arXiv subjects

Xin Tong

Publications and source records attributed to Xin Tong.

At least 37 records · Page 2Linked to original sources

arXiv2026

SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields

3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts -- critical for efficient editing and modeling. Existing quad-remeshing techniques typically produce complex layouts with irregular loops, leading to tedious manual cleanup and extensive algorithm tuning. We introduce SQuadGen, a diffusion-based generative framework that leverages Chart Distance Fields (CDF) to synthesize simple quad layouts on 3D shapes. Our approach addresses two key challenges: (1) the discrete nature of mesh connectivity, which hinders learning, and (2) the scarcity of large-scale datasets with simple quad meshes. To overcome the first, we propose CDF, a continuous surface-based representation enabling effective learning and synthesis of quad layouts. To address the second, we define loop-aware simplicity metrics and construct a large-scale dataset of high-quality quad layouts recovered from public 3D repositories through a robust quad-recovery pipeline. Extensive evaluations across diverse 3D inputs show that SQuadGen consistently outperforms existing methods, producing robust, artist-friendly simple quad layouts.

cs.GR↗

arXiv2026

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc

cs.LG↗

arXiv2026

LPM 1.0: Video-based Character Performance Model

Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Learning such performance from video is a promising alternative to traditional 3D pipelines. However, existing video models struggle to jointly achieve high expressiveness, real-time inference, and long-horizon identity stability, a tension we call the performance trilemma. Conversation is the most comprehensive performance scenario, as characters simultaneously speak, listen, react, and emote while maintaining identity over time. To address this, we present LPM 1.0 (Large Performance Model), focusing on single-person full-duplex audio-visual conversational performance. Concretely, we build a multimodal human-centric dataset through strict filtering, speaking-listening audio-video pairing, performance understanding, and identity-aware multi-reference extraction; train a 17B-parameter Diffusion Transformer (Base LPM) for highly controllable, identity-consistent performance through multimodal conditioning; and distill it into a causal streaming generator (Online LPM) for low-latency, infinite-length interaction. At inference, given a character image with identity-aware references, LPM 1.0 generates listening videos from user audio and speaking videos from synthesized audio, with text prompts for motion control, all at real-time speed with identity-stable, infinite-length generation. LPM 1.0 thus serves as a visual engine for conversational agents, live streaming characters, and game NPCs. To systematically evaluate this setting, we propose LPM-Bench, the first benchmark for interactive character performance. LPM 1.0 achieves state-of-the-art results across all evaluated dimensions while maintaining real-time inference.

cs.CV↗

arXiv2026

NexusAI: Enabling Design Space Exploration of Ideas through Cognitive Abstraction and Functional Decomposition

Large Language Models (LLMs) offer vast potential for creative ideation; however, their standard interaction paradigm often produces unstructured textual outputs that lead users to prematurely converge on sub-optimal ideas-a phenomenon known as fixation. While recent creativity tools have begun to structure these outputs, they remain compositionally opaque: ideas are organized as monolithic units that cannot be decomposed, abstracted, or recombinable at a sub-idea level. To address this, we propose Cognitive Abstraction (CA), a computational pipeline that transforms raw LLM-generated inspiration into a navigable and transformable design space. We implement this pipeline in NexusAI, a prototype diagramming system that supports (I) decomposition of inspiration into typed functional fragments, (II) multi-level abstraction to externalize mental scaling, and (III) cross-dimensional recombination to spark novel design directions. A within-subject user study (N=14) demonstrates that NexusAI significantly improves design space exploration, reduces cognitive overhead, and facilitates perspective reframing compared to a baseline. Our work contributes: (1) a characterization of "compositional opacity" as a barrier in human-AI co-creation; (2) the CA pipeline for operationalizing creative cognitive primitives at scale; and (3) empirical evidence that structured, multi-level representations can effectively mitigate fixation and support divergent exploration.

cs.HC↗

arXiv2026

CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks

Although Large Language Models (LLMs) demonstrate proficiency in knowledge-intensive tasks, current interfaces frequently precipitate cognitive misalignment by failing to externalize users' underlying reasoning structures. Existing tools typically represent intent as "flat lists," thereby disregarding the causal dependencies and revisable assumptions inherent in human decision-making. We introduce CogInstrument, a system that represents user reasoning through cognitive motifs-compositional, revisable units comprising concepts linked by causal dependencies. CogInstrument extracts these motifs from natural language interactions and renders them as editable graphical structures to facilitate bidirectional alignment. This structural externalization enables both the user and the LLM to inspect, negotiate, and reconcile reasoning processes iteratively. A within-subjects study (N=12) demonstrates that CogInstrument explicitly surfaces implicit reasoning structures, facilitating more targeted revision and reusability over conventional LLM-based dialogue interfaces. By enabling users to verify the logical grounding of LLM outputs, CogInstrument significantly enhances user agency, trust, and structural control over the collaboration. This work formalizes cognitive motifs as a fundamental unit for human-LLM alignment, providing a novel framework for achieving structured, reasoning-based human-AI collaboration.

