arXiv subjects

Jialin Chen

Publications and source records attributed to Jialin Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Magnetically Mediated Cross-Layer Pairing in Pressurized Trilayer Nickelate La$_4$Ni$_3$O$_{10}$

The recently discovered trilayer nickelate superconductor La$_4$Ni$_3$O$_{10}$ under pressure has emerged as a promising platform for exploring unconventional superconductivity. However, the pairing mechanism remains a subject of active investigations. With large-scale density matrix renormalization group calculations on a realistic two-orbital trilayer Hubbard model, we elucidate the superconducting (SC) mechanism in this system. Our results reveal distinct magnetic correlations in the two different orbitals: while the $d_{z^2}$ orbital exhibits both interlayer and cross-layer antiferromagnetic (AFM) correlations, the $d_{x^2-y^2}$ orbital shows exclusively cross-layer AFM correlations, rendering a quasi-long-range SC order in the latter. We demonstrate that the Hund's rule coupling is essential for forming the SC order, and discuss the effects of kinetic AFM correlation and Hubbard repulsive $U$. Our findings motivate a further simplification of the trilayer Hubbard to an effective bilayer mixed-dimensional Hubbard model, providing a unified framework for understanding interlayer SC in both trilayer and bilayer nickelates.

cond-mat.str-el↗

arXiv2025

Low-Rank Adaptation for Foundation Models: A Comprehensive Review

The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing, computer vision, and scientific discovery. However, the substantial parameter count of these models, often reaching billions or trillions, poses significant challenges in adapting them to specific downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a highly promising approach for mitigating these challenges, offering a parameter-efficient mechanism to fine-tune foundation models with minimal computational overhead. This survey provides the first comprehensive review of LoRA techniques beyond large Language Models to general foundation models, including recent techniques foundations, emerging frontiers and applications of low-rank adaptation across multiple domains. Finally, this survey discusses key challenges and future research directions in theoretical understanding, scalability, and robustness. This survey serves as a valuable resource for researchers and practitioners working with efficient foundation model adaptation.

cs.LG↗

arXiv2025

GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models

Retrieval-Augmented Generation (RAG) has significantly mitigated the hallucinations of Large Language Models (LLMs) by grounding the generation with external knowledge. Recent extensions of RAG to graph-based retrieval offer a promising direction, leveraging the structural knowledge for multi-hop reasoning. However, existing graph RAG typically decouples retrieval and reasoning processes, which prevents the retriever from adapting to the reasoning needs of the LLM. They also struggle with scalability when performing multi-hop expansion over large-scale graphs, or depend heavily on annotated ground-truth entities, which are often unavailable in open-domain settings. To address these challenges, we propose a novel graph retriever trained end-to-end with LLM, which features an attention-based growing and pruning mechanism, adaptively navigating multi-hop relevant entities while filtering out noise. Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together, thereby enhancing its reasoning capability and facilitating interactive joint training of the graph retriever and the LLM reasoner. Experimental results across three QA benchmarks show that our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks. Notably, our framework eliminates the need for predefined ground-truth entities by directly optimizing the retriever using LLM logits as implicit feedback, making it especially effective in open-domain settings.

cs.LG↗

arXiv2025

Analyzing Gait Adaptation with Hemiplegia Simulation Suits and Digital Twins

To advance the development of assistive and rehabilitation robots, it is essential to conduct experiments early in the design cycle. However, testing early prototypes directly with users can pose safety risks. To address this, we explore the use of condition-specific simulation suits worn by healthy participants in controlled environments as a means to study gait changes associated with various impairments and support rapid prototyping. This paper presents a study analyzing the impact of a hemiplegia simulation suit on gait. We collected biomechanical data using a Vicon motion capture system and Delsys Trigno EMG and IMU sensors under four walking conditions: with and without a rollator, and with and without the simulation suit. The gait data was integrated into a digital twin model, enabling machine learning analyses to detect the use of the simulation suit and rollator, identify turning behavior, and evaluate how the suit affects gait over time. Our findings show that the simulation suit significantly alters movement and muscle activation patterns, prompting users to compensate with more abrupt motions. We also identify key features and sensor modalities that are most informative for accurately capturing gait dynamics and modeling human-rollator interaction within the digital twin framework.

