arXiv subjects

Xin Tong

Publications and source records attributed to Xin Tong.

At least 55 records · Page 3Linked to original sources

arXiv2026

A Burden Shared is a Burden Halved: A Fairness-Adjusted Approach to Classification

We investigate the fairness issue in classification, where automated decisions are made for individuals from different protected groups. In high-consequence scenarios, decision errors can disproportionately affect certain protected groups, leading to unfair outcomes. To address this issue, we propose a fairness-adjusted selective inference (FASI) framework and develop data-driven algorithms that achieve statistical parity by controlling the false selection rate (FSR) among protected groups. Our FASI algorithm operates by converting the outputs of black-box classifiers into R-values, which are both intuitive and computationally efficient. These R-values serve as the basis for selection rules that are provably valid for FSR control in finite samples for protected groups, effectively mitigating the unfairness in group-wise error rates. We demonstrate the numerical performance of our approach using both simulated and real data.

stat.ME↗

arXiv2026

ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting

Most current audio-driven facial animation research primarily focuses on generating videos with neutral emotions. While some studies have addressed the generation of facial videos driven by emotional audio, efficiently generating high-quality talking head videos that integrate both emotional expressions and style features remains a significant challenge. In this paper, we propose ESGaussianFace, an innovative framework for emotional and stylized audio-driven facial animation. Our approach leverages 3D Gaussian Splatting to reconstruct 3D scenes and render videos, ensuring efficient generation of 3D consistent results. We propose an emotion-audio-guided spatial attention method that effectively integrates emotion features with audio content features. Through emotion-guided attention, the model is able to reconstruct facial details across different emotional states more accurately. To achieve emotional and stylized deformations of the 3D Gaussian points through emotion and style features, we introduce two 3D Gaussian deformation predictors. Futhermore, we propose a multi-stage training strategy, enabling the step-by-step learning of the character's lip movements, emotional variations, and style features. Our generated results exhibit high efficiency, high quality, and 3D consistency. Extensive experimental results demonstrate that our method outperforms existing state-of-the-art techniques in terms of lip movement accuracy, expression variation, and style feature expressiveness.

cs.CV↗

arXiv2025

Meson properties and symmetry emergence based on the deep neural network

As a key property of hadrons, the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions. In this work, a deep neural network model with the Transformer architecture is built to precisely predict meson widths in the range of $10^{-14} \sim 625$ MeV based on meson quantum numbers and masses. The relative errors of the predictions are $0.12\%, 2.0\%,$ and $0.54\%$ in the training set, the test set, and all the data, respectively. We present the predicted meson width spectra for the currently discovered states and some theoretically predicted ones. The model is also used as a probe to study the quantum numbers and inner structures for some undetermined states including the exotic states. Notably, this data-driven model is investigated to spontaneously exhibit good charge conjugation symmetry and approximate isospin symmetry consistent with physical principles. The results indicate that the deep neural network can serve as an independent complementary research paradigm to describe and explore the hadron structures and the complicated interactions in particle physics alongside the traditional experimental measurements, theoretical calculations, and lattice simulations.

hep-ph↗

arXiv2025

Degree-Weighted Social Learning

We study social learning in which agents weight neighbors' opinions differently based on their degrees, capturing situations in which agents place more trust in well-connected individuals or, conversely, discount their influence. We derive asymptotic properties of learning outcomes in large stochastic networks and analyze how the weighting rule affects societal wisdom and convergence speed. We find that assigning greater weight to higher-degree neighbors harms wisdom but has a non-monotonic effect on convergence speed, depending on the diversity of views within high- and low-degree groups, highlighting a potential trade-off between convergence speed and wisdom.

