arXiv subjects

Yuan Zhang

Publications and source records attributed to Yuan Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

On a Local Radial Rigidity Phenomenon of Elliptic Systems on Riemannian Manifolds

In this paper, we study local radial rigidity phenomena for a broad class of general-order elliptic systems on Riemannian manifolds via a reduction to singular ordinary differential equations of Euler type. These rigidity properties have natural applications to several geometric problems, including prescribed curvature problems of Yamabe and Paneitz type in conformal geometry, higher-order analogues arising from harmonic maps, and Calabi-type problems on Kähler manifolds. The method applies also to higher-order nonlinear Poisson systems and, more generally, to weighted divergence-form elliptic systems, yielding local uniqueness and existence results for solutions with prescribed initial jets at the singularity.

math.AP↗

arXiv2026

Extreme Optical Field Confinement and Enhancement in a Plasmonic Picopatch within a Nanoparticle-on-Mirror Resonator

Plasmonic resonances in metallic nanogaps can confine light into nanometric regions, but reaching modes of volume $\approx 1$ nm$^3$ remains challenging. We present a detailed theoretical analysis of the optical modes of an experimentally-motivated nanoresonator configuration that contains a picopatch formed by the lifting of a few gold atoms in the gap of a Nanoparticle-on-Mirror (NPoM) structure. Classical simulations indicate that the plasmonic modes associated with the picopatch geometry can confine light to extremely small regions and are highly sensitive to the picopatch size and shape, enabling broad tunability. Furthermore, these modes can couple strongly with other nanocavity modes of the structure, as identified from a clear anti-crossing behavior of the polaritonic resonances. Remarkably, up to $\approx 2000$-fold electric field enhancement inside the picopatch and tiny effective mode volumes approaching $\approx 1$ nm$^3$ are obtained. Further, changing the morphology of the picopatch does not modify the qualitative findings, and increasing the absorption losses in the classical simulations, to mimic quantum (non-local) effects in the metal permittivity, decreases the electric field enhancement only moderately. Compared to the standard picocavities formed by single-atom protrusions, picopatches are an intriguing alternative to reach extreme optical field confinement and enhancement in plasmonic cavities.

physics.optics↗

arXiv2026

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent

LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which may lead to privacy leakage, financial loss, or even full system compromise. In this paper, we present AgentGuard, an attribute-based access control framework for tool-use LLM-based agents. AgentGuard adopts a client-server architecture. On the client side, AgentGuard provides lightweight integration for agents implemented in different programming languages and architectures. It requires only minor code modifications (e.g., around 10 lines) without changing the underlying agent execution logic. On the server side, AgentGuard provides three complementary inspection mechanisms to cover both single-tool and cross-tool security risks in agent execution. In addition, it offers a visualized front-end interface for security policy specification and runtime auditing. Currently, AgentGuard is publicly accessible at https://github.com/WhitzardAgent/AgentGuard.

cs.CR↗

arXiv2026

JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation

We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.

cs.GR↗

arXiv2026

Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control

Natural language is an intuitive interface for humanoid robots, yet streaming whole-body control requires control representations that are executable now and anticipatory of future physical transitions. Existing language-conditioned humanoid systems typically generate kinematic references that a low-level tracker must repair reactively, or use latent/action policies whose outputs do not explicitly encode upcoming contact changes, support transfers, and balance preparation. We propose \textbf{DAJI} (\emph{Dynamics-Aligned Joint Intent}), a hierarchical framework that learns an anticipatory joint-intent interface between language generation and closed-loop control. DAJI-Act distills a future-aware teacher into a deployable diffusion action policy through student-driven rollouts, while DAJI-Flow autoregressively generates future intent chunks from language and intent history. Experiments show that DAJI achieves strong results in anticipatory latent learning, single-instruction generation, and streaming instruction following, reaching 94.42\% rollout success on HumanML3D-style generation and 0.152 subsequence FID on BABEL.