cs.HC↗

arXiv2026

NLOS-Aided Joint OTA Synchronization and Off-Grid Imaging for Distributed MIMO Systems

Distributed multiple-input multiple-output (MIMO) architectures enable large-scale integrated sensing and communication (ISAC) by providing high spatial resolution and robustness through spatial diversity. However, practical phase-coherent sensing is challenged by phase synchronization errors and modeling mismatch caused by grid discretization. Existing over-the-air (OTA) synchronization methods typically treat synchronization and sensing tasks separately, which may lead to inaccurate phase alignment when multipath components are used for imaging. In this paper, we propose a non-line-of-sight (NLOS)-aided joint OTA synchronization and off-grid imaging framework for distributed MIMO ISAC systems. First, a line-of-sight (LOS)-assisted coarse synchronization is performed to establish initial phase coherence across distributed links. Subsequently, an iterative refinement stage exploits reconstructed NLOS components obtained from imaging results. By modeling off-grid effects via a first-order Taylor expansion, we transform measurements with nonlinear off-grid offset into an augmented linear model with jointly sparse reflectivity and off-set variables. The imaging problem is reformulated as a structured sparse recovery task and solved using a tailored off-grid approximate message passing (OG-AMP) algorithm. The imaging and synchronization modules are coupled within a closed-loop alternative optimization framework, where improved imaging enables more accurate phase refinement, and vice versa. Numerical results show that the proposed framework achieves accurate synchronization and imaging under phase errors. Compared with conventional approaches, it shows superior robustness and accuracy.

eess.SP↗

arXiv2026

From Pets to Robots: MojiKit as a Data-Informed Toolkit for Affective HRI Design

Designing affective behaviors for animal-inspired social robots often relies on intuition and personal experience, leading to fragmented outcomes. To provide more systematic guidance, we first coded and analyzed human-pet interaction videos, validated insights through literature and interviews, and created structured reference cards that map the design space of pet-inspired affective interactions. Building on this, we developed MojiKit, a toolkit combining reference cards, a zoomorphic robot prototype (MomoBot), and a behavior control studio. We evaluated MojiKit in co-creation workshops with 18 participants, finding that MojiKit helped them design 35 affective interaction patterns beyond their own pet experiences, while the code-free studio lowered the technical barrier and enhanced creative agency. Our contributions include the data-informed structured resource for pet-inspired affective HRI design, an integrated toolkit that bridges reference materials with hands-on prototyping, and empirical evidence showing how MojiKit empowers users to systematically create richer, more diverse affective robot behaviors.

cs.HC↗

arXiv2026

Precision measurement of the ground-state hyperfine constant for $^9Be^+$ in a linear Paul trap via magnetically insensitive hyperfine transitions

Direct measurements of the ground-state magnetically insensitive hyperfine transition |F=2,mF=0>->|F=1,mF=0> of $^9Be^+$ ions have been performed using microwave-driven state transfer. The $^9Be^+$ ions are confined and laser-cooled in a linear Paul trap, forming a Coulomb crystal. The transition frequencies have been measured over a magnetic field range of $ \pm 0.5 mT $ centered at zero magnetic field, and the acquired data were fitted accounting for the high-order Zeeman effect. The hyperfine constant A is determined to be -625.008840(35) MHz, achieving a relative precision of $ 5.6 \times 10^{-8}$.

physics.atom-ph↗

arXiv2026

Development and Application of an eV Neutron Polarization for Parity Violation Studies at CSNS Back-n Beamline

The dynamic enhancement of symmetry-breaking effects in neutron-nucleus resonances provides a sensitive testing ground for Time-Reversal Invariance Violation (TRIV). Exploiting this mechanism, the Neutron Optics Parity and Time Reversal Experiment (NOPTREX) seeks to elucidate the origin of the universe's baryon asymmetry. Critical to this effort is the precise measurement of Parity Violation (PV) asymmetries, which is essential to calibrate the nuclear parameters required for future TRIV experiments. To facilitate these studies, we developed an eV polarized neutron at the Back-n white neutron beamline of the China Spallation Neutron Source (CSNS). Neutron polarization is generated by an in-situ Spin-Exchange Optical Pumping (SEOP) $^3$He filter. Spin manipulation is performed by an adiabatic spin flipper, while spin polarization is preserved over the flight path by a vacuum transport system equipped with a solenoidal guide field. Experiments successfully measured an asymmetry of approximately $7.8 \pm 2.4$ (stat.) $\pm 0.3$ (sys.) % at the 0.747 eV p-wave resonance of $^{139}$La. These results are in agreement with previous results on this resonance and validate the system's capability for PV measurements.