econ.TH↗

arXiv2025

Multi-Head Spectral-Adaptive Graph Anomaly Detection

Graph anomaly detection technology has broad applications in financial fraud and risk control. However, existing graph anomaly detection methods often face significant challenges when dealing with complex and variable abnormal patterns, as anomalous nodes are often disguised and mixed with normal nodes, leading to the coexistence of homophily and heterophily in the graph domain. Recent spectral graph neural networks have made notable progress in addressing this issue; however, current techniques typically employ fixed, globally shared filters. This 'one-size-fits-all' approach can easily cause over-smoothing, erasing critical high-frequency signals needed for fraud detection, and lacks adaptive capabilities for different graph instances. To solve this problem, we propose a Multi-Head Spectral-Adaptive Graph Neural Network (MHSA-GNN). The core innovation is the design of a lightweight hypernetwork that, conditioned on a 'spectral fingerprint' containing structural statistics and Rayleigh quotient features, dynamically generates Chebyshev filter parameters tailored to each instance. This enables a customized filtering strategy for each node and its local subgraph. Additionally, to prevent mode collapse in the multi-head mechanism, we introduce a novel dual regularization strategy that combines teacher-student contrastive learning (TSC) to ensure representation accuracy and Barlow Twins diversity loss (BTD) to enforce orthogonality among heads. Extensive experiments on four real-world datasets demonstrate that our method effectively preserves high-frequency abnormal signals and significantly outperforms existing state-of-the-art methods, especially showing excellent robustness on highly heterogeneous datasets.

cs.LG↗

arXiv2025

AInsteinBench: Benchmarking Coding Agents on Scientific Repositories

We introduce AInsteinBench, a large-scale benchmark for evaluating whether large language model (LLM) agents can operate as scientific computing development agents within real research software ecosystems. Unlike existing scientific reasoning benchmarks which focus on conceptual knowledge, or software engineering benchmarks that emphasize generic feature implementation and issue resolving, AInsteinBench evaluates models in end-to-end scientific development settings grounded in production-grade scientific repositories. The benchmark consists of tasks derived from maintainer-authored pull requests across six widely used scientific codebases, spanning quantum chemistry, quantum computing, molecular dynamics, numerical relativity, fluid dynamics, and cheminformatics. All benchmark tasks are carefully curated through multi-stage filtering and expert review to ensure scientific challenge, adequate test coverage, and well-calibrated difficulty. By leveraging evaluation in executable environments, scientifically meaningful failure modes, and test-driven verification, AInsteinBench measures a model's ability to move beyond surface-level code generation toward the core competencies required for computational scientific research.

cs.SE↗

arXiv2025

RecGPT-V2 Technical Report

Large language models (LLMs) have demonstrated remarkable potential in transforming recommender systems from implicit behavioral pattern matching to explicit intent reasoning. While RecGPT-V1 successfully pioneered this paradigm by integrating LLM-based reasoning into user interest mining and item tag prediction, it suffers from four fundamental limitations: (1) computational inefficiency and cognitive redundancy across multiple reasoning routes; (2) insufficient explanation diversity in fixed-template generation; (3) limited generalization under supervised learning paradigms; and (4) simplistic outcome-focused evaluation that fails to match human standards. To address these challenges, we present RecGPT-V2 with four key innovations. First, a Hierarchical Multi-Agent System restructures intent reasoning through coordinated collaboration, eliminating cognitive duplication while enabling diverse intent coverage. Combined with Hybrid Representation Inference that compresses user-behavior contexts, our framework reduces GPU consumption by 60% and improves exclusive recall from 9.39% to 10.99%. Second, a Meta-Prompting framework dynamically generates contextually adaptive prompts, improving explanation diversity by +7.3%. Third, constrained reinforcement learning mitigates multi-reward conflicts, achieving +24.1% improvement in tag prediction and +13.0% in explanation acceptance. Fourth, an Agent-as-a-Judge framework decomposes assessment into multi-step reasoning, improving human preference alignment. Online A/B tests on Taobao demonstrate significant improvements: +2.98% CTR, +3.71% IPV, +2.19% TV, and +11.46% NER. RecGPT-V2 establishes both the technical feasibility and commercial viability of deploying LLM-powered intent reasoning at scale, bridging the gap between cognitive exploration and industrial utility.

