arXiv subjects

Dong Zhang

Publications and source records attributed to Dong Zhang.

At least 19 recordsLinked to original sources

arXiv2026

RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report

On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.

cs.CV↗

arXiv2026

Convex-like Submanifolds, Caps and a Volume Comparison Theorem

Convex-like submanifolds in the Lorentz-Minkowski spaces are introduced in this paper as a natural and broad generalization of convex surfaces in the Euclidean space. Associated with such a convex-like submanifold in a Minkowski space, we define roofs (which resembles the supporting planes), caps (which are generated by the light rays in the normal bundle), and towers (which revives the notion of interior for such high codimensional objects). As a touchstone of this theory, a volume comparison theorem is proved, which is a non-trivial generalization of the obvious fact that among two nested convex surfaces, the outer one has larger volume. Finally we provide two important applications of this theorem.

math.DG↗

arXiv2026

MadStree: automated evaluation of tree-level de Sitter correlators

We first derived the formulae of recursive reduction and dlog-form differential equations for arbitrary tree-level cosmological correlator, taking the external relations of massless bulk propagators into consideration. The differential equations could be systematically solved and provide the efficient evaluation of them. We have implemented this methodology as a user-friendly Mathematica package MadStree for computing arbitrary tree-level cosmological correlators.

hep-ph↗

arXiv2026

Combinatorial Courant-Fischer-Weyl Minimax Principle on Cheeger $k$-constants of Weighted Forests

We present several max-min and minimax characterizations of Cheeger $k$-constants in weighted forests, thereby providing the first combinatorial analogue of the Courant-\\Fischer-Weyl minimax principle. As for applications, we prove that the forest 1-Laplacian variational eigenvalues are independent of the choice of typical indexes; we propose a refined higher order Cheeger inequality which establishes a relationship between Miclo's multiway Cheeger constants and the variational eigenvalues of graph $p$-Laplacians; and we show a purely combinatorial proof for the equality $h_k=λ_k(Δ_1)$ on trees which connects the 1-Laplacian variational eigenvalues and the multiway Cheeger constants.

math.CO↗

arXiv2026

New graph invariants based on $p$-Laplacian eigenvalues

We present monotonicity inequalities for certain functions involving eigenvalues of $p$-Laplacians on signed graphs with respect to $p$. Inspired by such monotonicity, we propose new spectrum-based graph invariants, called (variational) cut-off adjacency eigenvalues, that are relevant to certain eigenvector-dependent nonlinear eigenvalue problem. Using these invariants, we obtain new lower bounds for the $p$-Laplacian variational eigenvalues, essentially giving the state-of-the-art spectral asymptotics for these eigenvalues. Moreover, based on such invariants, we establish two inertia bounds regarding the cardinalities of a maximum independent set and a minimum edge cover, respectively. The first inertia bound enhances the classical Cvetković bound, and the second one implies that the $k$-th $p$-Laplacian variational eigenvalue is of the order $2^p$ as $p$ tends to infinity whenever $k$ is larger than the cardinality of a minimum edge cover of the underlying graph. We further discover an interesting connection between graph $p$-Laplacian eigenvalues and tensor eigenvalues and discuss applications of our invariants to spectral problems of tensors.

math.SP↗

arXiv2026

Graphon as a Bridge between Graphs and Manifolds

We show that there exist graphons that interpolate between Riemannian manifolds and weighted geometric graphs. Specifically, the graph-to-manifold approximation used in manifold learning can be regarded as the composition of a graph-to-graphon convergence and a graphon-to-manifold convergence in a certain sense. Furthermore, we establish a monotonicity inequality which reveals an implicit relationship between numerous combinatorial parameters and geometric quantities on graphons. Using this inequality, we find relations among conductance, maxcut problem, capacity, and packing radius, as well as their limiting behaviors under graph-to-graphon and graphon-to-manifold convergences; some of these relations are novel even for simple graphs and closed manifolds. We also find that in the graphon-to-manifold limiting process, the purely combinatorial parameters diverge, leading to a ``blowup'' phenomenon; and continuous versions of some graph parameters cannot be realized via Riemannian manifolds, but can be realized via graphons.

