arXiv subjects

Ruiqi Xu

Publications and source records attributed to Ruiqi Xu.

10 recordsLinked to original sources

arXiv2026

ShellMaker: Language-Guided Exterior Completion under Structural Constraints

Despite advances in indoor scene generation, synthesizing coherent building exteriors consistent with generated interiors remains largely unexplored. Existing methods can generate floor plans and wall layouts but typically stop at a structural shell, lacking stylistically consistent facades and roofs. Completing these exteriors is challenging because the footprint, wall geometry, and opening semantics must remain fixed-constraints that unconstrained generative models often violate. We introduce ShellMaker, a language-guided exterior completion framework that operates under these structural constraints. Given a building scaffold and a text style prompt, ShellMaker generates a complete exterior mesh with PBR materials by combining parametric roof generation, LLM-based part-aware prompt refinement, joint wall-roof material retrieval, and geometry-aware assembly. Operating on a format agnostic scaffold representation, ShellMaker generalizes to indoor generators, CityGML, and CAD inputs, while maintaining structural consistency and improving architectural coherence over retrieval and unconstrained generative baselines. The project page is available at https://ruiqixu37.github.io/ShellMaker_web/

cs.CV↗

arXiv2026

Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate

Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that convergence reflects genuine deliberation or social compliance. We show that the conventional answer flip rate conflates three distinct mechanisms: spontaneous instability, stance-induced conformity, and reasoning-induced persuasion. Our three-source decomposition framework isolates each through controlled counterfactual conditions. In the primary MMLU-Pro setting, 37% of agent-question observations change under self-reflection alone, while robustness tests show substantial model-dependent instability across GPQA-Diamond and three model families; strict conformity is 29% in the primary setting and remains predominantly harmful across model replications (57-77% correct-to-wrong). A controlled information-gradient experiment reveals that even vacuous reasoning is associated with 20-39% error adoption among resistant agents, with reasoning-like presentation carrying substantial persuasive weight. Harmful conformity can be predicted from Round 0 features (AUC = 0.79), and risk-targeted intervention reduces it by 13.6 percentage points (p < 0.001). However, without correctness labels or self-reflection controls, reducing peer adoption does not improve accuracy, because harmful and beneficial influence cannot be distinguished.

cs.CL↗

arXiv2025

Chirality reversal at finite magnetic impurity strength and local signatures of a topological phase transition

We study the honeycomb lattice with a single magnetic impurity modeled by adding imaginary next-nearest-neighbor hopping ih on a single hexagon. This Haldane defect gives a topological mass term to the gapless Dirac cones and generates chirality. For a small density of defects Neehus et al [arXiv:2405.19289] found that the system's chirality reverses at a critical hc ~ 0.95 associated with an unexpected tri-critical point of Dirac fermions at zero defect density. We investigate this zero-density limit by analyzing a single defect and computing two experimentally relevant measures of chirality: (1) orbital magnetization via local Chern marker, a bulk probe of all occupied states; and (2) electronic currents of low-energy states. Both probes show a chirality reversal at a critical hc ~ 0.9--1. Motivated by this consistency we propose a defect-scale toy model whose low energy states reverse their chirality at hc' ~ 0.87. Remarkably, the same pair of zero energy bound states also generate the critical point hc in the full impurity projected T-matrix. Our results show how the chirality reversal produced by an impurity can be observed either in local probes or in the global topology and suggest a possible role of the microscopic defect structure at the critical point.

cond-mat.mes-hall↗

arXiv2025

ProcTex: Consistent and Interactive Text-to-texture Synthesis for Part-based Procedural Models

Recent advances in generative modeling have driven significant progress in text-guided texture synthesis. However, current methods focus on synthesizing texture for single static 3D object, and struggle to handle entire families of shapes, such as those produced by procedural programs. Applying existing methods naively to each procedural shape is too slow to support exploring different parameter configurations at interactive rates, and also results in inconsistent textures across the procedural shapes. To this end, we introduce ProcTex, the first text-to-texture system designed for part-based procedural models. ProcTex enables consistent and real-time text-guided texture synthesis for families of shapes, which integrates seamlessly with the interactive design flow of procedural modeling. To ensure consistency, our core approach is to synthesize texture for a template shape from the procedural model, followed by a texture transfer stage to apply the texture to other procedural shapes via solving dense correspondence. To ensure interactiveness, we propose a novel correspondence network and show that dense correspondence can be effectively learned by a neural network for procedural models. We also develop several techniques, including a retexturing pipeline to support structural variation from procedural parameters, and part-level UV texture map generation for local appearance editing. Extensive experiments on a diverse set of procedural models validate ProcTex's ability to produce high-quality, visually consistent textures while supporting interactive applications.

cs.GR↗

arXiv2024

Double Layer-Interlocked Crystals of Nitrogen-Rich Compounds under Zero-Pressure Conditions

Stabilizing nitrogen-rich compound crystals under conventional conditions is a key issue in the development and application of high-energy density materials (HEDMs). Herein, a two-dimensional double-layer interlocked Li4(N5)2 nitrogen-rich compound crystals, in which the two N5 rings are locked to by sharing four Li atoms, was found to maintain structural stability at zero pressure conditions. Dynamics studies reliably confirm crystal stability below 250 K. Furthermore, the stability of Li4(N5)2 crystal mainly arises from the ionic interaction between Li atoms and N5 rings, formed by the charge transfer from Li atoms to N5 rings. This study highlights the feasibility of stabilizing nitrogen-rich compound crystals under conventional conditions, paving the way for atomic level advancements in HEDMs.