cs.IR↗

arXiv2025

$(\infty,\infty)$-Categorical Universal Motives

Ever since the introduction of motivic homotopy theory, as a well-proposed approximation of Grothendieck's dream, algebraic geometers then have the chance to study schemes via a homotopy theory. However topologists also found that lifting the usual homotopy theory over a sphere spectrum to the motivic homotopy category over a motivic bigraded sphere spectrum can make breakthroughs on elementary topology problems (such as computing homotopy groups of spheres, motivic Adams spectral sequences and so on). On the other hand, topological spaces can be all regarded as Grothendieck topoi, as in Lurie's work on ultracategories. Following Scholze, Lurie we systematically consider an $(\infty,\infty)$-ultracategorical universal motivic formalism, which directly fits into Lurie's framework on ultracategories, where we construct universal ultragestalten through motivicalization. The gestalten higher categorical six-functor formalism then allows us to consider the following classes of problems of different flavors: (I) Six-functor formalism for all Grothendieck sites and Grothendieck topoi; (II) Six-functor formalism for all topological spaces. We then in this paper got the chance to apply this to many problems in $p$-adic geometry and $p$-adic functional analysis: (I) $(\infty,\infty)$-categoricalization of motivic $+$-de Rham prismatization approach to generalization of Colmez's Montréal functor; (II) $(\infty,\infty)$-categoricalization of motivic generalized Riemann-Hilbert correspondence after Bhatt-Lurie; (III) $(\infty,\infty)$-categorical universal motives of derived algebraic stacks over $\mathbb{E}_\infty$-ring objects in the derived $\infty$-category of sphere spectrum, via universal motives of large Fargues-Fontaine gestalten, in families.

math.AG↗

arXiv2025

Neural Beam Field for Spatial Beam RSRP Prediction

Accurately predicting beam-level reference signal received power (RSRP) is essential for beam management in dense multi-user wireless networks, yet challenging due to high measurement overhead and fast channel variations. This paper proposes Neural Beam Field (NBF), a hybrid neural-physical framework for efficient and interpretable spatial beam RSRP prediction. Central to our approach is the introduction of the Multi-path Conditional Power Profile (MCPP), a learnable physical intermediary representing the site-specific propagation environment. This approach decouples the environment from specific antenna/beam configurations, which helps the model learn site-specific multipath features and enhances its generalization capability. We adopt a decoupled ``blackbox-whitebox" design: a Transformer-based deep neural network (DNN) learns the MCPP from sparse user measurements and positions, while a physics-inspired module analytically infers beam RSRP statistics. To improve convergence and adaptivity, we further introduce a Pretrain-and-Calibrate (PaC) strategy that leverages ray-tracing priors for physics-grounded pretraining and then RSRP data for on-site calibration. Extensive simulation results demonstrate that NBF significantly outperforms conventional table-based channel knowledge maps (CKMs) and pure blackbox DNNs in prediction accuracy, training efficiency, and generalization, while maintaining a compact model size. The proposed framework offers a scalable and physically grounded solution for intelligent beam management in next-generation dense wireless networks.

cs.IT↗

arXiv2025

SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?

Academic survey writing, which distills vast literature into a coherent and insightful narrative, remains a labor-intensive and intellectually demanding task. While recent approaches, such as general DeepResearch agents and survey-specialized methods, can generate surveys automatically (a.k.a. LLM4Survey), their outputs often fall short of human standards and there lacks a rigorous, reader-aligned benchmark for thoroughly revealing their deficiencies. To fill the gap, we propose a fine-grained, quiz-driven evaluation framework SurveyBench, featuring (1) typical survey topics source from recent 11,343 arXiv papers and corresponding 4,947 high-quality surveys; (2) a multifaceted metric hierarchy that assesses the outline quality (e.g., coverage breadth, logical coherence), content quality (e.g., synthesis granularity, clarity of insights), and non-textual richness; and (3) a dual-mode evaluation protocol that includes content-based and quiz-based answerability tests, explicitly aligned with readers' informational needs. Results show SurveyBench effectively challenges existing LLM4Survey approaches (e.g., on average 21% lower than human in content-based evaluation).

cs.CL↗

arXiv2025

Integrated Sensing, Communication, and Positioning in Cellular Vehicular Networks

In this correspondence, a novel integrated sensing and communication (ISAC) framework is proposed to accomplish data communication, vehicle positioning, and environment sensing simultaneously in a cellular vehicular network. By incorporating the vehicle positioning problem with the existing computational-imaging-based ISAC models, we formulate a special integrated sensing, communication, and positioning problem in which the unknowns are highly coupled. To mitigate the rank deficiency and make it solvable, we discretize the region of interest (ROI) into sensing and positioning pixels respectively, and exploit both the line-of-sight and non-line-of-sight propagation of the vehicles' uplink access signals. The resultant problem is shown to be a polynomial bilinear compressed sensing (CS) reconstruction problem, which is then solved by the alternating optimization (AO) algorithm to iteratively achieve symbol detection, vehicle positioning and environment sensing. Performance analysis and numerical results demonstrate the effectiveness of the proposed method.