math.CO↗

arXiv2026

On-Chip Shaping of Surface Acoustic Waves via Continuous Diffractive Modulation

Precise shaping of surface acoustic waves (SAWs) on anisotropic piezoelectric substrates is complicated by elastic anisotropy and electromechanical coupling. Here we introduce a continuous diffractive acoustic lens (CDAL), in which weak phase-velocity perturbations produced by subwavelength metallization, together with diffraction, drive lateral field redistribution. An anisotropic thin-element propagation model enables efficient inverse design of the CDAL contour. Laser Doppler vibrometry verifies prescribed lateral field profiles and multichannel beam splitting with unequal widths. By combining continuous diffractive modulation with discrete source-phase encoding, we further shape the lateral field into a Bessel profile, demonstrating joint amplitude-and-phase control. This work provides a high-precision and fabrication-compatible mechanism for on-chip SAW field modulation.

physics.class-ph↗

arXiv2026

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute. Prior to RL, we conduct mid-training on a broad multimodal corpus to provide ample exploration space, and build a solid infrastructure on the pretrained hybrid-SWA architecture to support subsequent scale-up. We scale RL compute along three dimensions: (1) larger batches and higher throughput, with an asynchronous training that consumes 1,568 samples and 2.7-3.7B tokens per step at context lengths of up to 1M; (2) more diverse and complex environments, spanning code, general, visual, and cyber domains under a mixture of agent harnesses; and (3) more grader compute, via groupwise agentic grading that yields more accurate reward signals for long-horizon tasks and steers the model towards shorter, more token-efficient solutions. To keep training stable at scale, we freeze the MoE router and establish a multi-layer defense against reward hacking. We further build infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency. We open-source the training dynamics, RL environments, and RL framework to facilitate reproduction and further research on scaled RL and model self-improvement.

cs.CL↗

arXiv2026

From Social Reasoning to Embodied Interaction: An Agentic Framework for Social Robots

Natural face-to-face human--robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent through coordinated physical behavior. Yet existing approaches rarely close this loop: foundation-model agents provide increasingly capable multimodal reasoning and memory but remain largely disembodied, while expressive virtual agents do not face the physical constraints of real robots, and physical social robots typically address social reasoning and embodied expression only partially. We present ARISE, a unified framework that bridges Agentic Reasoning and Interactive Social Embodiment on the Sophia humanoid robot. ARISE integrates multimodal context understanding, long-term memory, and reactive and proactive interaction to determine when and what to communicate, and translates social intent into robot-native gestures coordinated with speech and mechanical facial expressions through streaming execution. Extensive evaluations on Sophia demonstrate strong perceived interaction quality, expressive and well-coordinated embodied behavior, and substantial latency reductions through streaming execution. These results highlight the importance of jointly reasoning about what to communicate, when to engage, and how to physically express social intent for natural interaction with humanoid robots. Project Page: https://robosocial.github.io/

cs.RO↗

arXiv2026

When voltage sensors fail: Electrochemically constrained fault-tolerant state estimation for flat-plateau LFP batteries

The flat voltage plateau of lithium iron phosphate (LFP)/graphite cells makes electrochemical-state errors and voltage-measurement abnormalities produce similar innovations, complicating state-of-charge (SOC) estimation. This work proposes an electrochemically constrained residual-bias compensation dual extended Kalman filter (RBC-DEKF) with uncertain-initialization commissioning. A thermal control-oriented parameter-grouped single-particle model (CPG-SPMT) provides paired-electrode dynamics and terminal-voltage prediction, while a separately configurable voltage-discrepancy state accommodates systematic residuals. When the initial SOC is uncertain, residual adaptation is suspended over a verified-healthy startup window. Buffered data support electrochemically constrained trajectory matching, followed by calibrated state replay and residual-channel reactivation. Frozen cross-cycle healthy-residual calibration supports commissioning and remains in the voltage prediction after handover. Evaluation covers 216 additive-bias and 168 multiplicative-gain profiles over 24 A123 temperature-drive-cycle trajectories. Relative to Single-EKF, the original RBC-DEKF reduces mean SOC RMSE from 7.646 to 0.170 percentage points for additive bias and from 22.646 to 0.356 percentage points for gain faults. Separately, 18 nonzero-initial-error profiles on three representative 50%-SOC-anchored segments give a full-record mean SOC RMSE of 1.747 percentage points, including startup, for the commissioned realization, versus 11.192 and 11.400 for the always-on RBC-DEKF and conventional joint EKF. Representative delayed bias, 10-s ramp, and gain tests show that the corrected SOC trajectory remains stable after fault introduction. The central contribution is electrochemically constrained temporal coordination of uncertain-state recovery and subsequent voltage-discrepancy accommodation.