cs.RO↗

arXiv2026

SEED: Targeted Data Selection by Weighted Independent Set

Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph, where nodes represent data samples weighted by influence, and edges connect semantically redundant pairs. This formulation naturally yields subsets that are simultaneously high-quality and diverse. However, two challenges arise in practice: naive node weights fail to distinguish informative signals from gradient noise, and edge construction under heterogeneous domain distributions produces structurally imbalanced graphs that bias selection toward sparse regions. To address these issues, we introduce two principled refinements from a unified graph perspective: (1) \textit{node value calibration} that restricts influence estimation to the bilateral salient subspace to ground node importance in task-relevant signals rather than surface-level statistics; (2) \textit{local scale normalization} that adapts edge thresholds to local neighborhood density, mitigating graph imbalance induced by cross-domain distribution shifts. Together, these components yield a robust and scalable data selection pipeline dubbed SEED. We further construct \texttt{Honeybee-Remake-SEED-200K}, a compact multimodal dataset curated by SEED. Extensive experiments show that SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation across diverse model families.

cs.LG↗

arXiv2026

Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents' social behaviors and internal emotions: generated behaviors rarely influence an agent's emotional state, and emotional states seldom shape subsequent behaviors. We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression. CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions; and user feedback continually revises both memory and emotional state, enabling reflection and anticipation. We instantiate CTEM as Auri, a companion agent on an instant-messaging platform, and report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.

cs.HC↗

arXiv2026

Generalized Priority-Aware Shapley Value

Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to be binary and acyclic, a restriction spectacularly violated in real-data examples such as aggregated human preferences and multi-criterion comparisons. We introduce the generalized priority-aware Shapley value (GPASV), a random order value defined on arbitrary directed weighted priority graphs, in which pairwise edges penalize rather than forbid order violations. GPASV covers a range of classical models as boundary cases. We establish GPASV through an axiomatic characterization, develop the associated computational methods, and introduce a priority sweeping diagnostic extending PASV's. We apply GPASV to LLM ensemble valuation on the cyclic Chatbot Arena preference graph, illustrating that priority-aware valuation is not a one-button operation: different balances of pairwise graph priority versus individual soft priority produce substantively different valuations of the same data.

cs.LG↗

arXiv2026

TextLDM: Language Modeling with Continuous Latent Diffusion

Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next step toward a single architecture for both generation (visual synthesis) and understanding (text generation) is to apply this framework to language modeling. We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification. A Transformer-based VAE maps discrete tokens to continuous latents, enhanced by Representation Alignment (REPA) with a frozen pretrained language model to produce representations effective for conditional denoising. A standard DiT then performs flow matching in this latent space, identical in architecture to its visual counterpart. The central challenge we address is obtaining high-quality continuous text representations: we find that reconstruction fidelity alone is insufficient, and that aligning latent features with a pretrained language model via REPA is critical for downstream generation quality. Trained from scratch on OpenWebText2, TextLDM substantially outperforms prior diffusion language models and matches GPT-2 under the same settings. Our results establish that the visual DiT recipe transfers effectively to language, taking a concrete step toward unified diffusion architectures for multimodal generation and understanding.

cs.CL↗

arXiv2026

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world models (e.g., UWM) that only model 2D pixel-space and fail to balance action efficiency and world modeling quality. To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos, and obtains spatial information efficiently through a lightweight structural adaptation: replicating the final few blocks of the pretrained Diffusion Transformer into a dedicated depth prediction branch for the reconstruction of future spatial information. Moreover, we propose Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency. ANS applies a specialized asynchronous denoising schedule during inference, which rapidly decodes actions with fewer steps to enable efficient real-time execution, while dedicating the full sequence of steps to generate high-fidelity video. Rather than entirely decoupling the timesteps during training, ANS samples from their joint distribution to align with the inference distribution. Pretrained on over 5,800 hours of robotic data, X-WAM achieves 79.2% and 90.7% average success rate on RoboCasa and RoboTwin 2.0 benchmarks, while producing high-fidelity 4D reconstruction and generation surpassing existing methods in both visual and geometric metrics.

