Searcharxiv⌕ Search

arXiv subjects

Tianqi Wang

Publications and source records attributed to Tianqi Wang.

At least 37 records · Page 2Linked to original sources
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↗
arXiv2025

Joint ML-Bayesian Approach to Adaptive Radar Detection in the presence of Gaussian Interference

This paper addresses the adaptive radar target detection problem in the presence of Gaussian interference with unknown statistical properties. To this end, the problem is first formulated as a binary hypothesis test, and then we derive a detection architecture grounded on the hybrid of Maximum Likelihood (ML) and Maximum A Posterior (MAP) approach. Specifically, we resort to the hidden discrete latent variables in conjunction with the Expectation-Maximization (EM) algorithms which cyclically updates the estimates of the unknowns. In this framework, the estimates of the a posteriori probabilities under each hypothesis are representative of the inherent nature of data and used to decide for the presence of a potential target. In addition, we prove that the developed detection scheme ensures the desired Constant False Alarm Rate property with respect to the unknown interference covariance matrix. Numerical examples obtained through synthetic and real recorded data corroborate the effectiveness of the proposed architecture and show that the MAP-based approach ensures evident improvement with respect to the conventional generalized likelihood ratio test at least for the considered scenarios and parameter setting.

eess.SP↗
arXiv2025

"An Image of Ourselves in Our Minds": How College-educated Online Dating Users Construct Profiles for Effective Self Presentation

Online dating is frequently used by individuals looking for potential relationships and intimate connections. Central to dating apps is the creation and refinement of a dating profile, which represents the way individuals desire to present themselves to potential mates, while hiding information they do not care to share. To investigate the way frequent users of dating apps construct their online profiles and perceive the effectiveness of strategies taken in making profiles, we conducted semi-structured interviews with 20 experienced users who are Chinese college-educated young adults and uncovered the processes and rationales by which they make profiles for online dating, particularly in selecting images for inclusion. We found that participants used idealized photos that exaggerated their positive personality traits, sometimes traits that they do not possess but perceive others to desire, and sometimes even traits they wish they had possessed. Users also strategically used photos that show personality and habits without showing themselves, and often hid certain identifying information to reduce privacy risks. This analysis signals potential factors that are key in building online dating profiles, providing design implications for systems that limit the use of inaccurate information while still promoting self-expression in relationship platforms.

cs.HC↗
arXiv2025

On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class exemplars. An emerging theory-guided framework for CIL trains task-specific models for a shared network, shifting the pressure of forgetting to task-id prediction. In EF-CIL, task-id prediction is more challenging due to the lack of inter-task interaction (e.g., replays of exemplars). To address this issue, we conduct a theoretical analysis of the importance and feasibility of preserving a discriminative and consistent feature space, upon which we propose a novel method termed DCNet. Concretely, it progressively maps class representations into a hyperspherical space, in which different classes are orthogonally distributed to achieve ample inter-class separation. Meanwhile, it also introduces compensatory training to adaptively adjust supervision intensity, thereby aligning the degree of intra-class aggregation. Extensive experiments and theoretical analysis verified the superiority of the proposed DCNet.

cs.CV↗
arXiv2024

"I Recall the Past": Exploring How People Collaborate with Generative AI to Create Cultural Heritage Narratives

Visitors to cultural heritage sites often encounter official information, while local people's unofficial stories remain invisible. To explore expression of local narratives, we conducted a workshop with 20 participants utilizing Generative AI (GenAI) to support visual narratives, asking them to use Stable Diffusion to create images of familiar cultural heritage sites, as well as images of unfamiliar ones for comparison. The results revealed three narrative strategies and highlighted GenAI's strengths in illuminating, amplifying, and reinterpreting personal narratives. However, GenAI showed limitations in meeting detailed requirements, portraying cultural features, and avoiding bias, which were particularly pronounced with unfamiliar sites due to participants' lack of local knowledge. To address these challenges, we recommend providing detailed explanations, prompt engineering, and fine-tuning AI models to reduce uncertainties, using objective references to mitigate inaccuracies from participants' inability to recognize errors or misconceptions, and curating datasets to train AI models capable of accurately portraying cultural features.