cs.ET↗

arXiv2025

Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks

In the era of foundation models and Large Language Models (LLMs), Euclidean space is the de facto geometric setting of our machine learning architectures. However, recent literature has demonstrated that this choice comes with fundamental limitations. To that end, non-Euclidean learning is quickly gaining traction, particularly in web-related applications where complex relationships and structures are prevalent. Non-Euclidean spaces, such as hyperbolic, spherical, and mixed-curvature spaces, have been shown to provide more efficient and effective representations for data with intrinsic geometric properties, including web-related data like social network topology, query-document relationships, and user-item interactions. Integrating foundation models with non-Euclidean geometries has great potential to enhance their ability to capture and model the underlying structures, leading to better performance in search, recommendations, and content understanding. This workshop focuses on the intersection of Non-Euclidean Foundation Models and Geometric Learning (NEGEL), exploring its potential benefits, including the potential benefits for advancing web-related technologies, challenges, and future directions. Workshop page: [https://hyperboliclearning.github.io/events/www2025workshop](https://hyperboliclearning.github.io/events/www2025workshop)

cs.CG↗

arXiv2025

DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments

This paper introduces DYNUS, an uncertainty-aware trajectory planner designed for dynamic unknown environments. Operating in such settings presents many challenges -- most notably, because the agent cannot predict the ground-truth future paths of obstacles, a previously planned trajectory can become unsafe at any moment, requiring rapid replanning to avoid collisions. Recently developed planners have used soft-constraint approaches to achieve the necessary fast computation times; however, these methods do not guarantee collision-free paths even with static obstacles. In contrast, hard-constraint methods ensure collision-free safety, but typically have longer computation times. To address these issues, we propose three key contributions. First, the DYNUS Global Planner (DGP) and Temporal Safe Corridor Generation operate in spatio-temporal space and handle both static and dynamic obstacles in the 3D environment. Second, the Safe Planning Framework leverages a combination of exploratory, safe, and contingency trajectories to flexibly re-route when potential future collisions with dynamic obstacles are detected. Finally, the Fast Hard-Constraint Local Trajectory Formulation uses a variable elimination approach to reduce the problem size and enable faster computation by pre-computing dependencies between free and dependent variables while still ensuring collision-free trajectories. We evaluated DYNUS in a variety of simulations, including dense forests, confined office spaces, cave systems, and dynamic environments. Our experiments show that DYNUS achieves a success rate of 100% and travel times that are approximately 25.0% faster than state-of-the-art methods. We also evaluated DYNUS on multiple platforms -- a quadrotor, a wheeled robot, and a quadruped -- in both simulation and hardware experiments.

cs.RO↗

arXiv2025

Strange mesons with one dynamical gluon: A light-front approach

We obtain the mass spectra of strange mesons using a light-front quantized Hamiltonian with Quantum Chromodynamics (QCD) input, incorporating quark-antiquark and quark-antiquark-gluon Fock components, along with a three-dimensional confinement. We work within the basis light-front quantization framework. The resulting eigenvectors can simultaneously describe the kaon's electromagnetic form factor, decay constant, distribution amplitude, and quark and gluon distribution functions under QCD scale evolution. Using the obtained kaon parton distribution functions (PDFs), supplemented by established nuclear PDFs, we also predict the kaon-nucleus-induced Drell-Yan cross section, which is expected to be measured soon by COMPASS++/AMBER at CERN.

hep-ph↗

arXiv2024

From Similarity to Superiority: Channel Clustering for Time Series Forecasting

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overlooking essential interactions between channels. Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM). CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster information instead of individual channel identities, combining the best of CD and CI worlds. Extensive experiments on real-world datasets demonstrate that CCM can (1) boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively; (2) enable zero-shot forecasting with mainstream time series forecasting models; (3) uncover intrinsic time series patterns among channels and improve interpretability of complex time series models.

