Searcharxiv⌕ Search

arXiv subjects

Rui Gao

Publications and source records attributed to Rui Gao.

At least 37 records · Page 2Linked to original sources
arXiv2026

Morphology-Independent Facial Expression Imitation for Human-Face Robots

Accurate facial expression imitation on human-face robots is crucial for achieving natural human-robot interaction. Most existing methods have achieved photorealistic expression imitation through mapping 2D facial landmarks to a robot's actuator commands. Their imitation of landmark trajectories is susceptible to interference from facial morphology, which would lead to a performance drop. In this paper, we propose a morphology-independent expression imitation method that decouples expressions from facial morphology to eliminate morphological influence and produce more realistic expressions for human-face robots. Specifically, we construct an expression decoupling module to learn expression semantics by disentangling the expression representation from the morphology representation in a self-supervised manner. We devise an expression transfer module to map the representations to the robot's actuator commands through a learning objective of perceiving expression errors, producing accurate facial expressions based on the learned expression semantics. To support experimental validation, a custom-designed and highly expressive human-face robot, namely Pengrui, is developed to serve as an experimental platform for realistic expression imitation. Extensive experiments demonstrate that our method enables the human-face robot to reproduce a wide range of human-like expressions effectively. All code and implementation details of the robot will be released.

cs.RO↗
arXiv2026

Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction

Achieving natural dyadic interaction requires generating facial expressions that are emotionally appropriate and socially aligned with human preference. Human feedback offers a compelling mechanism to guide such alignment, yet how to effectively incorporate this feedback into facial expression generation remains underexplored. In this paper, we propose a facial expression generation method aligned with human preference by leveraging human feedback to produce contextually and emotionally appropriate expressions for natural dyadic interaction. A key to our method is framing the generation of identity-independent facial expressions as an action learning process, allowing human feedback to assess their validity free from visual or identity bias. We establish a closed feedback loop in which listener expressions dynamically respond to evolving conversational cues of the speaker. Concretely, we train a vision-language-action model via supervised fine-tuning to map the speaker's multimodal signals into controllable low-dimensional expression representations of a 3D morphable model. We further introduce a human-feedback reinforcement learning strategy that integrates the imitation of high-quality expression response with critic-guided optimization. Experiments on two benchmarks demonstrate that our method effectively aligns facial expressions with human preference and achieves superior performance.

cs.CV↗
arXiv2026

Wasserstein Proximal Policy Gradient

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal update, we derive Wasserstein Proximal Policy Gradient (WPPG) via an operator-splitting scheme that alternates an optimal transport update with a heat step implemented by Gaussian convolution. This formulation avoids evaluating the policy's log density or its gradient, making the method directly applicable to expressive implicit stochastic policies specified as pushforward maps. We establish a global linear convergence rate for WPPG, covering both exact policy evaluation and actor-critic implementations with controlled approximation error. Empirically, WPPG is simple to implement and attains competitive performance on standard continuous-control benchmarks.

cs.LG↗
arXiv2026

LLM-Driven Scenario-Aware Planning for Autonomous Driving

Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic. Existing HPSF methods often fail to make reliable mode transitions or sustain efficient driving in congested environments, owing to heuristic scene recognition and low-frequency control updates. To address the limitation, this paper proposes LAP, a large language model (LLM) driven, adaptive planning method, which switches between high-speed driving in low-complexity scenes and precise driving in high-complexity scenes, enabling high qualities of trajectory generation through confined gaps. This is achieved by leveraging LLM for scene understanding and integrating its inference into the joint optimization of mode configuration and motion planning. The joint optimization is solved using tree-search model predictive control and alternating minimization. We implement LAP by Python in Robot Operating System (ROS). High-fidelity simulation results show that the proposed LAP outperforms other benchmarks in terms of both driving time and success rate.

cs.RO↗
arXiv2026

Parallel mean curvature surfaces with constant contact angle along free boundaries

