arXiv subjects

Tianqi Wang

Publications and source records attributed to Tianqi Wang.

At least 19 recordsLinked to original sources

arXiv2026

B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven Methodology

In the one-time selling B2B context, the buying cycle may last months or even years. During the long process, targeting customers that have a high potential to make purchases and recommending personalized campaigns accordingly are important for effective marketing. For this goal, we study the following problems, B2B customer data aggregation, customer feature generation, and prediction of whether a B2B customer would show interest in making a purchase (i.e., prediction of conversion into sales funnel). We propose an algorithm to aggregate individual contacts to the B2B customer level based on multiple keys. For non-standardized keys such as company names, we propose a novel architecture to cluster them in a domain encompassing irregularities such as spelling mistakes and spelling variants. We then define and generate a set of features and apply the CatBoost model for customer conversion prediction. Our framework achieves 91\% prediction accuracy. Based on the prediction results and analysis of the model, we then discuss personalized campaign recommendations to foster conversion.

cs.LG↗

arXiv2026

Geometric finiteness in paracomplex hyperbolic spaces

We develop a framework for studying discrete subgroups of $\mathsf{PGL}(d+1,\mathbb{R})$ via the paracomplex hyperbolic space $\mathbb{H}_τ^d$, a rank-$1$ pseudo-Riemannian symmetric space. We characterize projective transverse, relatively Anosov, and Anosov subgroups in terms of properly discontinuous, geometrically finite, and convex-cocompact actions respectively on their weak hulls, which are canonical flow spaces in the spacelike unit tangent bundle of $\mathbb{H}_τ^d$. A key ingredient is the construction of a Busemann-type horofunction on the spacelike unit tangent bundle with the properties needed to describe cuspidal geometry. We further prove for relatively Anosov subgroups that the geodesic flows on their weak hulls are uniformly hyperbolic, giving a relative analogue of the Axiom A property.

math.DG↗

arXiv2026

Human-Centric Intelligence in the Era of Foundation Models: A Survey

Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear. To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency. We next present the methodological foundations of the field, covering human-centric data families, computational architecture paradigms, and representative training and inference optimization strategies. We then systematically review representative methods across these levels and organize the associated datasets, benchmarks, and evaluation metrics. We further discuss open challenges and promising research directions toward human-centric intelligence that is scalable, trustworthy, physically grounded, and deployable, aiming to provide a coherent framework and practical reference for advancing the field. Finally, we provide a systematically organized and continuously updated collection of human-centric AI literature and resources on our project page.

cs.CV↗

arXiv2026

Regularity of Manhattan manifolds and exact dimensionality for relatively Anosov groups

We establish several results about Patterson--Sullivan measures for relatively Anosov groups. First, we prove that these measures are exact dimensional with respect to visual metrics induced by Gromov models in the Groves--Manning quasi-isometry class. Under the additional assumption that the group is relatively Morse, we show that the associated scalar Cartan metric is Gromov hyperbolic and that the corresponding boundary premetric is a visual metric to which the exact-dimensionality theorem applies. Second, we prove that their Manhattan manifolds are $C^1$-regular, from which we deduce that the growth indicator is $C^1$-regular and strictly concave on the interior of the limit cone. This extends the case of Anosov representations by Kim--Oh--Wang. Our methods are dynamical, and we exploit the fact due to Kim--Oh and Blayac--Canary--Zhu--Zimmer that Bowen--Margulis--Sullivan measures for relatively Anosov groups are finite and mixing.

math.GR↗

arXiv2026

Positive representations over real closed fields

We develop the theory of $Θ$-positive representations from general Fuchsian groups to linear groups over real closed fields. Our definition, which does not assume the boundary map to be continuous, encompasses many generalizations of positive or Anosov representations that have been considered in the literature.

math.GT↗

arXiv2026

GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning

Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Language-Image Pre-trained (CLIP) models have shown strong potential for CIL due to their powerful generalization ability. However, existing methods still face two key challenges: shared-parameter adaptation tends to cause old-knowledge drift, and task-specific knowledge organization often leads to poorly calibrated cross-task responses, making reliable routing difficult. To address these issues, we propose GR4CIL, a framework combining task discrimination and knowledge routing for CLIP-based CIL. GR4CIL preserves task-specific visual knowledge while maintaining an incrementally stable shared textual semantic space, thereby reducing interference across tasks. Moreover, we introduce an orthogonal compensation mechanism to mitigate modality-gap-induced bias, enhance within-task discrimination, and enlarge the score margin between the ground-truth task and competing tasks. As a result, GR4CIL enables more reliable task-aware routing over learned knowledge while retaining the zero-shot generalization capability. Experiments on multiple benchmarks show that GR4CIL consistently outperforms strong baselines.