eess.SY↗

arXiv2026

Choquet-type extensions of set-pair functions, and applications in graph limits, hypergraphs, and metric measure spaces

We propose Choquet-type extensions for set-pair functions, an $L^p$-integration of a family of such extensions, and the associated min-max extension constants, and apply these to investigate variational problems and establish sharp bounds for many combinatorial and geometric quantities. Specifically, we use Choquet-type extensions to construct equivalent functional representations of fractional optimization problems with set-variables, which find applications in various settings, such as maxcut and bipartiteness ratio on graph limits, and Cheeger constants on Riemannian manifolds. We further establish the $L^p$ integration of a family of Choquet-type extensions, and apply it to derive spectral bounds for conductance and other combinatorial quantities on measure spaces. A monotonicity inequality on min-max extension constants is proposed, which unifies classical estimates and uncovers new bounds for many geometric and combinatorial quantities, such as torsional rigidity, Cheeger constants, Dirichlet $p$-isoperimetric constant, and $p$-Laplacian eigenvalues, in seemingly unrelated underlying structures----including hypergraphs, graph limits, Riemannian manifolds and metric measure spaces.

math.CO↗

arXiv2026

Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis

Exploring high-order correlations and long-range dependencies in brain networks holds significant value for both neuroscience research and clinical diagnosis. However, previous studies have lacked a unified integration of high-order and long-range dependency information in brain networks, and there is substantial redundancy behind various types of information. These issues limit their effectiveness in the diagnosis of brain diseases. To address this, we propose an Information Bottleneck-Guided Adaptive HyperGraph Transformer (IBAHGT). By incorporating the information bottleneck (IB) principle, this approach enables adaptive learning of high-order correlations and both short- and long-range dependencies within a unified framework for brain network analysis, achieving high-precision brain disease diagnosis. IBAHGT consists of three key components: an information bottleneck-guided adaptive hypergraph convolution, which introduces a novel hypergraph information bottleneck (HIB) principle to adaptively learn hypergraph message-passing weights between nodes and hyperedges, optimizes information flow and captures high-order information in brain networks that is maximally informative and minimally redundant (MIMR). The Transformer encoder captures global information within brain networks through the attention mechanism, specifically modeling short- and long-range dependencies. An information bottleneck-guided node-level adaptive fusion employs the IB principle to learn independent weights for each node, facilitating the fine-grained integration of high-order information and global information to obtain an efficient representation for downstream tasks. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art methods and can identify biomarkers for clinical applications.

cs.AI↗

arXiv2026

Nonlinear spectral graph theory

Nonlinear spectral graph theory is an extension of the traditional (linear) spectral graph theory and studies relationships between spectral properties of nonlinear operators defined on a graph and topological properties of the graph itself. Many of these relationships get tighter when going from the linear to the nonlinear case. In this manuscript, we discuss the spectral theory of the graph $p$-Laplacian operator. In particular we report links between the $p$-Laplacian spectrum and higher-order Cheeger (or isoperimetric) constants, sphere packing constants, independence and matching numbers of the graph. The main aim of this paper is to present a complete and self-contained introduction to the problem accompanied by a discussion of the main results and the proof of new results that fill some gaps in the theory. The majority of the new results are devoted to the study of the graph infinity Laplacian spectrum and the information that it yields about the packing radii, the independence numbers and the matching number of the graph. This is accompanied by a novel discussion about the nodal domains induced by the infinity eigenfunctions. There are also new results about the variational spectrum of the $p$-Laplacian, the regularity of the $p$-Laplacian spectrum varying $p$, and the relations between the $1$-Laplacian spectrum and new Cheeger constants.

math.SP↗

arXiv2026

Large-Scale Pretraining for Improving Deep Learning-Based Geometric Distortion Correction of Diffusion-Weighted Imaging