cs.LG↗

arXiv2024

DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs

Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios, where each node and edge are associated with text descriptions, and both the graph structure and text descriptions evolve over time. Despite their broad applicability, there is a notable scarcity of benchmark datasets tailored to DyTAGs, which hinders the potential advancement in many research fields. To address this gap, we introduce Dynamic Text-attributed Graph Benchmark (DTGB), a collection of large-scale, time-evolving graphs from diverse domains, with nodes and edges enriched by dynamically changing text attributes and categories. To facilitate the use of DTGB, we design standardized evaluation procedures based on four real-world use cases: future link prediction, destination node retrieval, edge classification, and textual relation generation. These tasks require models to understand both dynamic graph structures and natural language, highlighting the unique challenges posed by DyTAGs. Moreover, we conduct extensive benchmark experiments on DTGB, evaluating 7 popular dynamic graph learning algorithms and their variants of adapting to text attributes with LLM embeddings, along with 6 powerful large language models (LLMs). Our results show the limitations of existing models in handling DyTAGs. Our analysis also demonstrates the utility of DTGB in investigating the incorporation of structural and textual dynamics. The proposed DTGB fosters research on DyTAGs and their broad applications. It offers a comprehensive benchmark for evaluating and advancing models to handle the interplay between dynamic graph structures and natural language. The dataset and source code are available at https://github.com/zjs123/DTGB.

cs.AI↗

arXiv2024

Coherently amplified ultrafast imaging using a free-electron interferometer

Accessing the low-energy non-equilibrium dynamics of materials and their polaritons with simultaneous high spatial and temporal resolution has been a bold frontier of electron microscopy in recent years. One of the main challenges lies in the ability to retrieve extremely weak signals while simultaneously disentangling amplitude and phase information. Here, we present Free-Electron Ramsey Imaging (FERI), a microscopy approach based on light-induced electron modulation that enables coherent amplification of optical near-fields in electron imaging. We provide simultaneous time-, space-, and phase-resolved measurements of a micro-drum made from a hexagonal boron nitride membrane visualizing the sub-cycle dynamics of 2D polariton wavepackets therein. The phase-resolved measurements reveals vortex-anti-vortex singularities on the polariton wavefronts, together with an intriguing phenomenon of a traveling wave mimicking the amplitude profile of a standing wave. Our experiments show a 20-fold coherent amplification of the near-field signal compared to conventional electron near-field imaging, resolving peak field intensities in the order of ~W/cm2, corresponding to field amplitudes of a few kV/m. As a result, our work paves the way for spatio-temporal electron microscopy of biological specimens and quantum materials, exciting yet delicate samples that are currently difficult to investigate.

physics.optics↗

arXiv2024

High-Resolution Observation and Magnetic Modeling of a Solar Minifilament: the Formation, Eruption and Failing Mechanisms

Minifilaments are widespread small-scale structures in the solar atmosphere. To better understand their formation and eruption mechanisms, we investigate the entire life of a sigmoidal minifilament located below a large quiescent filament observed by BBSO/GST on 2015 August 3. The Hα structure initially appears as a group of arched threads, then transforms into two J-shaped arcades, and finally forms a sigmoidal shape. SDO/AIA observations in 171Å show that two coronal jets occur around the southern footpoint of the minifilament before the minifilament eruption. The minifilament eruption starts from the southern footpoint, then interacts with the overlying filament and fails. The aforementioned observational changes correspond to three episodes of flux cancellations observed by SDO/HMI. Unlike previous studies, the flux cancellation occurs between the polarity where southern footpoint of the minifilament is rooted in and an external polarity. We construct two magnetic field models before the eruption using the flux rope insertion method, and find an hyperbolic flux tube (HFT) above the flux cancellation site. The observation and modeling results suggest that the eruption is triggered by the external magnetic reconnection between the core field of the minifilament and the external fields due to flux cancellations. This study reveals a new triggering mechanism for minifilament eruptions and a new relationship between minifilament eruptions and coronal jets.