cs.CV↗

arXiv2026

Notions of Anosov representation of relatively hyperbolic groups

We prove that divergent, extended geometrically finite (in the sense of Weisman arXiv:2205.07183) representations can be interpreted as restricted Anosov (in the sense of Tholozan--Wang arXiv:2307.02934) representations over certain flow spaces. We also show that the representations of this type are stable under small type preserving deformations. As an example, we show that a representation induced from a geometrically finite one through a Galois covering, constructed in Tholozan--Wang arXiv:2307.02934, is divergent and extended geometrically finite with a non-homeomorphic boundary extension.

math.GT↗

arXiv2026

Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT

Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. However, recovering reliable image content and visually consistent textures is still a crucial challenge. In this paper, we present a Progressively Texture-aware Diffusion (PTD) model, a coarse-to-fine learning framework tailored for SVCT. Specifically, PTD comprises a basic reconstructive module PTD$_{\textit{rec}}$ and a conditional diffusion module PTD$_{\textit{diff}}$. PTD$_{\textit{rec}}$ first learns a deterministic mapping to recover the majority of the underlying low-frequency signals (i.e., coarse content with smoothed textures), which serves as the initial estimation to enable fidelity. Moreover, PTD$_{\textit{diff}}$ aims to reconstruct high-fidelity details for coarse prediction, which explores a dual-domain guided conditional diffusion to generate reliable and consistent textures. Extensive experiments on sparse-view CT reconstruction demonstrate that our PTD achieves superior performance in terms of structure similarity and visual appeal with only a few sampling steps, which mitigates the randomness inherent in general diffusion models and enables a better trade-off between visual quality and fidelity of high-frequency details.

cs.CV↗

arXiv2026

The Art of Midwifery in LLMs: Optimizing Role Personas for Large Language Models as Moral Assistants

With the development of Large Language Models (LLMs) in consulting, their role in moral decision-making has become prominent. However, existing research predominantly consider AI as an independent "moral agent" adhering to the "Human-AI Alignment" paradigm. In this study, we propose that AI should serve as a "moral assistant", facilitating users' moral growth through the "Art of Midwifery" rather than substituting human judgment. We endow LLMs with distinct persona archetypes and conducted dialogues across six moral scenarios. Findings reveal that while the virtue exemplar excelled overall, optimal performance was context-dependent: the Guardian Angel excelled in bioethical crises for emotional support, whereas the Socratic persona better elicited reflection in existential dilemmas. We introduce "Constructive Divergence", arguing that AI should offer alternative perspectives at critical moment rather than blindly accommodate users, transcending traditional alignment paradigms.

cs.SI↗

arXiv2026

Assessing the livability within the 15-minute city concept based on mobile phone data

Many cities promote walkability through concepts such as the compact city and 15-minute city to enhance urban livability, yet few methods link spatial walkability features to empirically measured livability and account for temporal dynamics. The method developed for this study uses mobile phone data from the Helsinki Metropolitan Area (Finland) to assess whether commonly used, literature-derived livability indicators (diversity, density, proximity, accessibility) predict observed human activity patterns across different times of day. We constructed two key dimensions of livability: attractiveness and walkability with quantifiable sub-indicators that were selected based on literature. Our analysis shows that walkability, and even more so the combined livability index, correlates with activity patterns, outperforming the pure attractiveness perspective. However, this relationship is temporally unstable, significantly weakening at night and fluctuating daily. Moreover, based on Geographically Weighted Regression analysis, our results reveal significant spatial variation in the relationship between livability and the intensity of human activities. The findings suggest that traditional urban planning goals, such as functional diversity to enhance walkability, contribute to livability but have a limited impact on the 15-minute city's overall sustainable mobility objectives, necessitating a larger-scale perspective and more functionally profiled approaches for urban development.

physics.soc-ph↗

arXiv2026

Cooperative concurrence of 4f and 3d flat bands in kagome heavy-fermion metal YbCr6Ge6