eess.SP↗

arXiv2025

A Study on Optimizing the Thermal Performance of Coaxial Heat Exchanger Systems in Medium-Deep Geothermal Wells

Medium-deep geothermal energy is a key renewable source, but existing coaxial downhole heat exchanger (DHE) systems suffer from low efficiency and temperature decay. This study evaluates the impacts of circulating flow rate, inlet temperature, and operation mode on DHE performance, using field data from two geothermal wells (Well A: 3200m, 130.5$^{\circ}$C; Well B: 2500m, 103.3$^{\circ}$C). Results show that under an optimal condition (LC3: 50 m$^3$/h, 30$^{\circ}$C), Well A's heat extraction rate increased from 35% to 42%, with its outlet temperature rising from 15$^{\circ}$C to 20$^{\circ}$C. In contrast, Well B's rate decreased from 15% to 5%. After one week of continuous operation, the outlet temperature of Well A dropped from 55.7$^{\circ}$C to 16.5$^{\circ}$C, and Well B's from 68$^{\circ}$C to 17$^{\circ}$C. Adopting an intermittent mode (16h operation, 8h shutdown daily) reduced the temperature decay rate by approximately 10%. Based on these findings, we propose optimization strategies: controlling flow rate to 35m$^3$/h, maintaining an inlet temperature of 6--10$^{\circ}$C, and implementing intermittent scheduling. This work provides guidance for the efficient design and sustainable operation of DHE systems.

physics.app-ph↗

arXiv2025

Strong decays of $P_ψ^N(4440)^+$ and $P_ψ^N(4457)^+$ within the Bethe-Salpeter framework

By combining the effective Lagrangian and Bethe-Salpeter framework, we studied the mass spectra, wave functions, and strong decay widths of the two pentaquark states $P_ψ^N(4440)^+$ and $P_ψ^N(4457)^+$ reported by LHCb in 2019. Taking into account both the mass ordering and the decay widths, our results favor the interpretation of $P_ψ^N(4440)^+$ and $P_ψ^N(4457)^+$ as the isospin-$\frac12$ $[\bar D^*Σ_c]$ molecular states with $J^P$ configuration $(\frac{3}{2})^-$ and $(\frac12)^-$, respectively. We first calculate the one-boson-exchange interaction kernel of $[\bar D^*Σ_c]$ in the isospin-$\frac12$ configuration. Then we present the Bethe-Salpeter equation (BSE) and wave functions for the bound states of a vector meson and a $\frac12$ baryon with $J^P={\frac12}^-$ and ${\frac32}^-$. The obtained mass results for the $(\frac32)^-$ and $(\frac12)^-$ are $4.442$ and $4.457$ GeV, respectively. Combining the effective Lagrangians and the BS wave functions, we further calculate the strong decay channels $\bar D^{(*)0}Λ_c^+$, $J/ψ(η_c) p$, and $\bar DΣ_c^{(*)}$ for the two $P_ψ^N$ states. In the favored $\frac32^-$ and $\frac12^-$ configuration, the obtained total widths are $21.8$ MeV and $13.0$ MeV, respectively, which are substantially consistent with the LHCb data. Our results suggest that $\bar D^{0}Λ_c^+$ and $\bar D^{(*)0}Λ_c^+$ are the dominant decay channels to detect $P_ψ^N(4440)^+$ and $P_ψ^N(4457)^+$, respectively.

hep-ph↗

arXiv2025

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models

Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: head importance is treated as input-agnostic, and raw attention weights poorly reflect each token's true contribution. We present HAVE (Head-Adaptive Gating and ValuE Calibration), a parameter-free decoding framework that directly addresses both challenges. HAVE introduces head-adaptive gating, which performs instance-level soft reweighing of attention heads, and value calibration, which augments attention with the magnitude of value vectors to approximate write-back contribution. Together, these modules construct token-level evidence aligned with model updates and fuse it with the LM distribution through a lightweight uncertainty-scaled policy. HAVE requires no finetuning and operates in a single forward pass, making it efficient and broadly applicable. Experiments across multiple QA benchmarks and LLM families demonstrate that HAVE consistently reduces hallucinations and outperforms strong baselines, including DAGCD, with modest overhead. The framework is transparent, reproducible, and readily integrates with off-the-shelf LLMs, advancing trustworthy generation in real-world settings.