cs.RO↗

arXiv2026

How Do Ice Shelves Calve? Peridynamic Modeling of Ice Shelf Fracture Driven by Wave Erosion, Basal Melting, and Buoyancy Flexure

An ice shelf is a floating extension of a land-based ice sheet into the ocean. It plays a crucial role in slowing down the flow of land ice into the sea, thus stabilizing the ice sheet. However, this stabilizing effect can be weakened by ice calving, a process in which large fragments of ice detach from the ice shelf. Although ice calving is widely acknowledged as a major contributor to ice mass loss, and its frequency and magnitude are highly sensitive to the environmental forcing, the underlying physics-based mechanisms remain poorly understood, particularly under ocean wave actions. In this context, we developed a nonlocal peridynamics (PD) framework to model the ice calving process subjected to wave-induced frontal corrosion. The proposed physics-based PD framework enables investigation of the coupled effects of self-weight bending, buoyancy-induced foot loosening, and ice calving process. To authors' best knowledge, this work represents the first attempt to employ a physics-based peridynamics framework for simulating ice calving processes. Compared with conventional finite element methods (FEM), the PD framework naturally captures crack initiation, interaction, and propagation without the need for special numerical treatments, thereby providing a robust tool for simulating fracture phenomena under large deformations and long-term environmental loading. To quantitatively resolve fracture processes, we implemented a static first Piola Kirchhoff virial stress formulation within the PD framework, allowing direct evaluation of stress concentration and energy release at evolving crack tips. Subsequently, the model is rigorously validated through one-to-one comparisons with finite-element stress fields, analytical beam-theory solutions, and recent field observations of wave-driven ice-shelf failure reported by Sartore et al. (2025).

cs.CE↗

arXiv2026

Measuring Structural Political Fragmentation

Political fragmentation denotes the differentiation of a political system into multiple groups and the extent of separation among them. It often manifests structurally in online interaction behaviors. To measure and compare political fragmentation across contexts, previous scholarship has often relied on network measures of polarisation such as modularity and the Krackhardt E-I index. Here, we show that these metrics combine two aspects of fragmentation: the strength of separation and the number of fragments. These two aspects have not been clearly distinguished in previous work, making comparisons across varied systems difficult to interpret. In addition, none of them is designed to capture the multiscale fragmentation structures that characterize real-world multi-dimensional political spaces. We compare several network measures and show that the two aspects of network fragmentation are best captured by the pairwise adaptive E-I index and the effective number of communities (ENC), while other measures confound the strength of separation and the number of fragments. Furthermore, we introduce a novel metric for multiscale fragmentation, the effective branching factor (EBF), capturing how political fragments at one level split into smaller fragments at the next level. Applying EBF to two empirical datasets spanning Brazil, Spain, and the United States yields consistent country rankings across datasets. Overall, these results clarify three complementary dimensions of structural political fragmentation: strength of separation, number of fragments, and between-level branching. They support a more holistic characterization of structural political fragmentation.

cs.SI↗

arXiv2026

Latent Linear Quadratic Regulator for Robotic Control Tasks

Model predictive control (MPC) has played a more crucial role in various robotic control tasks, but its high computational requirements are concerning, especially for nonlinear dynamical models. This paper presents a $\textbf{la}$tent $\textbf{l}$inear $\textbf{q}$uadratic $\textbf{r}$egulator (LaLQR) that maps the state space into a latent space, on which the dynamical model is linear and the cost function is quadratic, allowing the efficient application of LQR. We jointly learn this alternative system by imitating the original MPC. Experiments show LaLQR's superior efficiency and generalization compared to other baselines.

cs.RO↗

arXiv2026

Pool model: a mass preserving multi particle aggregation process

We present and study the Pool model in $\mathbb{R}^2$, a rotationally symmetric analogue of Multi-Particle Diffusion-Limited Aggregation (MDLA), in which particles ("droplets") perform continuous-time random walks and are absorbed upon entering a circular pool initially centered at the origin. Each absorbed particle increases the pool's mass, and the pool expands so that its area grows accordingly, yielding a natural mass-preserving dynamics. A central tool which is of independent interest is a version of Kurtz's theorem for this model, depicting the field of particles conditioned on the growth of the pool as an independent non-homogeneous Poisson point process.