Flat-band (FB) systems originating from special lattice geometry like in kagome metals as well as localized orbitals in the materials such as heavy-fermion (HF) compounds have induced intensive interest due to their band topology and strong electron correlation effects, leading to emergent quantum states of matter. However, the question of how these two distinct FBs coexist and interact remains unsettled. Here, we report that YbCr6Ge6 hosting both Cr-kagome lattice and Yb-4f electrons exhibits HF behaviors and a robust antiferromagnetic ground state with transition temperature TN = 3 K, significantly higher than other similar kagome metals with Yb ions. Angle-resolved photoemission spectroscopy measurements reveal the coexistence of FBs originating from both Cr-kagome lattice and localized Yb-4f electrons near Fermi energy level EF. More importantly, the clear spectroscopic signatures of a hybridization of Yb-4f FB with kagome-lattice-derived conduction bands and the high density of states of Cr-kagome FB near EF provide the underlying microscopic mechanisms of HF behaviors and enhanced antiferromagnetism in YbCr6Ge6. Our findings demonstrate that the novel kagome HF metals can not only host the cooperative coexistence of two different types of FBs, but also provide a paradigm material platform to explore the exotic correlated topological quantum phenomena.

cond-mat.str-el↗

arXiv2025

Coexistence of near-EF van Hove singularity and in-gap topological Dirac surface states in superconducting electrides

Superconducting electrides have attracted growing attention for their potential to achieve high superconducting transition temperatures (TC) under pressure. However, many known electrides are chemically reactive and unstable, making high-quality single-crystal growth, characterization, and measurements difficult, and most do not exhibit superconductivity at ambient pressure. In contrast, La3In stands out for its ambient-pressure superconductivity (TC ~ 9.4 K) and the availability of high-quality single crystals. Here, we investigate its low-energy electronic structure using angle-resolved photoemission spectroscopy and first-principles calculations. The bands near the Fermi energy are mainly derived from La 5d and In 5p orbitals. A saddle point is directly observed at the Brillouin zone (BZ) boundary, while a three-dimensional van Hove singularity crosses EF at the BZ corner. First-principles calculations further reveal topological Dirac surface states within the bulk energy gap above EF. The coexistence of a high density of states and in-gap topological surface states near EF suggests that La3In offers a promising platform for tuning superconductivity and exploring possible topological superconducting phases through doping or external pressure.

cond-mat.supr-con↗

arXiv2025

Element2Vec: Build Chemical Element Representation from Text for Property Prediction

Accurate property data for chemical elements is crucial for materials design and manufacturing, but many of them are difficult to measure directly due to equipment constraints. While traditional methods use the properties of other elements or related properties for prediction via numerical analyses, they often fail to model complex relationships. After all, not all characteristics can be represented as scalars. Recent efforts have been made to explore advanced AI tools such as language models for property estimation, but they still suffer from hallucinations and a lack of interpretability. In this paper, we investigate Element2Vecto effectively represent chemical elements from natural languages to support research in the natural sciences. Given the text parsed from Wikipedia pages, we use language models to generate both a single general-purpose embedding (Global) and a set of attribute-highlighted vectors (Local). Despite the complicated relationship across elements, the computational challenges also exist because of 1) the discrepancy in text distribution between common descriptions and specialized scientific texts, and 2) the extremely limited data, i.e., with only 118 known elements, data for specific properties is often highly sparse and incomplete. Thus, we also design a test-time training method based on self-attention to mitigate the prediction error caused by Vanilla regression clearly. We hope this work could pave the way for advancing AI-driven discovery in materials science.

cs.CL↗

arXiv2025

Field-free superconducting diode effect of NbSe2 induced by strain

Superconducting diodes, similar to semiconductor diodes, possess unidirectional superconducting properties and are the fundamental units for constructing superconducting quantum computing, thus attracting widespread attention. At present, most of superconducting diodes require an external magnetic field or proximity effect to break time reversal symmetry (TRS). The cases of intrinsic superconducting diode effect (SDE) under zero magnetic field are relatively scarce, and there are still some puzzles especially regarding the reasons for the TRS breaking. Here, we not only report field free SDE in NbSe2 induced by strain, but also large values of the difference of Ic+ and |Ic-| (ΔIc) of 286 μA and the superconducting diode efficiency (η) of 6.76 % are achieved. Interestingly, ΔIc varies with the magnetic field and exhibits two distinct evolutionary behaviors with B-odd or B-even symmetry in various devices. We attribute this to the selective activation of two independent, spatially-orthogonal mechanisms: a stress-induced real-space polarity and a field-induced reciprocal-space asymmetric energy bands. In general, we propose an extremely effectively method to produce field free SDE, even when the material itself does not possess field free SDE, and provide new perspectives to understand the SDE which build new avenues for superconducting quantum devices.