physics.ins-det↗

arXiv2026

DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces

Large Language Models are reshaping task automation, yet remain limited in complex, multi-step real-world tasks that require aligning with vague user intent and enabling dynamic user override. From a formative study with 12 participants, we found that end-users actively seek to shape task-oriented interfaces rather than relying on one-shot outputs. To address this, we introduce the human-agent co-generation paradigm, materialized in DuetUI. This LLM-empowered system unfolds alongside task progress through a bidirectional context loop-the agent scaffolds the interface by decomposing the task, while the user's direct manipulations implicitly steer the agent's next generation step. In a technical ablation study and a user study with 24 participants, DuetUI improved task efficiency and interface usability, supporting more seamless human-agent collaboration. Our contributions include the proposal of this novel paradigm, the design of a proof-of-concept DuetUI prototype embodying it, and empirical and technical insights from an initial evaluation of how this bidirectional loop may help align agents with human intent and inform future development.

cs.HC↗

arXiv2026

How Do We Research Human-Robot Interaction in the Age of Large Language Models? A Systematic Review

Advances in large language models (LLMs) are profoundly reshaping the field of human-robot interaction (HRI). While prior work has highlighted the technical potential of LLMs, few studies have systematically examined their human-centered impact (e.g., human-oriented understanding, user modeling, and levels of autonomy), making it difficult to consolidate emerging challenges in LLM-driven HRI systems. Therefore, we conducted a systematic literature search following the PRISMA guideline, identifying 86 articles that met our inclusion criteria. Our findings reveal that: (1) LLMs are transforming the fundamentals of HRI by reshaping how robots sense context, generate socially grounded interactions, and maintain continuous alignment with human needs in embodied settings; and (2) current research is largely exploratory, with different studies focusing on different facets of LLM-driven HRI, resulting in wide-ranging choices of experimental setups, study methods, and evaluation metrics. Finally, we identify key design considerations and challenges, offering a coherent overview and guidelines for future research at the intersection of LLMs and HRI.

cs.RO↗

arXiv2026

Expert Divergence Learning for MoE-based Language Models

The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address this, we introduce Expert Divergence Learning, a novel pre-training strategy that explicitly encourages functional specialization among experts. Our method incorporates a label-driven auxiliary loss that leverages domain labels inherent in pre-training corpora to maximize the Jensen-Shannon Divergence between the expert routing distributions of different data domains. This optimization objective guides the model to develop diverged routing policies for varied domains and closer routing policies for the same domain, which leads to emergent and organized expert specialization. We validate our approach by pre-training MoE models of up to 15 billion parameters from scratch. Experimental results demonstrate that models trained with Expert Divergence Learning not only achieve a lower language modeling loss but also exhibit significant performance improvements across a diverse range of downstream benchmarks. Further analysis confirms that our method effectively mitigates expert homogenization and brings greater functional specialization, all with negligible computational overhead during training.

cs.LG↗

arXiv2026

FAIR: Framing AIs Role in Programming Competitions -- Understanding How LLMs Are Changing the Game in Competitive Programming

This paper investigates how large language models (LLMs) are reshaping competitive programming. The field functions as an intellectual contest within computer science education and is marked by rapid iteration, real-time feedback, transparent solutions, and strict integrity norms. Prior work has evaluated LLMs performance on contest problems, but little is known about how human stakeholders -- contestants, problem setters, coaches, and platform stewards -- are adapting their workflows and contest norms under LLMs-induced shifts. At the same time, rising AI-assisted misuse and inconsistent governance expose urgent gaps in sustaining fairness and credibility. Drawing on 37 interviews spanning all four roles and a global survey of 207 contestants, as well as an API-based crawl of Codeforces contest logs (2022-2025) for quantitative analysis, we contribute: (i) an empirical account of evolving workflows, (ii) an analysis of contested fairness norms, and (iii) a chess-inspired governance approach with actionable measures -- real-time LLMs checks in online contests, peer co-monitoring and reporting, and cross-validation against offline performance -- to curb LLMs-assisted misuse while preserving fairness, transparency, and credibility.

cs.HC↗

arXiv2026

Physics-Inspired Target Shape Detection and Reconstruction in mmWave Communication Systems