cs.HC↗
arXiv2024

Theseus: Exploring Efficient Wafer-Scale Chip Design for Large Language Models

The emergence of the large language model~(LLM) poses an exponential growth of demand for computation throughput, memory capacity, and communication bandwidth. Such a demand growth has significantly surpassed the improvement of corresponding chip designs. With the advancement of fabrication and integration technologies, designers have been developing Wafer-Scale Chips~(WSCs) to scale up and exploit the limits of computation density, memory capacity, and communication bandwidth at the level of a single chip. Existing solutions have demonstrated the significant advantages of WSCs over traditional designs, showing potential to effectively support LLM workloads. Despite the benefits, exploring the early-stage design space of WSCs for LLMs is a crucial yet challenging task due to the enormous and complicated design space, time-consuming evaluation methods, and inefficient exploration strategies. To address these challenges, we propose Theseus, an efficient WSC design space exploration framework for LLMs. We construct the design space of WSCs with various constraints considering the unique characteristics of WSCs. We propose efficient evaluation methodologies for large-scale NoC-based WSCs and introduce multi-fidelity Bayesian optimization to efficiently explore the design space. Evaluation results demonstrate the efficiency of Theseus that the searched Pareto optimal results outperform GPU cluster and existing WSC designs by up to 62.8\%/73.7\% in performance and 38.6\%/42.4\% in power consumption for LLM training, while improving up to 23.2$\times$ and 15.7$\times$ for the performance and power of inference tasks. Furthermore, we conduct case studies to address the design tradeoffs in WSCs and provide insights to facilitate WSC designs for LLMs.

cs.AR↗
arXiv2024

Gromov hyperbolicity of intrinsic metrics from isoperimetric inequalities

In this paper we investigate the Gromov hyperbolicity of the classical Kobayashi and Hilbert metrics, and the recently introduced minimal metric. Using the linear isoperimetric inequality characterization of Gromov hyperbolicity, we show if these metrics have an "expanding property" near the boundary, then they are Gromov hyperbolic. This provides a new characterization of the convex domains whose Hilbert metric is Gromov hyperbolic, a new proof of Balogh-Bonk's result that the Kobayashi metric is Gromov hyperbolic on a strongly pseudoconvex domain, a new proof of the second author's result that the Kobayashi metric is Gromov hyperbolic on a convex domain with finite type, and a new proof of Fiacchi's result that the minimal metric is Gromov hyperbolic on a strongly minimally convex domain. We also characterize the smoothly bounded convex domains where the minimal metric is Gromov hyperbolic.

math.DG↗
arXiv2024

KAN based Autoencoders for Factor Models

Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we introduce a novel approach to latent factor conditional asset pricing models. While previous machine learning applications in asset pricing have predominantly used Multilayer Perceptrons with ReLU activation functions to model latent factor exposures, our method introduces a KAN-based autoencoder which surpasses MLP models in both accuracy and interpretability. Our model offers enhanced flexibility in approximating exposures as nonlinear functions of asset characteristics, while simultaneously providing users with an intuitive framework for interpreting latent factors. Empirical backtesting demonstrates our model's superior ability to explain cross-sectional risk exposures. Moreover, long-short portfolios constructed using our model's predictions achieve higher Sharpe ratios, highlighting its practical value in investment management.

cs.LG↗
arXiv2024

Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning

Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new classes. At inference time, it automatically reactivates the required neural units to retrieve knowledge and leaves the remaining inactivated to prevent interference. We name our model AutoActivator, which is effective and scalable. To gain insights into the neural unit dynamics, we theoretically analyze the model's convergence property via a universal approximation theorem on learning sequential mappings, which is under-explored in the CIL community. Experiments show that our method achieves strong CIL performance in rehearsal-free and minimal-expansion settings with different backbones.