astro-ph.SR↗

arXiv2024

Orbital-selective Superconductivity in the Pressurized Bilayer Nickelate La$_3$Ni$_2$O$_7$: An Infinite Projected Entangled-Pair State Study

The newly discovered high-$T_c$ nickelate superconductor La$_3$Ni$_2$O$_7$ has generated significant research interest. To uncover the pairing mechanism, it is essential to investigate the intriguing interplay between the two $e_g$, i.e., $d_{x^2-y^2}$ and $d_{z^2}$ orbitals. Here we perform an infinite projected entangled-pair state (iPEPS) study of the bilayer $t$-$J$ model, directly in the thermodynamic limit and with orbitally selective parameters for $d_{x^2-y^2}$ and $d_{z^2}$ orbitals, respectively. The $d_{x^2-y^2}$ electrons exhibit significant intralayer hopping $t_\parallel$ and spin couplings $J_\parallel$, with interlayer $J_\perp$ passed from the $d_{z^2}$ electrons. However, the interlayer $t_\perp$ is negligible in this case. In contrast, the $d_{z^2}$ orbital demonstrates strong interlayer $t_\perp$ and $J_\perp$, while the inherent intralayer $t_\parallel$ and $J_\parallel$ are small. Based on the iPEPS results, we find clear orbital-selective behaviors in La$_3$Ni$_2$O$_7$. The $d_{x^2-y^2}$ orbitals exhibit robust superconductive (SC) order driven by the interlayer coupling $J_\perp$; while the $d_{z^2}$ band shows relatively weak SC order as a result of small $t_\parallel$ (lack of coherence) but large $t_\perp$ (strong Pauli blocking). Furthermore, by substituting rare-earth element Pm or Sm with La, we find an enhanced SC order, which opens up a promising avenue for discovering nickelate superconductors with even higher $T_c$.

cond-mat.str-el↗

arXiv2024

Qubit-Wise Architecture Search Method for Variational Quantum Circuits

Considering the noise level limit, one crucial aspect for quantum machine learning is to design a high-performing variational quantum circuit architecture with small number of quantum gates. As the classical neural architecture search (NAS), quantum architecture search methods (QAS) employ methods like reinforcement learning, evolutionary algorithms and supernet optimiza-tion to improve the search efficiency. In this paper, we propose a novel qubit-wise architec-ture search (QWAS) method, which progres-sively search one-qubit configuration per stage, and combine with Monte Carlo Tree Search al-gorithm to find good quantum architectures by partitioning the search space into several good and bad subregions. The numerical experimental results indicate that our proposed method can balance the exploration and exploitation of cir-cuit performance and size in some real-world tasks, such as MNIST, Fashion and MOSI. As far as we know, QWAS achieves the state-of-art re-sults of all tasks in the terms of accuracy and circuit size.

quant-ph↗

arXiv2024

Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition

The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-the-art attention model is scalable to accommodate the growing sequence lengths typically encountered in high-resolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of capturing both short-term fluctuations and long-term trends in the data. We then propose a new time series transformer backbone (KronTime) by introducing Kronecker-decomposed attention to process such multi-level time series, which sequentially calculates attention from the lower level to the upper level. Experiments on four long time series datasets demonstrate superior classification results with improved efficiency compared to baseline methods.

cs.LG↗

arXiv2024

Pair density wave, unconventional superconductivity, and non-Fermi liquid quantum critical phase in frustrated Kondo lattice

Motivated by the recent discovery of an intermediate quantum critical phase between the antiferromagnetic order and the Fermi liquid in the frustrated Kondo lattice CePdAl, we study here a Kondo-Heisenberg chain with frustrated $J_1$-$J_2$ XXZ interactions among local spins using the density matrix renormalization group method. Our simulations reveal a global phase diagram with rich ground states including the antiferromagnetic order, the valence-bond-solid and bond-order-wave orders, the pair density wave state, the uniform superconducting state, and the Luttinger liquid state. We show that both the pair density wave and uniform superconductivity belong to the family of Luther-Emery liquids and may arise from pair instability of an intermediate quantum critical phase with medium Fermi volume in the presence of strong quantum fluctuations, while the Luttinger liquid has a large Fermi volume. This suggests a deep connection between the pair density wave, the unconventional superconductivity, and the non-Fermi liquid quantum critical phase.

