arXiv subjects

Bowen Hao

Publications and source records attributed to Bowen Hao.

15 recordsLinked to original sources

arXiv2026

Enhancing Group Recommendation with Memory-Augmented Reasoning in LLM Agent

The core challenge in group recommendation lies in modeling the dynamic evolution of user preferences and explain?ing the consensus formation process. Existing Large Language Model (LLM)-based methods, despite improved interpretability, treat interaction history as fixed text, ignoring the natural evolution of group/user preferences over time, and lacking explicit modeling of the complex group decision-making process. To address these issues, we propose AGR, a LLM-based agent, which consists of a Memory Module and a Reasoning Module. The Memory Module employs a token-based hash table to dynamically manage the historical interactions of groups and users. This design supports fundamental operations including insertion, updating, retrieval, forgetting of irrelevant records, and summarization of evolving group and user profiles for efficiently tracking. Based on these retrieved dynamic profiles, the Reason?ing Module then performs a multi-step reasoning process includ?ing Group Interests Collection, Group Consensus Refinement, Multi-dimensional Evaluation and Explainable Recommendation Generation, thereby moving beyond black-box inference to de?liver fully interpretable recommendations. In practice, we adopt the Reinforcement Fine-Tuning (RFT) paradigm, where we first use Supervised Fine-Tuning (SFT) to equip the model with basic capabilities for invoking the Memory and Reasoning modules, and then employ Group Relative Policy Optimization (GRPO) to enhance its autonomous ability to coordinate these modules. Experiments on LastFM and Douban datasets demonstrate that AGR significantly outperforms existing state-of-the-art methods in both recommendation accuracy and explainability. Our model is open-sourced at https://huggingface.co/niuqimeng/AGR.

cs.IR↗

arXiv2026

Large Field-Free Superconducting Diode Effect with Nonmonotonic Polarity Reversals in NbSe$_2$/CrBr$_3$ Heterostructures

The superconducting diode effect (SDE), characterized by nonreciprocal dissipationless supercurrent, offers a promising route toward ultralow-power superconducting electronics. Yet most realizations require an external magnetic field, and achieving a large, controllable SDE at zero field remains challenging. Here we report a field-free SDE with an efficiency reaching 35.7% in a van der Waals NbSe$_2$/CrBr$_3$ heterostructure, whose polarity is programmable by magnetic-field history. Unlike conventional mechanisms based on finite-momentum pairing, the SDE originates from the leading symmetry-allowed cubic term odd in Cooper-pair momentum, which yields unequal critical currents while leaving the equilibrium condensate at zero momentum. Remarkably, upon sweeping a perpendicular magnetic field, the diode polarity undergoes nonmonotonic and hysteretic reversals that cannot be explained by Meissner screening or conventional ferromagnetic proximity. Combining transport measurements, micromagnetic simulations, and a generalized Ginzbur-Landau theory, we attribute these unconventional behaviors to layered ferrimagnetism in CrBr$_3$, where coexisting ferromagnetic and antiferromagnetic interlayer couplings produce a history-dependent interfacial exchange field acting on NbSe$_2$. Our results reveal a distinct mechanism for nonreciprocal superconductivity and establish layered van der Waals magnetism as a versatile platform for high-efficiency, programmable, field-free superconducting diodes.

cond-mat.supr-con↗

arXiv2026

Surface Functionalization Enables Two-Dimensional Altermagnetism and Giant Tunnel Magnetoresistance

Two-dimensional (2D) altermagnets (AMs) are highly desirable for ultrafast, stray-field-free spintronics because they combine compensated magnetic order and momentum-dependent spin splitting with the scalability, tunability, and interface compatibility of atomically thin materials. However, practical 2D AMs remain scarce. Rather than relying solely on the search for intrinsic 2D AMs, an appealing route is to transform known 2D antiferromagnets (AFMs) into AMs through symmetry engineering. Here, we propose surface functionalization as a symmetry-guided, nonvolatile chemical switch for realizing this AFM-to-AM transformation. By breaking inversion and out-of-plane mirror symmetries while preserving the rotation symmetry connecting opposite-spin sublattices, single-sided functionalization lifts spin degeneracy and induces altermagnetic spin splitting. Using monolayer FeSe as a representative platform, first-principles calculations show that hydrogenation, oxidation, and fluorination convert spin-degenerate antiferromagnetic FeSe into a d-wave AM with pronounced momentum-dependent spin splitting. At the device level, our transport simulations reveal that the functionalized FeSe monolayer magnetic tunnel junctions exhibit giant tunnel magnetoresistance (TMR) up to $1.87\times10^3\%$, originating from momentum-selective spin filtering between parallel and antiparallel Néel-vector configurations. The strong dependence of TMR on functionalization geometry further demonstrates that surface chemistry provides an effective control knob for altermagnetic transport. Our work establishes a symmetry-to-chemistry-to-device strategy for engineering 2D AMs and developing high-performance altermagnetic spintronic devices.

