arXiv subjects

Jin Li

Publications and source records attributed to Jin Li.

At least 127 records · Page 7Linked to original sources

arXiv2025

An MLE analysis on the relationship between the initial-state granularity and final-state flow factorization

In this study, we employ the maximum likelihood estimator (MLE) to investigate the relationship between initial-state fluctuations and final-state anisotropies in relativistic heavy-ion collisions. The granularity of the initial state, reflecting fluctuations in the initial conditions (IC), is modeled using a peripheral tube model. Besides differential flow, our analysis focuses on a class of more sensitive observables known as flow factorization. Specifically, we evaluate these observables using MLE, an asymptotically normal and unbiased tool in standard statistical inference. Our findings show that the resulting differential flow remains essentially unchanged for different IC defined by the peripheral tube model. The resulting harmonic coefficients obtained using MLE and multi-particle cumulants are found to be consistent. However, the calculated flow factorizations show significant variations depending on both the IC and the estimators, which is attributed to their sensitivity to initial-state fluctuations. Thus, we argue that MLE offers a compelling alternative to standard methods such as multi-particle correlators, particularly for sensitive observables constructed from higher moments of the azimuthal distribution.

nucl-th↗

arXiv2025

Target Speaker Lipreading by Audio-Visual Self-Distillation Pretraining and Speaker Adaptation

Lipreading is an important technique for facilitating human-computer interaction in noisy environments. Our previously developed self-supervised learning method, AV2vec, which leverages multimodal self-distillation, has demonstrated promising performance in speaker-independent lipreading on the English LRS3 dataset. However, AV2vec faces challenges such as high training costs and a potential scarcity of audio-visual data for lipreading in languages other than English, such as Chinese. Additionally, most studies concentrate on speakerindependent lipreading models, which struggle to account for the substantial variation in speaking styles across di?erent speakers. To address these issues, we propose a comprehensive approach. First, we investigate cross-lingual transfer learning, adapting a pre-trained AV2vec model from a source language and optimizing it for the lipreading task in a target language. Second, we enhance the accuracy of lipreading for specific target speakers through a speaker adaptation strategy, which is not extensively explored in previous research. Third, after analyzing the complementary performance of lipreading with lip region-of-interest (ROI) and face inputs, we introduce a model ensembling strategy that integrates both, signi?cantly boosting model performance. Our method achieved a character error rate (CER) of 77.3% on the evaluation set of the ChatCLR dataset, which is lower than the top result from the 2024 Chat-scenario Chinese Lipreading Challenge.

eess.AS↗

arXiv2025

Seesaw Experimentation: A/B Tests with Spillovers

This paper examines how spillover effects in A/B testing can impede organizational progress and develops strategies for mitigating these challenges. We identify a phenomenon termed ``seesaw experimentation'', where a firm's overall performance paradoxically deteriorates despite achieving continuous improvements in measured A/B testing metrics. Seesaw experimentation arises when successful innovations in primary metrics generate negative externalities in secondary, unmeasured dimensions. To address this problem, we propose implementing a positive hurdle rate for A/B test approval. We derive the optimal hurdle rate, offering a simple solution that preserves decentralized experimentation while mitigating negative spillovers.

econ.GN↗

arXiv2025

Characterization and Optimization of a Cryogenic Pure CsI Detector with Remarkable Light Yield and Unprecedented Energy Resolution for CLOVERS Experiment

In this study, we comprehensively characterized and optimized a cryogenic pure CsI (pCsI) detector. We utilized a {$\SI{2}{cm}\times\SI{2}{cm}\times\SI{2}{cm}$} cube crystal coupled with a HAMAMATSU R11065 photomultiplier tube, achieving a remarkable light yield of \SI{35.2}{PE/\keV_{ee}} and an unprecedented energy resolution of \SI{6.9}{\%} at {\SI{59.54}{\keV}}. Additionally, we measured the scintillation decay time of pCsI, which was significantly shorter than that of CsI(Na) at room temperature. Furthermore, we investigated the impact of temperature, surface treatment, and crystal shape on light yield. Notably, the light yield peaked at approximately \SI{20}{\K} and remained stable within the range of \SI{70}--\SI{100}{\K}. The light yield of the polished crystals was approximately 1.5 times greater than that of the ground crystals, whereas the crystal shape exhibited minimal influence on the light yield. These results are crucial for the design of the \SI{10}{\kg} pCsI detector for the future CLOVERS (Coherent eLastic neutrinO(V)-nucleus scattERing at China Spallation Neutron Source (CSNS)) experiment.`