math.PR↗

arXiv2026

CoD-Lite: Real-Time Diffusion-Based Generative Image Compression

Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios that demand lightweight models. In this paper, we explore the design of real-time and lightweight diffusion codecs by addressing two pivotal questions. First, does diffusion pre-training benefit lightweight diffusion codecs? Through systematic analysis, we find that generation-oriented pre-training is less effective at small model scales whereas compression-oriented pre-training yields consistently better performance. Second, are transformers essential? We find that while global attention is crucial for standard generation, lightweight convolutions suffice for compression-oriented diffusion when paired with distillation. Guided by these findings, we establish a one-step lightweight convolution diffusion codec that achieves real-time $60$~FPS encoding and $42$~FPS decoding at 1080p. Further enhanced by distillation and adversarial learning, the proposed codec reduces bitrate by 85\% at a comparable FID to MS-ILLM, bridging the gap between generative compression and practical real-time deployment. Codes are released at https://github.com/microsoft/GenCodec/tree/main/CoD_Lite

cs.CV↗

arXiv2026

Data-Driven Observers Design for Descriptor Systems

State estimation constitutes a core task in monitoring, supervision, and control of dynamic systems. This paper proposes a data-driven framework for the design of state observers for descriptor systems. Necessary and sufficient conditions for the existence of a standard state observer are derived purely from data under mild assumptions. When the system is subject to unknown inputs, we further extend the framework to the data-driven design method for full-order unknown input observer (UIO). Notably, for both the standard state observer and the UIO, we establish the mathematical equivalence between the proposed data-driven existence conditions and classical model-based ones. Moreover, the data-driven approach is applied to the design of extended state observers, enabling simultaneous estimation of system states and disturbances via system augmentation. Numerical simulations validate the effectiveness of the proposed methods.

eess.SY↗

arXiv2026

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge but still presents formidable reasoning challenges, such as complex constraints, nested logical branches, and semantic interference. To address this gap, we introduce General365, a benchmark specifically designed to assess general reasoning in LLMs. By restricting background knowledge to a K-12 level, General365 explicitly decouples reasoning from specialized expertise. The benchmark comprises 365 seed problems and 1,095 variant problems across eight categories, ensuring both high difficulty and diversity. Evaluations across 26 leading LLMs reveal that even the top-performing model achieves only 62.8% accuracy, in stark contrast to the near-perfect performances of LLMs in math and physics benchmarks. These results suggest that the reasoning abilities of current LLMs are heavily domain-dependent, leaving significant room for improvement in broader applications. We envision General365 as a catalyst for advancing LLM reasoning beyond domain-specific tasks toward robust, general-purpose real-world scenarios. Code, Dataset, and Leaderboard: https://general365.github.io

cs.CL↗

arXiv2026

Key-Embedded Privacy for Decentralized AI in Biomedical Omics

The rapid adoption of data-driven methods in biomedicine has intensified concerns over privacy, governance, and regulation, limiting raw data sharing and hindering the assembly of representative cohorts for clinically relevant AI. This landscape necessitates practical, efficient privacy solutions, as cryptographic defenses often impose heavy overhead and differential privacy can degrade performance, leading to sub-optimal outcomes in real-world settings. Here, we present a lightweight federated learning method, INFL, based on Implicit Neural Representations that addresses these challenges. Our approach integrates plug-and-play, coordinate-conditioned modules into client models, embeds a secret key directly into the architecture, and supports seamless aggregation across heterogeneous sites. Across diverse biomedical omics tasks, including cohort-scale classification in bulk proteomics, regression for perturbation prediction in single-cell transcriptomics, and clustering in spatial transcriptomics and multi-omics with both public and private data, we demonstrate that INFL achieves strong, controllable privacy while maintaining utility, preserving the performance necessary for downstream scientific and clinical applications.

cs.LG↗