cs.LG↗
arXiv2024

DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving

End-to-end driving has made significant progress in recent years, demonstrating benefits such as system simplicity and competitive driving performance under both open-loop and closed-loop settings. Nevertheless, the lack of interpretability and controllability in its driving decisions hinders real-world deployment for end-to-end driving systems. In this paper, we collect a comprehensive end-to-end driving dataset named DriveCoT, leveraging the CARLA simulator. It contains sensor data, control decisions, and chain-of-thought labels to indicate the reasoning process. We utilize the challenging driving scenarios from the CARLA leaderboard 2.0, which involve high-speed driving and lane-changing, and propose a rule-based expert policy to control the vehicle and generate ground truth labels for its reasoning process across different driving aspects and the final decisions. This dataset can serve as an open-loop end-to-end driving benchmark, enabling the evaluation of accuracy in various chain-of-thought aspects and the final decision. In addition, we propose a baseline model called DriveCoT-Agent, trained on our dataset, to generate chain-of-thought predictions and final decisions. The trained model exhibits strong performance in both open-loop and closed-loop evaluations, demonstrating the effectiveness of our proposed dataset.

cs.CV↗
arXiv2024

LiMAML: Personalization of Deep Recommender Models via Meta Learning

In the realm of recommender systems, the ubiquitous adoption of deep neural networks has emerged as a dominant paradigm for modeling diverse business objectives. As user bases continue to expand, the necessity of personalization and frequent model updates have assumed paramount significance to ensure the delivery of relevant and refreshed experiences to a diverse array of members. In this work, we introduce an innovative meta-learning solution tailored to the personalization of models for individual members and other entities, coupled with the frequent updates based on the latest user interaction signals. Specifically, we leverage the Model-Agnostic Meta Learning (MAML) algorithm to adapt per-task sub-networks using recent user interaction data. Given the near infeasibility of productionizing original MAML-based models in online recommendation systems, we propose an efficient strategy to operationalize meta-learned sub-networks in production, which involves transforming them into fixed-sized vectors, termed meta embeddings, thereby enabling the seamless deployment of models with hundreds of billions of parameters for online serving. Through extensive experimentation on production data drawn from various applications at LinkedIn, we demonstrate that the proposed solution consistently outperforms the baseline models of those applications, including strong baselines such as using wide-and-deep ID based personalization approach. Our approach has enabled the deployment of a range of highly personalized AI models across diverse LinkedIn applications, leading to substantial improvements in business metrics as well as refreshed experience for our members.

cs.IR↗
arXiv2024

Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and network expansion for balancing model stability and plasticity, which, however, compromises their practical value due to privacy and memory concerns. Instead, this paper considers a strict yet realistic setting, where the training data from previous tasks is unavailable and the model size remains relatively constant during sequential training. To achieve such desiderata, we propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. This is achieved by the synergy between two key components: HSIC-Bottleneck Orthogonalization (HBO) implements non-overwritten parameter updates mediated by Hilbert-Schmidt independence criterion in an orthogonal space and EquiAngular Embedding (EAE) enhances decision boundary adaptation between old and new tasks with predefined basis vectors. Extensive experiments demonstrate that our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.