physics.ins-det↗

arXiv2025

Online Detection of Water Contamination Under Concept Drift

Water Distribution Networks (WDNs) are vital infrastructures, and contamination poses serious public health risks. Harmful substances can interact with disinfectants like chlorine, making chlorine monitoring essential for detecting contaminants. However, chlorine sensors often become unreliable and require frequent calibration. This study introduces the Dual-Threshold Anomaly and Drift Detection (AD&DD) method, an unsupervised approach combining a dual-threshold drift detection mechanism with an LSTM-based Variational Autoencoder(LSTM-VAE) for real-time contamination detection. Tested on two realistic WDNs, AD&DD effectively identifies anomalies with sensor offsets as concept drift, and outperforms other methods. A proposed decentralized architecture enables accurate contamination detection and localization by deploying AD&DD on selected nodes.

cs.LG↗

arXiv2024

Learned Data Compression: Challenges and Opportunities for the Future

Compressing integer keys is a fundamental operation among multiple communities, such as database management (DB), information retrieval (IR), and high-performance computing (HPC). Recent advances in \emph{learned indexes} have inspired the development of \emph{learned compressors}, which leverage simple yet compact machine learning (ML) models to compress large-scale sorted keys. The core idea behind learned compressors is to \emph{losslessly} encode sorted keys by approximating them with \emph{error-bounded} ML models (e.g., piecewise linear functions) and using a \emph{residual array} to guarantee accurate key reconstruction. While the concept of learned compressors remains in its early stages of exploration, our benchmark results demonstrate that an SIMD-optimized learned compressor can significantly outperform state-of-the-art CPU-based compressors. Drawing on our preliminary experiments, this vision paper explores the potential of learned data compression to enhance critical areas in DBMS and related domains. Furthermore, we outline the key technical challenges that existing systems must address when integrating this emerging methodology.

cs.DB↗

arXiv2024

IGNITE: Individualized GeNeration of Imputations in Time-series Electronic health records

Electronic Health Records present a valuable modality for driving personalized medicine, where treatment is tailored to fit individual-level differences. For this purpose, many data-driven machine learning and statistical models rely on the wealth of longitudinal EHRs to study patients' physiological and treatment effects. However, longitudinal EHRs tend to be sparse and highly missing, where missingness could also be informative and reflect the underlying patient's health status. Therefore, the success of data-driven models for personalized medicine highly depends on how the EHR data is represented from physiological data, treatments, and the missing values in the data. To this end, we propose a novel deep-learning model that learns the underlying patient dynamics over time across multivariate data to generate personalized realistic values conditioning on an individual's demographic characteristics and treatments. Our proposed model, IGNITE (Individualized GeNeration of Imputations in Time-series Electronic health records), utilises a conditional dual-variational autoencoder augmented with dual-stage attention to generate missing values for an individual. In IGNITE, we further propose a novel individualized missingness mask (IMM), which helps our model generate values based on the individual's observed data and missingness patterns. We further extend the use of IGNITE from imputing missingness to a personalized data synthesizer, where it generates missing EHRs that were never observed prior or even generates new patients for various applications. We validate our model on three large publicly available datasets and show that IGNITE outperforms state-of-the-art approaches in missing data reconstruction and task prediction.

cs.LG↗

arXiv2024

Multi-robot autonomous 3D reconstruction using Gaussian splatting with Semantic guidance

Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to single robot, and rapid reconstruction of large-scale scenes remains challenging. Additionally, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots, and results show that it can effectively plan view paths and reconstruct scenes with high quality.

cs.RO↗

arXiv2024

Emergenet: A Digital Twin of Sequence Evolution for Scalable Emergence Risk Assessment of Animal Influenza A Strains