cond-mat.mtrl-sci↗

arXiv2024

Dual-Path Mechanism of Amino Acid Racemization Mediated by Quantum Mechanical Tunneling

The racemization of amino acids constitutes one of the most elemental and critical reactions, holding primitive significance for understanding the life's origin and maintenance. Nevertheless, its mechanism at the atomic level has been persistently misunderstood for more than a century. In this work, we demonstrate that the racemization of amino acid molecules in aqueous environments can occur simultaneously by two pathways via the carboxyl (COOH) and amino (NH2) groups. Behind this result, the quantum mechanical tunneling (QMT) effect plays a pivotal role, as evidenced by the tunneling hindrance of the NH2 reaction and the tunneling enhancement of the COOH reaction. Notably, the disparity in the QMT effect leads to a crossover between the COOH and NH2 reactions within 200-257 K, such that NH2 reactions dominate at high temperatures and COOH reactions dominate at low temperatures. Our work emphasizes the significance of QMT effect in the racemization of amino acids and therefore introduces a dual-path coexistence mechanism, offering valuable insights into the origin of homochirality in extreme environments of the early Earth.

physics.chem-ph↗

arXiv2024

Combining Cloud and Mobile Computing for Machine Learning

Although the computing power of mobile devices is increasing, machine learning models are also growing in size. This trend creates problems for mobile devices due to limitations like their memory capacity and battery life. While many services, like ChatGPT and Midjourney, run all the inferences in the cloud, we believe a flexible and fine-grained task distribution is more desirable. In this work, we consider model segmentation as a solution to improving the user experience, dividing the computation between mobile devices and the cloud in a way that offloads the compute-heavy portion of the model while minimizing the data transfer required. We show that the division not only reduces the wait time for users but can also be fine-tuned to optimize the workloads of the cloud. To achieve that, we design a scheduler that collects information about network quality, client device capability, and job requirements, making decisions to achieve consistent performance across a range of devices while reducing the work the cloud needs to perform.

cs.DC↗

arXiv2023

Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training

In this work, we introduce the concept of complex text style transfer tasks, and constructed complex text datasets based on two widely applicable scenarios. Our dataset is the first large-scale data set of its kind, with 700 rephrased sentences and 1,000 sentences from the game Genshin Impact. While large language models (LLM) have shown promise in complex text style transfer, they have drawbacks such as data privacy concerns, network instability, and high deployment costs. To address these issues, we explore the effectiveness of small models (less than T5-3B) with implicit style pre-training through contrastive learning. We also propose a method for automated evaluation of text generation quality based on alignment with human evaluations using ChatGPT. Finally, we compare our approach with existing methods and show that our model achieves state-of-art performances of few-shot text style transfer models.

cs.CL↗

arXiv2023

Sequential Flipping: A Donor-Acceptor Exchange Mechanism in Water Trimer

The donor-acceptor exchange (DAE) is a significant hydrogen bond network rearrangement (HBNR) mechanism because it can lead to the change of hydrogen bond direction. In this work, we report a new DAE mechanism found in water trimer that is realized by sequential flipping (SF) of all molecules rather than the well-known proton transfer (PT) process. Meanwhile, the SF process has a much smaller potential barrier (0.262 eV) than the previously predicted collective rotation process (about 1.7 eV), implying that SF process is a main flipping process that can lead to DAE. Importantly, high-precision ab initio calculations show that SF-DAE can make the water ring to show a clear chiral difference from PT-DAE, which brings the prospect of distinguishing the two confusing processes based on circular dichroism spectra. The reaction rate analysis including the quantum tunneling indicates an obvious temperature-dependent competitive relationship between SF and PT processes, specifically, the SF process dominates above 65 K, while the PT process dominates below 65 K. Therefore, in most cases, the contribution for DAE mainly comes from the flipping process, rather than the PT process as previously thought. Our work enriches the understanding of the DAE mechanism in water trimer and provides a piece of the jigsaw that has been sought to the HBNR mechanism.

physics.chem-ph↗

arXiv2022

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

As Artificial Intelligence as a Service gains popularity, protecting well-trained models as intellectual property is becoming increasingly important. There are two common types of protection methods: ownership verification and usage authorization. In this paper, we propose Non-Transferable Learning (NTL), a novel approach that captures the exclusive data representation in the learned model and restricts the model generalization ability to certain domains. This approach provides effective solutions to both model verification and authorization. Specifically: 1) For ownership verification, watermarking techniques are commonly used but are often vulnerable to sophisticated watermark removal methods. By comparison, our NTL-based ownership verification provides robust resistance to state-of-the-art watermark removal methods, as shown in extensive experiments with 6 removal approaches over the digits, CIFAR10 & STL10, and VisDA datasets. 2) For usage authorization, prior solutions focus on authorizing specific users to access the model, but authorized users can still apply the model to any data without restriction. Our NTL-based authorization approach instead provides data-centric protection, which we call applicability authorization, by significantly degrading the performance of the model on unauthorized data. Its effectiveness is also shown through experiments on the aforementioned datasets.

cs.LG↗