cs.LG↗
arXiv2023

AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model

Traffic accidents, being a significant contributor to both human casualties and property damage, have long been a focal point of research for many scholars in the field of traffic safety. However, previous studies, whether focusing on static environmental assessments or dynamic driving analyses, as well as pre-accident predictions or post-accident rule analyses, have typically been conducted in isolation. There has been a lack of an effective framework for developing a comprehensive understanding and application of traffic safety. To address this gap, this paper introduces AccidentGPT, a comprehensive accident analysis and prevention multi-modal large model. AccidentGPT establishes a multi-modal information interaction framework grounded in multi-sensor perception, thereby enabling a holistic approach to accident analysis and prevention in the field of traffic safety. Specifically, our capabilities can be categorized as follows: for autonomous driving vehicles, we provide comprehensive environmental perception and understanding to control the vehicle and avoid collisions. For human-driven vehicles, we offer proactive long-range safety warnings and blind-spot alerts while also providing safety driving recommendations and behavioral norms through human-machine dialogue and interaction. Additionally, for traffic police and management agencies, our framework supports intelligent and real-time analysis of traffic safety, encompassing pedestrian, vehicles, roads, and the environment through collaborative perception from multiple vehicles and road testing devices. The system is also capable of providing a thorough analysis of accident causes and liability after vehicle collisions. Our framework stands as the first large model to integrate comprehensive scene understanding into traffic safety studies. Project page: https://accidentgpt.github.io

cs.CE↗
arXiv2023

DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving

Safety is the primary priority of autonomous driving. Nevertheless, no published dataset currently supports the direct and explainable safety evaluation for autonomous driving. In this work, we propose DeepAccident, a large-scale dataset generated via a realistic simulator containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset with 40k annotated samples. In addition, we propose a new task, end-to-end motion and accident prediction, which can be used to directly evaluate the accident prediction ability for different autonomous driving algorithms. Furthermore, for each scenario, we set four vehicles along with one infrastructure to record data, thus providing diverse viewpoints for accident scenarios and enabling V2X (vehicle-to-everything) research on perception and prediction tasks. Finally, we present a baseline V2X model named V2XFormer that demonstrates superior performance for motion and accident prediction and 3D object detection compared to the single-vehicle model.

cs.CV↗
arXiv2023

Multi-View Class Incremental Learning

Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views, requiring no access to earlier views of data. However, MVCIL is challenged by the catastrophic forgetting of old information and the interference with learning new concepts. To address this, we first develop a randomization-based representation learning technique serving for feature extraction to guarantee their separate view-optimal working states, during which multiple views belonging to a class are presented sequentially; Then, we integrate them one by one in the orthogonality fusion subspace spanned by the extracted features; Finally, we introduce selective weight consolidation for learning-without-forgetting decision-making while encountering new classes. Extensive experiments on synthetic and real-world datasets validate the effectiveness of our approach.

cs.LG↗
arXiv2023

Magnetic kagome materials RETi3Bi4 family with weak interlayer interactions

Kagome materials have attracted a surge of research interest recently, especially for the ones combining with magnetism, and the ones with weak interlayer interactions which can fabricate thin devices. However, kagome materials combining both characters of magnetism and weak interlayer interactions are rare. Here we investigate a new family of titanium based kagome materials RETi3Bi4 (RE = Eu, Gd and Sm). The flakes of nanometer thickness of RETi3Bi4 can be obtained by exfoliation due to the weak interlayer interactions. According to magnetic measurements, out-of-plane ferromagnetism, out-of-plane anti-ferromagnetism, and in-plane ferromagnetism are formed for RE = Eu, Gd, and Sm respectively. The magnetic orders are simple and the saturation magnetizations can be relatively large since the rare earth elements solely provide the magnetic moments. Further by angle-resolved photoemission spectroscopy (ARPES) and first-principles calculations, the electronic structures of RETi3Bi4 are investigated. The ARPES results are consistent with the calculations, indicating the bands characteristic with kagome sublattice in RETi3Bi4. We expect these materials to be promising candidates for observation of the exotic magnetic topological phases and the related topological quantum transport studies.

cond-mat.mtrl-sci↗
arXiv2023

Simple Anosov representations of closed surface groups

We introduce and study \emph{simple Anosov representations} of closed hyperbolic surface groups, analogous to Minsky's \emph{primitive stable representations} of free groups. We prove that the set of simple Anosov representations into $\mathrm{SL}(d,\mathbb{C})$ with $d \geqslant 4$ strictly contains the set of Anosov representations. As a consequence, we construct domains of discontinuity for the mapping class group action on character varieties which contain non-discrete representations.

math.GT↗