arXiv subjects

Junting Wang

Publications and source records attributed to Junting Wang.

13 recordsLinked to original sources

arXiv2026

Classical and vincular patterns of length three in generalized alternating permutations

Let k be an integer at least 2, and let D_{N,k} be the set of permutations of {1,...,N} whose descent set is exactly {k, 2k, ..., k*floor((N-1)/k)}. We enumerate the elements of D_{N,k} avoiding each classical and each vincular pattern of length three. For classical patterns, we give recursive bijections from the 132- and 231-avoiding classes to ordered forests of complete k-ary trees, obtaining the Raney number. The 213- and 312-avoiding classes are obtained from these forest bijections by completing the last block and applying reverse-complement symmetry. The remaining classical case 321 is expressed by RSK. For vincular patterns, we enumerate the six fully consecutive patterns and the twelve patterns with exactly one adjacency. The closed-form results are accompanied by bijective models: the Catalan, Raney, Fuss-Catalan, and RSK cases are natural k-ary or fixed-descent extensions of classical bijections, while the product and poset cases arise from block-insertion and record/tree-poset encodings forced by the adjacency conditions.

math.CO↗

arXiv2026

Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

Semantic IDs (SIDs) are now a central component of generative recommendation. Current SID-based systems assign three roles to the same token sequence. Shared prefixes are intended to organize related items, the complete SID identifies an individual item, and each generated token narrows the items that can still be returned. We systematically investigate SIDs from item encoding and SID construction to autoregressive generation and final recommendation. We examine how SID construction changes item representations and how those changes affect generation. Across three Amazon domains and eight SID constructions, SID neighborhoods recover only 32.2% of the encoder's ten nearest neighbors on average. Alternative item descriptions still retrieve the corresponding item first in 99.57% of controlled cases, yet change 38.4% of exact SIDs. These results show that SIDs retain broad organization but lose much of the encoder's fine local structure, while their exact tokens are not determined by item meaning alone. This loss becomes consequential during generation. After the final semantic token, TIGER retains only 29.9% of held-out targets that were plausible recommendations before SID filtering. Motivated by these findings, we propose Item-Supported Decoding (ISD), a lightweight inference-time method that allows a user-specific item ranking to support corresponding SID prefixes before beam search discards them. The same ranking then orders the generated items. ISD requires no additional parameters or retraining of the SID constructor or decoder. We empirically show that ISD improves NDCG@10 over the corresponding SID backbone in every evaluated setting, with relative gains of up to 31.2%. Our results show that SIDs provide useful coarse item organization, but their fine boundaries should not alone determine which items remain available during generation.

cs.AI↗

arXiv2026

SafeImpute: Reliable Clinical Data Imputation via Conformal Selection

Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly, leading to pervasive missingness. While many imputation methods improve average accuracy, they provide limited guidance on which imputed values are reliable enough for high-stakes downstream use. In this work, we study reliable clinical imputation, aiming to produce accurate imputations while selectively releasing the reliable results, with statistical control over clinically unacceptable errors. To achieve this goal, we propose SafeImpute, a reliable imputation framework for irregular and sparse clinical longitudinal records. SafeImpute constructs an event graph that captures both intra-patient temporal trajectories and inter-patient clinical similarity, and learns imputations with a two-relation GNN and adaptive fusion, regularized by an auxiliary masked reconstruction objective. For reliability guarantees, SafeImpute converts a proxy risk score into conformal p-values and applies the Benjamini--Hochberg procedure to control the false discovery rate (FDR) of unacceptable errors among released imputations at a user-specified tolerance. Experiments on our Mayo Clinic data, the public MIMIC-III and MIMIC-IV datasets show that SafeImpute achieves strong imputation accuracy while providing reliable error control, outperforming diverse baselines in both standard imputation evaluation and FDR-controlled selective-release evaluation.