cond-mat.mtrl-sci↗

arXiv2026

Altermagnets Enable Gate-Switchable Helical and Chiral Topological Transport with Spin-Valley-Momentum-Locked Dual Protection

We establish a unified, symmetry-driven framework that combines the alternating spin splitting of altermagnets with valley topology to realize and electrically interconvert helical and chiral topological phases within a single material platform. We first demonstrate a magnetic analogue of the quantum spin Hall effect in altermagnets, hosting helical spin-valley-momentum-locked (SVML) edge states characterized by a composite spin-valley Chern number Csv = 2. Large-scale quantum transport simulations show these SVML edge states exhibit fully quantized spin conductance robust against nonmagnetic and long-range magnetic disorder, reflecting their dual topological protection, while remaining vulnerable to short-range magnetic disorder. Exploiting that the counterpropagating SVML modes are linked by crystal rotation symmetry, we introduce a gate-tunable sublattice-staggered potential that selectively gaps one valley and converts the helical state into a chiral quantum anomalous Hall phase with Csv = 1, robust against all disorder types. Reversing the potential switches the transmitted spin-valley polarization. Our first-principles calculations identify monolayer V2STeO and VO families as realistic platforms supporting both helical and chiral topological phases and their electrical switching. These results establish altermagnets as electrically programmable platforms for robust topological devices across charge, spin, and valley.

cond-mat.mes-hall↗

arXiv2026

Interface-Enhanced Superconductivity in Ultrathin TiN Proximitized by Topological Insulators

High-quality topological insulator-superconductor (TI-SC) heterostructure with an atomically sharp and well-controlled interface is crucial for realizing topological superconductivity and topological quantum qubit. In particular, many studies of TI-SC heterostructures have focused on inducing superconducting gap in the TI layer via proximity effect, while the active manipulation of superconductivity in the SC layer remains largely unexplored. In this work, we fabricated TI/TiN heterostructures using highly air-stable, ultrathin TiN films as the SC layer, and observed an interface-enhanced superconductivity that contrasts with the conventional proximity effect in superconductor-normal metal interface. Band structure measurements reveal a consistent shift of Dirac point with Tc enhancement. Interfacial charge transfer provides a plausible explanation for this shift based on the systematic analysis and is therefore a likely contributor to the observed Tc enhancement. First principles calculations elucidate the charge transfer pathways, highlighting the critical role of the interfacial BiTe (BiSe)bilayer. Our results not only provide a tunable TI-SC hybrid system with robust superconductivity at ultrathin thickness, but also offer a potential route for manipulating superconductivity in TI-SC heterostructures via interface engineering.

cond-mat.mtrl-sci↗

arXiv2026

Symmetry-Driven Unconventional Magnetoelectric Coupling in Perovskite Altermagnets: From Bulk to the Two-Dimensional Limit

The emergence of altermagnets establishes a new paradigm for multiferroics. Unlike conventional multiferroics relying on direct magnetoelectric coupling, multiferroic altermagnets host a crystal-symmetry-mediated magnetoelectric interaction that is intrinsically more efficient and robust. Among candidate material platforms, layered perovskites are particularly appealing owing to their structural diversity and synthetic versatility. However, magnetoelectric properties at the two-dimensional scale remain largely unexplored, hindering their applicability in miniaturized, highly integrated devices. Here, we systematically investigate the dimensional evolution of ferroelectric polarization and magnetism in perovskite systems through symmetry analysis. We demonstrate that altermagnetism can persist in the two-dimensional limit, yet is strongly constrained by the magnetic configuration-with only C-type antiferromagnetic order supporting it. Based on mode-decomposition calculations, we further reveal that symmetry-restricted multimode couplings simultaneously govern ferroelectric polarization and altermagnetic spin splitting. Finally, combined with first-principles calculations, we propose several strategies to lift the magnetic-configuration constraint, extending the range of viable altermagnetic systems. These results underscore the critical role of dimensionality in symmetry-driven magnetoelectric coupling in perovskite altermagnets and pave the way toward next-generation electrically controlled spintronic and multiferroic devices.

cond-mat.mtrl-sci↗

arXiv2025

Emergent Multiferroic Altermagnets and Spin Control via Noncollinear Molecular Polarization