Despite having triggered devastating pandemics in the past, our ability to quantitatively assess the emergence potential of individual strains of animal influenza viruses remains limited. This study introduces Emergenet, a tool to infer a digital twin of sequence evolution to chart how new variants might emerge in the wild. Our predictions based on Emergenets built only using 220,151 Hemagglutinnin (HA) sequences consistently outperform WHO seasonal vaccine recommendations for H1N1/H3N2 subtypes over two decades (average match-improvement: 3.73 AAs, 28.40\%), and are at par with state-of-the-art approaches that use more detailed phenotypic annotations. Finally, our generative models are used to scalably calculate the current odds of emergence of animal strains not yet in human circulation, which strongly correlates with CDC's expert-assessed Influenza Risk Assessment Tool (IRAT) scores (Pearson's $r = 0.721, p = 10^{-4}$). A minimum five orders of magnitude speedup over CDC's assessment (seconds vs months) then enabled us to analyze 6,354 animal strains collected post-2020 to identify 35 strains with high emergence scores ($> 7.7$). The Emergenet framework opens the door to preemptive pandemic mitigation through targeted inoculation of animal hosts before the first human infection.

q-bio.PE↗

arXiv2024

Observation of Majorana zero modes emerged from topological Dirac semimetal states under uniaxial strain

The topological properties observed in iron-based superconductors extend our understanding of vortex Majorana quasiparticle excitations in unexpected ways. Vortex Majorana physics has been extensively studied within the context of the topologically protected surface Dirac state. By employing an in-situ strain device, we demonstrate that uniaxial strain can generate Majorana zero modes out of the topological Dirac semimetal bulk state in LiFeAs. Uniaxial strain along [100] direction is found to enhance the band renormalization of LiFeAs, effectively reducing the energy separation between the Fermi level and the topological Dirac semimetal state, and breaking C4 symmetry. Using scanning tunneling microscopy, we observe the evolution of vortex bound states in the topological Dirac semimetal state region, accompanied by the emergence of Majorana zero modes and vortex bound states contributed by the bulk band. Our work provides a controllable method for experimentally engineering Majorana physics in iron-based superconductors, and offers valuable insights into the topological Dirac semimetal state with intrinsic s-wave superconductivity.

cond-mat.supr-con↗

arXiv2024

Synergistic Interplay of Large Language Model and Digital Twin for Autonomous Optical Networks: Field Demonstrations

The development of large language models (LLM) has revolutionized various fields and is anticipated to drive the advancement of autonomous systems. In the context of autonomous optical networks, creating a high-level cognitive agent in the control layer remains a challenge. However, LLM is primarily developed for natural language processing tasks, rendering them less effective in predicting the physical dynamics of optical communications. Moreover, optical networks demand rigorous stability, where direct deployment of strategies generated from LLM poses safety concerns. In this paper, a digital twin (DT)-enhanced LLM scheme is proposed to facilitate autonomous optical networks. By leveraging monitoring data and advanced models, the DT of optical networks can accurately characterize their physical dynamics, furnishing LLMs with dynamic-updated information for reliable decision-making. Prior to deployment, the generated strategies from LLM can be pre-verified in the DT platform, which also provides feedback to the LLM for further refinement of strategies. The synergistic interplay between DT and LLM for autonomous optical networks is demonstrated through three scenarios: performance optimization under dynamic loadings in an experimental C+L-band long-haul transmission link, protection switching for device upgrading in a field-deployed six-node mesh network, and performance recovery after fiber cuts in a field-deployed C+L-band transmission link.

cs.NI↗

arXiv2024

UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding

Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on training models to match global image representations with textual descriptions, thereby overlooking the critical alignment between local regions and corresponding text tokens. This paper extends CLIP with multi-granularity alignment. Notably, we deliberately construct a new dataset comprising pseudo annotations at various levels of granularities, encompassing image-level, region-level as well as pixel-level captions and tags. Accordingly, we develop a Unified Multi-Granularity learning framework, termed UMG-CLIP, which simultaneously empowers the model with versatile perception abilities across different levels of detail. With parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP variants and achieves state-of-the-art performance on diverse image understanding benchmarks, including open-world recognition, retrieval, semantic segmentation, and panoptic segmentation tasks. We believe that UMG-CLIP represents a valuable advancement in vision-language foundation models. The code is available at https://github.com/lygsbw/UMG-CLIP.

cs.CV↗

arXiv2024

Prospects of constraining on the polarizations of gravitational waves from binary black holes using space- and ground-based detectors