cs.LG↗

arXiv2025

Breaking Peierls theorem in polyacetylene chains via topological design

Peierls theorem postulates that a one-dimensional (1D) metallic chain must undergo a metal-to-insulator transition via lattice distortion, resulting in bond length alternation (BLA) within the chain. The validity of this theorem has been repeatedly proven in practice, as evidenced by the absence of a metallic phase in low-dimensional atomic lattices and electronic crystals, including conjugated polymers, artificial 1D quantum nanowires, and anisotropic inorganic crystals. Overcoming this transition enables realizing long-sought organic quantum phases of matter, including 1D synthetic organic metals and even high-temperature organic superconductors. Herein, we demonstrate that the Peierls transition can be globally suppressed by employing lattice topology engineering of classic trans-polyacetylene chains connected to open-shell nanographene terminals. The appropriate topology connection enables an effective interplay between the zero-energy modes (ZMs) of terminal and the finite odd-membered polyacetylene (OPA) chains. This creates a critical topology-defined highest occupied molecular orbital (HOMO) that compensates for bond density variations, thereby suppressing BLA and reestablishing their quasi-1D metallic character. Moreover, it also causes the formation of an unconventional boundary-free resonance state, being delocalized over the entire chain with non-decaying spectral weight, distinguishing them from traditional solitons observed in polyacetylene. Our finding sets the stage for pioneering the suppression of material instability and the creation of synthetic organic quantum materials with unconventional quantum phases previously prohibited by the Peierls transition.

cond-mat.mes-hall↗

arXiv2025

Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches typically learn from behavior-derived item-item associations using GNNs or leverage item content alone. However, these methods often overlook two key challenges: (i) user behaviors (e.g., co-view/co-purchase) only provide noisy weak supervision, and (ii) behavior signals are long-tailed, leaving many items with sparse associations. We propose MMSC, a self-supervised multi-modal relational representation learning framework that combines a multi-modal foundation model adapted to encode item metadata and a self-supervised denoising module that learns relationship-aware representations from noisy user behaviors, unified by a hierarchical aggregation mechanism. We further use LLM-assisted supervision to mitigate noise in behavior-derived supervision during training. Experiments on five real-world datasets show that MMSC consistently outperforms existing baselines by 26.1% for substitutable and 39.2% for complementary item inference, while remaining effective for cold-start items. We share our code for reproducibility.

cs.IR↗

arXiv2025

LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation

Zero-shot cross-domain sequential recommendation (ZCDSR) enables predictions in unseen domains without additional training or fine-tuning, addressing the limitations of traditional models in sparse data environments. Recent advancements in large language models (LLMs) have significantly enhanced ZCDSR by facilitating cross-domain knowledge transfer through rich, pretrained representations. Despite this progress, domain semantic bias -- arising from differences in vocabulary and content focus between domains -- remains a persistent challenge, leading to misaligned item embeddings and reduced generalization across domains. To address this, we propose a novel semantic bias-aware framework that enhances LLM-based ZCDSR by improving cross-domain alignment at both the item and sequential levels. At the item level, we introduce a generalization loss that aligns the embeddings of items across domains (inter-domain compactness), while preserving the unique characteristics of each item within its own domain (intra-domain diversity). This ensures that item embeddings can be transferred effectively between domains without collapsing into overly generic or uniform representations. At the sequential level, we develop a method to transfer user behavioral patterns by clustering source domain user sequences and applying attention-based aggregation during target domain inference. We dynamically adapt user embeddings to unseen domains, enabling effective zero-shot recommendations without requiring target-domain interactions...

cs.IR↗

arXiv2024

A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer

Sequential recommenders are crucial to the success of online applications, \eg e-commerce, video streaming, and social media. While model architectures continue to improve, for every new application domain, we still have to train a new model from scratch for high quality recommendations. On the other hand, pre-trained language and vision models have shown great success in zero-shot or few-shot adaptation to new application domains. Inspired by the success of pre-trained models in peer AI fields, we propose a novel pre-trained sequential recommendation framework: PrepRec. We learn universal item representations by modeling item popularity dynamics. Through extensive experiments on five real-world datasets, we show that PrepRec, without any auxiliary information, can not only zero-shot transfer to a new domain, but achieve competitive performance compared to state-of-the-art sequential recommender models with only a fraction of the model size. In addition, with a simple post-hoc interpolation, PrepRec can improve the performance of existing sequential recommenders on average by 13.8\% in Recall@10 and 29.5% in NDCG@10. We provide an anonymized implementation of PrepRec at https://anonymous.4open.science/r/PrepRec--2F60/

cs.IR↗

arXiv2023

Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning

Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feedforeward neural networks (FNN), among which the FNN shows better real-time performance while maintain the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is diffcult to be satisfied in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different traning tasks. By MTL, common features could be extracted, thus accelerating the learning process on given tasks, and reducing the demand for reference samples, so as to enhance the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 at the South China Sea. Results shows that MTL outperforms the state-of-the-art methods in terms of accuracy for SSP inversion, while inherits the real-time advantage of FNN during the inversion stage.