Altermagnets, with spin splitting and vanishing magnetization, have been attributed to many fascinating phenomena and potential applications. In particular, integrating ferroelectricity with altermagnetism to enable magnetoelectric coupling and electric control of spin has drawn significant attention. However, its experimental realization and precise spin manipulation remain elusive. Here, by focusing on molecular ferroelectrics, the first discovered ferroelectrics renowned for their highly controllable molecular polarizations and structural flexibility, we reveal that these obstacles can be removed by an emergent multiferroic altermagnets with tunable spin polarization in a large class of fabricated organic materials. Using a symmetry-based design and a tight-binding model, we uncover the underlying mechanism of such molecular ferroelectric altermagnets and demonstrate how noncollinear molecular polarization can switch the spin polarization on and off and even reverse its sign. From the first-principles calculations, we verify the feasibility of these materials in a series of well-established hybrid organic-inorganic perovskites and metal-organic frameworks. Our findings bridge molecular ferroelectrics and altermagnetic spintronics, highlighting an unexplored potential of multifunctional organic multiferroics.

cond-mat.mtrl-sci↗

arXiv2025

ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula

Traditional Chinese Medicine (TCM) formulas play a significant role in treating epidemics and complex diseases. Existing models for TCM utilize traditional algorithms or deep learning techniques to analyze formula relationships, yet lack comprehensive results, such as complete formula compositions and detailed explanations. Although recent efforts have used TCM instruction datasets to fine-tune Large Language Models (LLMs) for explainable formula generation, existing datasets lack sufficient details, such as the roles of the formula's sovereign, minister, assistant, courier; efficacy; contraindications; tongue and pulse diagnosis-limiting the depth of model outputs. To address these challenges, we propose ZhiFangDanTai, a framework combining Graph-based Retrieval-Augmented Generation (GraphRAG) with LLM fine-tuning. ZhiFangDanTai uses GraphRAG to retrieve and synthesize structured TCM knowledge into concise summaries, while also constructing an enhanced instruction dataset to improve LLMs' ability to integrate retrieved information. Furthermore, we provide novel theoretical proofs demonstrating that integrating GraphRAG with fine-tuning techniques can reduce generalization error and hallucination rates in the TCM formula task. Experimental results on both collected and clinical datasets demonstrate that ZhiFangDanTai achieves significant improvements over state-of-the-art models. Our model is open-sourced at https://huggingface.co/tczzx6/ZhiFangDanTai1.0.

cs.CL↗

arXiv2025

Two-Dimensional Ferroelectric Altermagnets: From Model to Material Realization

Multiferroic altermagnets offer new opportunities for magnetoelectric coupling and electrically tunable spintronics. However, due to intrinsic symmetry conflicts between altermagnetism and ferroelectricity, achieving their coexistence, known as ferroelectric altermagnets (FEAM), remains an outstanding challenge, especially in two-dimensional (2D) systems. Here, we propose a universal, symmetry-based design principle for 2D FEAM, supported by tight-binding models and first-principles calculations. We show that lattice distortions can break spin equivalence and introduce the necessary rotation-related symmetry, enabling altermagnetism with electrically reversible spin splitting. Guided by this framework, we identify a family of 2D vanadium oxyhalides and sulfide halides as promising FEAM candidates. In these compounds, pseudo Jahn-Teller distortions and Peierls-like dimerization cooperatively establish the required symmetry conditions. We further propose the magneto-optical Kerr effect as an experimental probe to confirm FEAM and its electric spin reversal. Our findings provide a practical framework for 2D FEAM and advancing electrically controlled spintronic devices.

cond-mat.mtrl-sci↗

arXiv2025

LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition

Visual speech recognition (VSR), commonly known as lip reading, has garnered significant attention due to its wide-ranging practical applications. The advent of deep learning techniques and advancements in hardware capabilities have significantly enhanced the performance of lip reading models. Despite these advancements, existing datasets predominantly feature stable video recordings with limited variability in lip movements. This limitation results in models that are highly sensitive to variations encountered in real-world scenarios. To address this issue, we propose a novel framework, LipGen, which aims to improve model robustness by leveraging speech-driven synthetic visual data, thereby mitigating the constraints of current datasets. Additionally, we introduce an auxiliary task that incorporates viseme classification alongside attention mechanisms. This approach facilitates the efficient integration of temporal information, directing the model's focus toward the relevant segments of speech, thereby enhancing discriminative capabilities. Our method demonstrates superior performance compared to the current state-of-the-art on the lip reading in the wild (LRW) dataset and exhibits even more pronounced advantages under challenging conditions.