cond-mat.str-el↗

arXiv2024

Bilayer $t$-$J$-$J_\perp$ Model and Magnetically Mediated Pairing in the Pressurized Nickelate La$_3$Ni$_2$O$_7$

The recently discovered nickelate superconductor La$_3$Ni$_2$O$_7$ has a high transition temperature near 80 K under pressure, which offers additional avenues of unconventional superconductivity. Here with state-of-the-art tensor-network methods, we study a bilayer $t$-$J$-$J_\perp$ model for La$_3$Ni$_2$O$_7$ and find a robust $s$-wave superconductive (SC) order mediated by interlayer magnetic couplings. Large-scale density matrix renormalization group calculations find algebraic pairing correlations with Luttinger parameter of $K_{\rm SC} \simeq 1$. Infinite projected entangled-pair state method obtains a nonzero SC order directly in the thermodynamic limit, and estimates a strong pairing strength $\barΔ_z \sim \mathcal{O}(0.1)$. Tangent-space tensor renormalization group simulations further determine a high SC temperature $T_c^*/J \sim \mathcal{O}(0.1)$ and clarify the temperature evolution of SC order. Because of the intriguing orbital selective behaviors and strong Hund's rule coupling in the compound, $t$-$J$-$J_\perp$ model has strong interlayer spin exchange (while negligible interlayer hopping), which greatly enhances the SC pairing in the bilayer system. Such a magnetically mediated strong pairing has also been observed recently in the optical lattice of ultracold atoms. Our accurate and comprehensive tensor-network calculations reveal robust SC order in the bilayer $t$-$J$-$J_\perp$ model and shed light on the high-$T_c$ superconductivity in the pressurized nickelate La$_3$Ni$_2$O$_7$.

cond-mat.str-el↗

arXiv2023

Generative Explanations for Graph Neural Network: Methods and Evaluations

Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to uncover the decision-making logic of GNNs, by generating underlying explanatory substructures. In this paper, we conduct a comprehensive review of the existing explanation methods for GNNs from the perspective of graph generation. Specifically, we propose a unified optimization objective for generative explanation methods, comprising two sub-objectives: Attribution and Information constraints. We further demonstrate their specific manifestations in various generative model architectures and different explanation scenarios. With the unified objective of the explanation problem, we reveal the shared characteristics and distinctions among current methods, laying the foundation for future methodological advancements. Empirical results demonstrate the advantages and limitations of different explainability approaches in terms of explanation performance, efficiency, and generalizability.

cs.LG↗

arXiv2023

Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation

Graph convolutions have been a pivotal element in learning graph representations. However, recursively aggregating neighboring information with graph convolutions leads to indistinguishable node features in deep layers, which is known as the over-smoothing issue. The performance of graph neural networks decays fast as the number of stacked layers increases, and the Dirichlet energy associated with the graph decreases to zero as well. In this work, we introduce a framelet system into the analysis of Dirichlet energy and take a multi-scale perspective to leverage the Dirichlet energy and alleviate the over-smoothing issue. Specifically, we develop a Framelet Augmentation strategy by adjusting the update rules with positive and negative increments for low-pass and high-passes respectively. Based on that, we design the Energy Enhanced Convolution (EEConv), which is an effective and practical operation that is proved to strictly enhance Dirichlet energy. From a message-passing perspective, EEConv inherits multi-hop aggregation property from the framelet transform and takes into account all hops in the multi-scale representation, which benefits the node classification tasks over heterophilous graphs. Experiments show that deep GNNs with EEConv achieve state-of-the-art performance over various node classification datasets, especially for heterophilous graphs, while also lifting the Dirichlet energy as the network goes deeper.

cs.LG↗