eess.AS↗

arXiv2023

Underwater Sound Speed Profile Construction: A Review

Real--time and accurate construction of regional sound speed profiles (SSP) is important for building underwater positioning, navigation, and timing (PNT) systems as it greatly affect the signal propagation modes such as trajectory. In this paper, we summarizes and analyzes the current research status in the field of underwater SSP construction, and the mainstream methods include direct SSP measurement and SSP inversion. In the direct measurement method, we compare the performance of popular international commercial temperature, conductivity, and depth profilers (CTD). While for the inversion methods, the framework and basic principles of matched field processing (MFP), compressive sensing (CS), and deep learning (DL) for constructing SSP are introduced, and their advantages and disadvantages are compared. The traditional direct measurement method has good accuracy performance, but it usually takes a long time. The proposal of SSP inversion method greatly improves the convenience and real--time performance, but the accuracy is not as good as the direct measurement method. Currently, the SSP inversion relies on sonar observation data, making it difficult to apply to areas that couldn't be covered by underwater observation systems, and these methods are unable to predict the distribution of sound velocity at future times. How to comprehensively utilize multi-source data and provide elastic sound velocity distribution estimation services with different accuracy and real-time requirements for underwater users without sonar observation data is the mainstream trend in future research on SSP construction.

eess.SP↗

arXiv2023

Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems

Modern neural collaborative filtering techniques are critical to the success of e-commerce, social media, and content-sharing platforms. However, despite technical advances -- for every new application domain, we need to train an NCF model from scratch. In contrast, pre-trained vision and language models are routinely applied to diverse applications directly (zero-shot) or with limited fine-tuning. Inspired by the impact of pre-trained models, we explore the possibility of pre-trained recommender models that support building recommender systems in new domains, with minimal or no retraining, without the use of any auxiliary user or item information. Zero-shot recommendation without auxiliary information is challenging because we cannot form associations between users and items across datasets when there are no overlapping users or items. Our fundamental insight is that the statistical characteristics of the user-item interaction matrix are universally available across different domains and datasets. Thus, we use the statistical characteristics of the user-item interaction matrix to identify dataset-independent representations for users and items. We show how to learn universal (i.e., supporting zero-shot adaptation without user or item auxiliary information) representations for nodes and edges from the bipartite user-item interaction graph. We learn representations by exploiting the statistical properties of the interaction data, including user and item marginals, and the size and density distributions of their clusters.

cs.IR↗

arXiv2020

Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10% accuracy) across six diverse, real-world datasets. We see stronger gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.

cs.SI↗

arXiv2019

An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms

This paper addresses the question of identifying the best candidate answer to a question on Community Question Answer (CQA) forums. The problem is important because Individuals often visit CQA forums to seek answers to nuanced questions. We develop a novel induced relational graph convolutional network (IR-GCN) framework to address the question. We make three contributions. First, we introduce a modular framework that separates the construction of the graph with the label selection mechanism. We use equivalence relations to induce a graph comprising cliques and identify two label assignment mechanisms---label contrast, label sharing. Then, we show how to encode these assignment mechanisms in GCNs. Second, we show that encoding contrast creates discriminative magnification---enhancing the separation between nodes in the embedding space. Third, we show a surprising result---boosting techniques improve learning over familiar stacking, fusion, or aggregation approaches for neural architectures. We show strong results over the state-of-the-art neural baselines in extensive experiments on 50 StackExchange communities.

cs.SI↗

arXiv2018

Atomically resolved probe-type scanning tunneling microscope for use in harsh vibrational cryogen-free superconducting magnet

We present a probe-type scanning tunneling microscope (STM) with atomic resolution that is designed to be directly inserted and work in a harsh vibrational cryogen-free superconducting magnet system. When a commercial variable temperature insert (VTI) is installed in the magnet and the STM is in turn housed in the VTI, a lowest temperature of 1.6 K can be achieved, where the STM still operates well. We have tested it in an 8 T superconducting magnet cooled with the pulse-tube cryocooler (PTC) and obtained atomically revolved graphite and NiSe2 images as well as the scanning tunneling spectrum (STS, i.e. dI/dV spectrum) data of the latter near its critical temperature, which show the formation process of the superconducting gap as a function of temperature. The drifting rates of the STM at 1.6 K in X-Y plane and Z direction are 1.15 and 1.71 pm/min respectively. Noise analysis for the tunneling current shows that the amplitudes of the dominant peaks (6.84 and 10.25Hz) are low. This is important as a cryogen-free magnet system has long been considered too harsh for any atomic resolution measurement.

physics.ins-det↗