The theory of general relativity (GR) predicts the existence of gravitational waves (GWs) with two tensor modes, while alternative theories propose up to six polarization modes. In this study, we investigate constraints on GW polarization using a model-independent parametrized post-Einsteinian framework and consider both space- and ground-based detectors. By evaluating the capabilities and network performance of LISA, Taiji, TianQin, LIGO, Virgo, KAGRA, and the Einstein Telescope (ET), we analyze their respective contributions. Among space-based detectors, Taiji provides the most stringent constraints compared with LISA and TianQin.Regarding ground-based detectors, LIGO excels in vector modes while ET offers comprehensive constraints across all polarization modes. In network scenarios, LISA+TJm performs best, and ET surpasses second-generation detector combinations. Furthermore, multiband observations effectively mitigate scalar mode degeneracies thereby significantly enhancing the performance of ground-based detectors. Ultimately, combined space- and ground-based observations provide robust constraints on GW polarizations that advance tests for deviations from GR. Our findings underscore the potential of future GW missions in refining our understanding of gravitational physics through precise measurements of polarizations.

gr-qc↗

arXiv2024

Scene Graph Generation with Role-Playing Large Language Models

Current approaches for open-vocabulary scene graph generation (OVSGG) use vision-language models such as CLIP and follow a standard zero-shot pipeline -- computing similarity between the query image and the text embeddings for each category (i.e., text classifiers). In this work, we argue that the text classifiers adopted by existing OVSGG methods, i.e., category-/part-level prompts, are scene-agnostic as they remain unchanged across contexts. Using such fixed text classifiers not only struggles to model visual relations with high variance, but also falls short in adapting to distinct contexts. To plug these intrinsic shortcomings, we devise SDSGG, a scene-specific description based OVSGG framework where the weights of text classifiers are adaptively adjusted according to the visual content. In particular, to generate comprehensive and diverse descriptions oriented to the scene, an LLM is asked to play different roles (e.g., biologist and engineer) to analyze and discuss the descriptive features of a given scene from different views. Unlike previous efforts simply treating the generated descriptions as mutually equivalent text classifiers, SDSGG is equipped with an advanced renormalization mechanism to adjust the influence of each text classifier based on its relevance to the presented scene (this is what the term "specific" means). Furthermore, to capture the complicated interplay between subjects and objects, we propose a new lightweight module called mutual visual adapter. It refines CLIP's ability to recognize relations by learning an interaction-aware semantic space. Extensive experiments on prevalent benchmarks show that SDSGG outperforms top-leading methods by a clear margin.

cs.CV↗

arXiv2024

SPFresh: Incremental In-Place Update for Billion-Scale Vector Search

Approximate Nearest Neighbor Search (ANNS) is now widely used in various applications, ranging from information retrieval, question answering, and recommendation, to search for similar high-dimensional vectors. As the amount of vector data grows continuously, it becomes important to support updates to vector index, the enabling technique that allows for efficient and accurate ANNS on vectors. Because of the curse of high dimensionality, it is often costly to identify the right neighbors of a single new vector, a necessary process for index update. To amortize update costs, existing systems maintain a secondary index to accumulate updates, which are merged by the main index by global rebuilding the entire index periodically. However, this approach has high fluctuations of search latency and accuracy, not even to mention that it requires substantial resources and is extremely time-consuming for rebuilds. We introduce SPFresh, a system that supports in-place vector updates. At the heart of SPFresh is LIRE, a lightweight incremental rebalancing protocol to split vector partitions and reassign vectors in the nearby partitions to adapt to data distribution shift. LIRE achieves low-overhead vector updates by only reassigning vectors at the boundary between partitions, where in a high-quality vector index the amount of such vectors are deemed small. With LIRE, SPFresh provides superior query latency and accuracy to solutions based on global rebuild, with only 1% of DRAM and less than 10% cores needed at the peak compared to the state-of-the-art, in a billion scale vector index with 1% of daily vector update rate.