The integration of sensing and communication (ISAC) is an essential function of future wireless systems. Due to its large available bandwidth, millimeter-wave (mmWave) ISAC systems are able to achieve high sensing accuracy. In this paper, we consider the multiple base-station (BS) collaborative sensing problem in a multi-input multi-output (MIMO) orthogonal frequency division multiplexing (OFDM) mmWave communication system. Our aim is to sense a remote target shape with the collected signals which consist of both the reflection and scattering signals. We first characterize the mmWave's scattering and reflection effects based on the Lambertian scattering model. Then we apply the periodogram technique to obtain rough scattering point detection, and further incorporate the subspace method to achieve more precise scattering and reflection point detection. Based on these, a reconstruction algorithm based on Hough Transform and principal component analysis (PCA) is designed for a single convex polygon target scenario. To improve the accuracy and completeness of the reconstruction results, we propose a method to further fuse the scattering and reflection points. Extensive simulation results validate the effectiveness of the proposed algorithms.

eess.SP↗

arXiv2026

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning

Large language models (LLMs), despite their powerful capabilities, suffer from factual hallucinations where they generate verifiable falsehoods. We identify a root of this issue: the imbalanced data distribution in the pretraining corpus, which leads to a state of "low-probability truth" and "high-probability falsehood". Recent approaches, such as teaching models to say "I don't know" or post-hoc knowledge editing, either evade the problem or face catastrophic forgetting. To address this issue from its root, we propose \textbf{PretrainRL}, a novel framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. The core principle of PretrainRL is "\textbf{debiasing then learning}." It actively reshapes the model's probability distribution by down-weighting high-probability falsehoods, thereby making "room" for low-probability truths to be learned effectively. To enable this, we design an efficient negative sampling strategy to discover these high-probability falsehoods and introduce novel metrics to evaluate the model's probabilistic state concerning factual knowledge. Extensive experiments on three public benchmarks demonstrate that PretrainRL significantly alleviates factual hallucinations and outperforms state-of-the-art methods.

cs.CL↗

arXiv2026

DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM Alignment

Recent large language models (LLMs) show promise in design tasks, yet a fundamental misalignment persists: design thinking requires iterative intent formulation, while LLMs treat inputs as complete specifications. This challenges design intent formulation, where designers must progressively refine understanding through exploration. Existing tools either sacrifice exploratory flexibility for structural stability or leave reasoning implicit, failing to support human-LLM alignment. Through a formative study with eight designers, we introduce curated reasoning-enabling designers to explicitly inspect, reorganize, and selectively regenerate LLM reasoning structures. We present DesignerlyLoop, implementing this through a two-layer structure separating design intent from LLM reasoning. A study with 20 designers demonstrates that curated reasoning significantly improves design quality and creativity. Our work contributes a novel interaction paradigm for human-LLM alignment, transforming LLMs from content generators into structured reasoning partners in creative design.

cs.HC↗

arXiv2026

Reflexa: Uncovering How LLM-Supported Reflection Scaffolding Reshapes Creativity in Creative Coding

Creative coding requires continuous translation between evolving concepts and computational artifacts, making reflection essential yet difficult to sustain. Creators often struggle to manage ambiguous intentions, emergent outputs, and complex code, limiting depth of exploration. This work examines how large language models (LLMs) can scaffold reflection not as isolated prompts, but as a system-level mechanism shaping creative regulation. From formative studies with eight expert creators, we derived reflection challenges and design principles that informed Reflexa, an integrated scaffold combining dialogic guidance, visualized version navigation, and iterative suggestion pathways. A within-subject study with 18 participants provides an exploratory mechanism validation, showing that structured reflection patterns mediate the link between AI interaction and creative outcomes. These reflection trajectories enhanced perceived controllability, broadened exploration, and improved originality and aesthetic quality. Our findings advance HCI understanding of reflection from LLM-assisted creative practices, and provide design strategies for building LLM-based creative tools that support richer human-AI co-creativity.

cs.HC↗

arXiv2026

Energy-Efficient Probabilistic Semantic Communication Over Visible Light Networks With Rate Splitting

Visible light communication (VLC) is emerging as a key technology for future wireless communication systems due to its unique physical-layer advantages over traditional radio-frequency (RF)-based systems. However, its integration with higher-layer techniques, such as semantic communication, remains underexplored. This paper investigates the energy efficiency maximization problem in a resource-constrained VLC-based probabilistic semantic communication (PSCom) system. In the considered model, light-emitting diode (LED) transmitters perform semantic compression to reduce data size, which incurs additional computation overhead. The compressed semantic information is transmitted to the users for semantic inference using a shared knowledge base that requires periodic updates to ensure synchronization. In the PSCom system, the knowledge base is represented by probabilistic graphs. To enable simultaneous transmission of both knowledge and information data, rate splitting multiple access (RSMA) is employed. The optimization problem focuses on maximizing energy efficiency by jointly optimizing transmit beamforming, direct current (DC) bias, common rate allocation, and semantic compression ratio, while accounting for both communication and computation costs. To solve this problem, an alternating optimization algorithm based on successive convex approximation (SCA) and Dinkelbach method is developed. Simulation results demonstrate the effectiveness of the proposed approach.

cs.IT↗