cs.CV↗

arXiv2023

Motif-Based Prompt Learning for Universal Cross-Domain Recommendation

Cross-Domain Recommendation (CDR) stands as a pivotal technology addressing issues of data sparsity and cold start by transferring general knowledge from the source to the target domain. However, existing CDR models suffer limitations in adaptability across various scenarios due to their inherent complexity. To tackle this challenge, recent advancements introduce universal CDR models that leverage shared embeddings to capture general knowledge across domains and transfer it through "Multi-task Learning" or "Pre-train, Fine-tune" paradigms. However, these models often overlook the broader structural topology that spans domains and fail to align training objectives, potentially leading to negative transfer. To address these issues, we propose a motif-based prompt learning framework, MOP, which introduces motif-based shared embeddings to encapsulate generalized domain knowledge, catering to both intra-domain and inter-domain CDR tasks. Specifically, we devise three typical motifs: butterfly, triangle, and random walk, and encode them through a Motif-based Encoder to obtain motif-based shared embeddings. Moreover, we train MOP under the "Pre-training \& Prompt Tuning" paradigm. By unifying pre-training and recommendation tasks as a common motif-based similarity learning task and integrating adaptable prompt parameters to guide the model in downstream recommendation tasks, MOP excels in transferring domain knowledge effectively. Experimental results on four distinct CDR tasks demonstrate the effectiveness of MOP than the state-of-the-art models.

cs.IR↗

arXiv2022

Self-supervised Graph Learning for Occasional Group Recommendation

As an important branch in Recommender System, occasional group recommendation has received more and more attention. In this scenario, each occasional group (cold-start group) has no or few historical interacted items. As each occasional group has extremely sparse interactions with items, traditional group recommendation methods can not learn high-quality group representations. The recent proposed Graph Neural Networks (GNNs), which incorporate the high-order neighbors of the target occasional group, can alleviate the above problem in some extent. However, these GNNs still can not explicitly strengthen the embedding quality of the high-order neighbors with few interactions. Motivated by the Self-supervised Learning technique, which is able to find the correlations within the data itself, we propose a self-supervised graph learning framework, which takes the user/item/group embedding reconstruction as the pretext task to enhance the embeddings of the cold-start users/items/groups. In order to explicitly enhance the high-order cold-start neighbors' embedding quality, we further introduce an embedding enhancer, which leverages the self-attention mechanism to improve the embedding quality for them. Comprehensive experiments show the advantages of our proposed framework than the state-of-the-art methods.

cs.IR↗

arXiv2022

A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation

Cold-start problem is a fundamental challenge for recommendation tasks. The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation. However, due to the over-smoothing problem, PT-GNN can only capture up to 3-order relation, which can not provide much useful auxiliary information to depict the target cold-start user or item. Besides, the embedding reconstruction task only considers the intra-correlations within the subgraph of users and items, while ignoring the inter-correlations across different subgraphs. To solve the above challenges, we propose a multi-strategy based pre-training method for cold-start recommendation (MPT), which extends PT-GNN from the perspective of model architecture and pretext tasks to improve the cold-start recommendation performance. Specifically, in terms of the model architecture, in addition to the short-range dependencies of users and items captured by the GNN encoder, we introduce a Transformer encoder to capture long-range dependencies. In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add embedding contrastive learning task to capture inter-correlations of users and items. We train the GNN and Transformer encoders on these pretext tasks under the meta-learning setting to simulate the real cold-start scenario, making the model easily and rapidly being adapted to new cold-start users and items. Experiments on three public recommendation datasets show the superiority of the proposed MPT model against the vanilla GNN models, the pre-training GNN model on user/item embedding inference and the recommendation task.

cs.IR↗

arXiv2020

Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach

The proliferation of massive open online courses (MOOCs) demands an effective way of course recommendation for jobs posted in recruitment websites, especially for the people who take MOOCs to find new jobs. Despite the advances of supervised ranking models, the lack of enough supervised signals prevents us from directly learning a supervised ranking model. This paper proposes a general automated weak supervision framework AutoWeakS via reinforcement learning to solve the problem. On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models. On the other hand, the framework enables automatically searching the optimal combination of these supervised and unsupervised models. Systematically, we evaluate the proposed model on several datasets of jobs from different recruitment websites and courses from a MOOCs platform. Experiments show that our model significantly outperforms the classical unsupervised, supervised and weak supervision baselines.

cs.DB↗

arXiv2020

Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation

Cold-start problem is a fundamental challenge for recommendation tasks. Despite the recent advances on Graph Neural Networks (GNNs) incorporate the high-order collaborative signal to alleviate the problem, the embeddings of the cold-start users and items aren't explicitly optimized, and the cold-start neighbors are not dealt with during the graph convolution in GNNs. This paper proposes to pre-train a GNN model before applying it for recommendation. Unlike the goal of recommendation, the pre-training GNN simulates the cold-start scenarios from the users/items with sufficient interactions and takes the embedding reconstruction as the pretext task, such that it can directly improve the embedding quality and can be easily adapted to the new cold-start users/items. To further reduce the impact from the cold-start neighbors, we incorporate a self-attention-based meta aggregator to enhance the aggregation ability of each graph convolution step, and an adaptive neighbor sampler to select the effective neighbors according to the feedbacks from the pre-training GNN model. Experiments on three public recommendation datasets show the superiority of our pre-training GNN model against the original GNN models on user/item embedding inference and the recommendation task.

cs.IR↗