cs.CL↗

arXiv2025

GestoBrush: Facilitating Graffiti Artists' Digital Creation Experiences through Embodied AR Interactions

Graffiti has long documented the socio-cultural landscapes of urban spaces, yet increasing global regulations have constrained artists' creative freedom, prompting exploration of digital alternatives. Augmented Reality (AR) offers opportunities to extend graffiti into digital environments while retaining spatial and cultural significance, but prior research has largely centered on audience engagement rather than the embodied creative processes of graffiti artists. To address this, we developed GestoBrush, a mobile AR prototype that turns smartphones into virtual spray cans, enabling graffiti creation through embodied gestures. A co-design workshop underscored the role of embodiment-physical engagement with surroundings and body-driven creative processes-in digital workflows. We evaluated GestoBrush with six graffiti artists and findings suggested that embodied AR interactions supporting artists bypass real-world constraints and explore new artistic possibilities, whose AR artworks created enhanced senses of intuitiveness, immersion, and expressiveness. This work highlight how embodied AR tools can bridge the gap between physical graffiti practice and digital expression, suggesting pathways for designing immersive creative systems that respect the cultural ethos of street art while expanding its possibilities in virtual spaces.

cs.HC↗

arXiv2025

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors

Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and other high-stakes settings. Earlier "refusal-direction" edits can bypass those layers, but they rely on a single vector that indiscriminately unlocks all hazardous topics, offering no semantic control. We introduce Mutually Exclusive Unlock Vectors (MEUV), a lightweight framework that factorizes the monolithic refusal direction into topic-aligned, nearly orthogonal vectors, each dedicated to one sensitive capability. MEUV is learned in a single epoch with a multi-task objective that blends a differential-ablation margin, cross-topic and orthogonality penalties, and several auxiliary terms. On bilingual malicious-prompt benchmarks, MEUV achieves an attack success rate of no less than 87% on Gemma-2-2B, LLaMA-3-8B, and Qwen-7B, yet cuts cross-topic leakage by up to 90% compared with the best single-direction baseline. Vectors trained in Chinese transfer almost unchanged to English (and vice versa), suggesting a language-agnostic refusal subspace. The results show that fine-grained, topic-level capability activation is achievable with minimal utility loss, paving the way for controlled LLMs deployment in security-sensitive domains.

cs.LG↗

arXiv2025

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models

With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updates while preserving model integrity. Experimental results demonstrate that LoRA-FP not only significantly reduces computational overhead compared to conventional approaches but also achieves superior robustness across diverse scenarios, including incremental training and model fusion. Our code and datasets are publicly available at https://github.com/Xuzhenhua55/LoRA-FP.

cs.CR↗

arXiv2025

Crystalline electric field excitations in Weyl semimetal \textit{R}AlSi (\textit{R} = Ce, Pr and Nd)

The rare earth intermetallic system \textit{R}Al\textit{X} (\textit{R} = rare earth elements, \textit{X} = Si and Ge) is known to be a promising candidate of magnetic Weyl semimetal. Due to the complex interactions between the rare earth elements and surrounding atoms, as well as hybridization with itinerant electrons, this family likely possesses highly intriguing and novel magnetic structures and thus exhibits dynamic behaviors. We systematically probe polycrystalline samples of \textit{R}AlSi (\textit{R} = La, Ce, Pr and Nd) combining inelastic neutron scattering (INS), heat capacity and magnetic susceptibility measurements. The INS measurements identify well-resolved crystalline electric field (CEF) excitations at 19.2 and 24.9 meV in CeAlSi, at 5.4 meV in PrAlSi, and at 2.5 and 4.2 meV in NdAlSi. We analyzed the INS data using the corresponding CEF models and determined the CEF parameters and ground state wave functions of \textit{R}AlSi (\textit{R} = Ce, Pr and Nd). Our results suggest strong single-ion anisotropy in their ground states: $|\pm3/2\rangle$ (94.5\%) in CeAlSi, $|\pm3\rangle$ (99.2\%) in PrAlSi, and $|\pm9/2\rangle$ (76.2\%) in NdAlSi. Notably, the weaker anisotropy and strong exchange interactions in NdAlSi promote competing magnetic orders and CEF splitting at low temperature, contrasting with the robust CEF levels in magnetic states of CeAlSi and PrAlSi.

cond-mat.str-el↗