We classify branched immersed disks in space forms with non-zero parallel mean curvature vector and non-orthogonal constant contact angle along the boundary in 4-dimensional space form. For higher codimensional case, we prove a codimension reduction theorem for branched immersed bordered Riemann surfaces of higher genus with multiple boundary components under the same parallel mean curvature and constant contact angle assumptions. Furthermore, we construct a family of explicit examples of branched minimal immersions satisfying the non-orthonormal constant contact angle free boundary condition, which demonstrate the sharpness of both the classification result and the codimension reduction result.

math.DG↗
arXiv2026

A Mesh-Adaptive Hypergraph Neural Network for Unsteady Flow Around Oscillating and Rotating Structures

Graph neural networks, recently introduced into the field of fluid flow surrogate modeling, have been successfully applied to model the temporal evolution of various fluid flow systems. Existing applications, however, are mostly restricted to cases where the domain is time-invariant. The present work extends the application of graph neural network-based modeling to fluid flow around structures rotating with respect to a certain axis. Specifically, we propose to apply a graph neural network-based surrogate model with part of the mesh/graph co-rotating with the structure and part of the mesh/graph static. A single layer of interface cells are constructed at the interface between the two parts and are allowed to distort and adapt, which helps in circumventing the difficulty of interpolating information encoded by the neural network at every graph neural network layer. Dedicated reconstruction and re-projection schemes are designed to counter the error caused by the distortion and connectivity change of the interface cells. The effectiveness of our proposed framework is examined on two test cases: (i) fluid flow around a 2D oscillating airfoil, and (ii) fluid flow past a 3D rotating cube. Our results show that the model achieves stable rollout predictions over hundreds or even a thousand time steps. We further demonstrate that one could enforce accurate, error-bounded prediction results by incorporating the measurements from sparse pressure sensors. In addition to the accurate flow field predictions, the lift and drag force predictions closely match with the computational fluid dynamics calculations, highlighting the potential of the framework for modeling fluid flow around rotating structures, and paving the path towards a graph neural network-based surrogate model for more complex scenarios like flow around marine propellers.

physics.flu-dyn↗
arXiv2026

DeepHalo: A Neural Choice Model with Controllable Context Effects

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself -- a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

cs.LG↗
arXiv2025

Sigma-MoE-Tiny Technical Report

Mixture-of-Experts (MoE) has emerged as a promising paradigm for foundation models due to its efficient and powerful scalability. In this work, we present Sigma-MoE-Tiny, an MoE language model that achieves the highest sparsity compared to existing open-source models. Sigma-MoE-Tiny employs fine-grained expert segmentation with up to 96 experts per layer, while activating only one expert for each token, resulting in 20B total parameters with just 0.5B activated. The major challenge introduced by such extreme sparsity lies in expert load balancing. We find that the widely-used load balancing loss tends to become ineffective in the lower layers under this setting. To address this issue, we propose a progressive sparsification schedule aiming to balance expert utilization and training stability. Sigma-MoE-Tiny is pre-trained on a diverse and high-quality corpus, followed by post-training to further unlock its capabilities. The entire training process remains remarkably stable, with no occurrence of irrecoverable loss spikes. Comprehensive evaluations reveal that, despite activating only 0.5B parameters, Sigma-MoE-Tiny achieves top-tier performance among counterparts of comparable or significantly larger scale. In addition, we provide an in-depth discussion of load balancing in highly sparse MoE models, offering insights for advancing sparsity in future MoE architectures. Project page: https://qghuxmu.github.io/Sigma-MoE-Tiny Code: https://github.com/microsoft/ltp-megatron-lm