cs.IR↗

arXiv2024

Isolated zero-energy flat-bands and intrinsic magnetism in carbon monolayers

Flat-band in twisted graphene bilayer has garnered widespread attention, and whether flat-bands can be realized in carbon monolayer is an interesting topic worth exploring in condensed matter physics. In this work, we demonstrate that, based on the theory of compact localized states, a series of two-dimensional carbon allotropes with flat-bands can be achieved. Two of them named as 191-8-66-C-r567x-1 and 191-10-90-C-r567x-1 are confirmed to be dynamically stable carbon phases with isolated or weakly overlapped flat-bands at the Fermi-level. The maximum Fermi velocities of the flat-band electrons are evaluated to be 1x10^4 m/s and 0.786x10^4 m/s, both of which are lower than the Fermi velocity of the flat-band electrons in magic-angle graphene (4x10^4 m/s). Furthermore, 191-8-66-C-r567x-1 has been confirmed to be a flat-band related magnetic half-metal with a magnetic moment of 1.854 miuB per cell, while 191-10-90-C-r567x-1 is a flat-band related magnetic normal metal with a magnetic moment of 1.663 miuB per cell. These results not only show that flat-bands can be constructed in carbon monolayer, but also indicate the potential for achieving metal-free magnetic materials with light elements based on flat-band theory.

cond-mat.mes-hall↗

arXiv2024

Cost-Effective Online Multi-LLM Selection with Versatile Reward Models

With the rapid advancement of large language models (LLMs), the diversity of multi-LLM tasks and the variability in their pricing structures have become increasingly important, as costs can vary greatly between different LLMs. To tackle these challenges, we introduce the \textit{C2MAB-V}, a \underline{C}ost-effective \underline{C}ombinatorial \underline{M}ulti-armed \underline{B}andit with \underline{V}ersatile reward models for optimal LLM selection and usage. This online model differs from traditional static approaches or those reliant on a single LLM without cost consideration. With multiple LLMs deployed on a scheduling cloud and a local server dedicated to handling user queries, \textit{C2MAB-V} facilitates the selection of multiple LLMs over a combinatorial search space, specifically tailored for various collaborative task types with different reward models. Based on our designed online feedback mechanism and confidence bound technique, \textit{C2MAB-V} can effectively address the multi-LLM selection challenge by managing the exploration-exploitation trade-off across different models, while also balancing cost and reward for diverse tasks. The NP-hard integer linear programming problem for selecting multiple LLMs with trade-off dilemmas is addressed by: i) decomposing the integer problem into a relaxed form by the local server, ii) utilizing a discretization rounding scheme that provides optimal LLM combinations by the scheduling cloud, and iii) continual online updates based on feedback. Theoretically, we prove that \textit{C2MAB-V} offers strict guarantees over versatile reward models, matching state-of-the-art results for regret and violations in some degenerate cases. Empirically, we show that \textit{C2MAB-V} effectively balances performance and cost-efficiency with nine LLMs for three application scenarios.

cs.LG↗

arXiv2024

Why Are Learned Indexes So Effective but Sometimes Ineffective?

Learned indexes have attracted significant research interest due to their ability to offer better space-time trade-offs compared to traditional B+-tree variants. Among various learned indexes, the PGM-Index based on error-bounded piecewise linear approximation is an elegant data structure that has demonstrated \emph{provably} superior performance over conventional B+-tree indexes. In this paper, we explore two interesting research questions regarding the PGM-Index: (a) \emph{Why are PGM-Indexes theoretically effective?} and (b) \emph{Why do PGM-Indexes underperform in practice?} For question~(a), we first prove that, for a set of $N$ sorted keys, the PGM-Index can, with high probability, achieve a lookup time of $O(\log\log N)$ while using $O(N)$ space. To the best of our knowledge, this is the \textbf{tightest bound} for learned indexes to date. For question~(b), we identify that querying PGM-Indexes is highly memory-bound, where the internal error-bounded search operations often become the bottleneck. To fill the performance gap, we propose PGM++, a \emph{simple yet effective} extension to the original PGM-Index that employs a mixture of different search strategies, with hyper-parameters automatically tuned through a calibrated cost model. Extensive experiments on real workloads demonstrate that PGM++ establishes a new Pareto frontier. At comparable space costs, PGM++ speeds up index lookup queries by up to $\mathbf{2.31\times}$ and $\mathbf{1.56\times}$ when compared to the original PGM-Index and state-of-the-art learned indexes.

cs.DB↗