Diffusion-weighted imaging (DWI) is widely used in clinical settings but remains vulnerable to geometric distortion. Conventional correction methods often require additional acquisitions or vendor-specific solutions, limiting their feasibility in high-throughput, resource-constrained settings. This study investigates whether large-scale pretraining strategies can improve deep learning-based distortion correction for single-phase-encoding DWI. We formulate the task as image reconstruction, and compare a non-pretrained baseline against a self-supervised and a generative pretrained model, evaluated using both quantitative image-similarity metrics and qualitative expert assessment. The best-performing model was further tested for transferability on data collected in an LMIC setting with acquisition shift. Pretrained models outperformed the non-pretrained baseline, with cWDM achieving the strongest results across both quantitative and qualitative evaluation. However, application to LMIC data revealed transferability challenges, including contrast alteration and over-reliance on T1-weighted anatomical structure. Registering images to a common standard space improved predictions, suggesting that harmonized preprocessing may enhance cross-domain deployment.

cs.CV↗

arXiv2026

Relative Time Intervals Representation for Word-level Timestamping with Masked Training

Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses this gap by enabling SpeechLLMs to jointly model speech content and temporal structure, effectively transforming them from ``content understanding machines" into ``temporal-aware content understanding machines". Specifically, we replace traditional absolute timestamps with relative timestamps, achieving a more compact vocabulary and stronger generalization capabilities. To efficiently infuse timestamp prediction ability into pre-trained large language models, we introduce a hybrid fine-tuning strategy: full-parameter fine-tuning of the timestamp-augmented embedding layer and language model head, combined with LoRA fine-tuning of the decoder layers. Moreover, we design a masked timestamp training objective, preventing the model from over-relying on ground-truth timestamps, and thereby enhancing robustness against noisy real-world annotations. Extensive experiments demonstrate that our approach achieves significant improvements in timestamp prediction accuracy while maintaining strong speech transcription performance.

cs.AI↗

arXiv2026

Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding

While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Existing speech QA paradigms and state-of-the-art Speech LLMs suffer from acoustic information loss and poor long-term context memory. To address these issues, we construct the LongAudioQA dataset and propose the GRGA model, which models heterogeneous audio features into a multi-dimensional graph and leverages agent planning for retrieval and answer generation.

cs.SD↗

arXiv2026

BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling

Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-powered dialogue systems offer a scalable alternative, but existing models face two fundamental challenges. First, they lack the bidirectional understanding needed to capture the layered nature of emotional expression, particularly in cases of progressive disclosure, where clients often present symptoms at the surface-level while concealing deeper trauma. Autoregressive (AR) models process information sequentially and cannot revise early interpretations when new evidence emerges later in the conversation. Second, they fail to effectively incorporate the relational knowledge that underlies clinical reasoning. In this paper, we propose \textbf{BiGraph-Diffuse}, the first large-scale diffusion language model tailored for the counseling domain. We further introduce \textbf{BiGraph-RAG}, a relation-free graph-structured retrieval strategy that relies only on lightweight entity extraction and semantic linking. This design preserves inferential pathways from observable symptoms to potential underlying causes, while incurring zero LLM token cost during indexing. Importantly, these two modules are not merely combined but mutually reinforcing. The diffusion model provides a holistic bidirectional context, enabling the system to defer premature judgments during progressive disclosure. Meanwhile, graph-based retrieval captures the structured interconnections of clinical knowledge. Extensive experiments demonstrate the effectiveness of BiGraph-Diffuse, and we further provide a solid theoretical analysis to support its design.

cs.AI↗

arXiv2026

Congruence Decomposition with Neural Block Solvers for Large-Scale PCI Assignment

Physical Cell Identity (PCI) assignment is essential for interference management in dense 5G networks. As cellular networks scale, PCI reuse becomes unavoidable, which may cause collisions, confusions, and multiple forms of modular interference. Jointly mitigating these effects gives rise to a large-scale, multi-objective combinatorial optimization problem that is difficult to solve efficiently at practical network scales. In this work, we propose a congruence decomposition framework with neural block solvers for large-scale PCI assignment. The proposed decomposition exploits the arithmetic structure of PCI values to decouple multiple modular interference objectives into a collection of blockwise Min-$k$-Partition subproblems, followed by a graph coloring procedure to resolve PCI conflicts. For the resulting NP-hard Min-$k$-Partition subproblems, we develop neural block solvers by parameterizing their relaxed quadratic formulations with graph neural networks, enabling efficient optimization at large scales. Discrete assignments are recovered through conditional expectation rounding with theoretical guarantees. Experiments on synthetic cellular graphs and real-world 5G networks show that the proposed method consistently outperforms existing modular-interference-aware baselines in modular interference reduction, conflict elimination, and computational efficiency.

cs.LG↗