photonic states are adiabatically eliminated, our scheme is robust against the spontaneous emissions of artificial atoms and the decays of transmission line resonator.

quant-ph↗