cond-mat.mtrl-sci↗

arXiv2025

FPI-Det: a face--phone Interaction Dataset for phone-use detection and understanding

The widespread use of mobile devices has created new challenges for vision systems in safety monitoring, workplace productivity assessment, and attention management. Detecting whether a person is using a phone requires not only object recognition but also an understanding of behavioral context, which involves reasoning about the relationship between faces, hands, and devices under diverse conditions. Existing generic benchmarks do not fully capture such fine-grained human--device interactions. To address this gap, we introduce the FPI-Det, containing 22{,}879 images with synchronized annotations for faces and phones across workplace, education, transportation, and public scenarios. The dataset features extreme scale variation, frequent occlusions, and varied capture conditions. We evaluate representative YOLO and DETR detectors, providing baseline results and an analysis of performance across object sizes, occlusion levels, and environments. Source code and dataset is available at https://github.com/KvCgRv/FPI-Det.

cs.CV↗

arXiv2025

Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consistency prior for 3D generation. On the other hand, the rich semantic information contained within the videos enables the generated content to be more faithful to the text prompts and semantically plausible. This paper explores how to apply the video modality in 3D asset generation, spanning datasets to models. We introduce Droplet3D-4M, the first large-scale video dataset with multi-view level annotations, and train Droplet3D, a generative model supporting both image and dense text input. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to produce spatially consistent and semantically plausible content. Moreover, in contrast to the prevailing 3D solutions, our approach exhibits the potential for extension to scene-level applications. This indicates that the commonsense priors from the videos significantly facilitate 3D creation. We have open-sourced all resources including the dataset, code, technical framework, and model weights: https://dropletx.github.io/.

cs.CV↗

arXiv2025

Synthesis of intrinsic magnetic topological insulator MnBi2nTe3n+1 family by chemical vapor transport method with feedback regulation

MnBi2nTe3n+1 (MBT) is a representative family of intrinsic magnetic topological insulators, in which numerous exotic phenomena such as the quantum anomalous Hall effect are expected. The high-quality crystal growth and magnetism manipulation are the most essential processes. Here we develop a modified chemical vapor transport method using a feedback-regulated strategy, which provides the closed-loop control of growth temperature within +/- 0.1 degree Celsius. Single crystals of MnBi2Te4, MnBi4Te7, and MnBi6Te10 are obtained under different temperature intervals respectively, and show variable tunability on magnetism by finely tuning the growth temperatures. Specifically, the cold-end temperatures not only vary the strength of antiferromagnetic coupling in MnBi2Te4, but also induce magnetic ground state transitions from antiferromagnetism to ferromagnetism in MnBi4Te7 and MnBi6Te10. In MnBi2Te4 with optimized magnetism, quantized transport with Chern insulator state is also realized at the low field of 3.7 T. Our results provide a systematic picture for the crystal growth and the rich magnetic tunability of MBT family, providing richer platforms for the related researches combining magnetism and topological physics.

cond-mat.mtrl-sci↗

arXiv2025

A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning

Vision foundation models in remote sensing have been extensively studied due to their superior generalization on various downstream tasks. Synthetic Aperture Radar (SAR) offers all-day, all-weather imaging capabilities, providing significant advantages for Earth observation. However, establishing a foundation model for SAR image interpretation inevitably encounters the challenges of insufficient information utilization and poor interpretability. In this paper, we propose a remote sensing foundation model based on complex-valued SAR data, which simulates the polarimetric decomposition process for pre-training, i.e., characterizing pixel scattering intensity as a weighted combination of scattering bases and scattering coefficients, thereby endowing the foundation model with physical interpretability. Specifically, we construct a series of scattering queries, each representing an independent and meaningful scattering basis, which interact with SAR features in the scattering query decoder and output the corresponding scattering coefficient. To guide the pre-training process, polarimetric decomposition loss and power self-supervision loss are constructed. The former aligns the predicted coefficients with Yamaguchi coefficients, while the latter reconstructs power from the predicted coefficients and compares it to the input image's power. The performance of our foundation model is validated on six typical downstream tasks, achieving state-of-the-art results. Notably, the foundation model can extract stable feature representations and exhibits strong generalization, even in data-scarce conditions.

cs.CV↗