cs.CL↗
arXiv2025

Long-Horizon Visual Imitation Learning via Plan and Code Reflection

Learning from long-horizon demonstrations with complex action sequences presents significant challenges for visual imitation learning, particularly in understanding temporal relationships of actions and spatial relationships between objects. In this paper, we propose a new agent framework that incorporates two dedicated reflection modules to enhance both plan and code generation. The plan generation module produces an initial action sequence, which is then verified by the plan reflection module to ensure temporal coherence and spatial alignment with the demonstration video. The code generation module translates the plan into executable code, while the code reflection module verifies and refines the generated code to ensure correctness and consistency with the generated plan. These two reflection modules jointly enable the agent to detect and correct errors in both the plan generation and code generation, improving performance in tasks with intricate temporal and spatial dependencies. To support systematic evaluation, we introduce LongVILBench, a benchmark comprising 300 human demonstrations with action sequences of up to 18 steps. LongVILBench emphasizes temporal and spatial complexity across multiple task types. Experimental results demonstrate that existing methods perform poorly on this benchmark, whereas our new framework establishes a strong baseline for long-horizon visual imitation learning.

cs.RO↗
arXiv2025

SIGMA: An AI-Empowered Training Stack on Early-Life Hardware

An increasing variety of AI accelerators is being considered for large-scale training. However, enabling large-scale training on early-life AI accelerators faces three core challenges: frequent system disruptions and undefined failure modes that undermine reliability; numerical errors and training instabilities that threaten correctness and convergence; and the complexity of parallelism optimization combined with unpredictable local noise that degrades efficiency. To address these challenges, SIGMA is an open-source training stack designed to improve the reliability, stability, and efficiency of large-scale distributed training on early-life AI hardware. The core of this initiative is the LUCIA TRAINING PLATFORM (LTP), the system optimized for clusters with early-life AI accelerators. Since its launch in March 2025, LTP has significantly enhanced training reliability and operational productivity. Over the past five months, it has achieved an impressive 94.45% effective cluster accelerator utilization, while also substantially reducing node recycling and job-recovery times. Building on the foundation of LTP, the LUCIA TRAINING FRAMEWORK (LTF) successfully trained SIGMA-MOE, a 200B MoE model, using 2,048 AI accelerators. This effort delivered remarkable stability and efficiency outcomes, achieving 21.08% MFU, state-of-the-art downstream accuracy, and encountering only one stability incident over a 75-day period. Together, these advances establish SIGMA, which not only tackles the critical challenges of large-scale training but also establishes a new benchmark for AI infrastructure and platform innovation, offering a robust, cost-effective alternative to prevailing established accelerator stacks and significantly advancing AI capabilities and scalability. The source code of SIGMA is available at https://github.com/microsoft/LuciaTrainingPlatform.

cs.DC↗
arXiv2025

An Efficient and Accurate Surrogate Modeling of Flapping Dynamics in Inverted Elastic Foils using Hypergraph Neural Networks

Cantilevered elastic foils can undergo self-induced, large-amplitude flapping when subject to fluid flow, a widely observed phenomenon of fluid-structure interaction, from fluttering leaves or the movement of fish fins. When harnessed in steady currents, these oscillations enable the extraction of kinetic energy from the flow. However, accurately predicting these dynamics requires high-fidelity simulations that are prohibitively expensive to perform across the broad configuration space needed for design optimization. To address this, we develop a novel graph neural network (GNN) surrogate for the inverted foil problem, modeled as an elastically mounted rigid foil undergoing trailing-edge pitching in uniform flow. The coupled fluid-structure dynamics are solved using a Petrov-Galerkin finite element method with an arbitrary Lagrangian-Eulerian formulation, providing high-fidelity data for training and validation. The surrogate uses a rotation-equivariant, quasi-monolithic GNN architecture: structural mesh motion is compressed via proper orthogonal decomposition and advanced through a multilayer perceptron. At the same time, the GNN evolves the flow field consistent with system states. Specifically, this study extends the hypergraph framework to flexible, self-oscillating foils, capturing the nonlinear coupling between vortex dynamics and structural motion. The GNN surrogate achieves less than 1.5% error in predicting tip displacement and force coefficients over thousands of time steps, while accurately reproducing dominant vortex-shedding frequencies. The model captures energy transfer metrics within 3% of full-order simulations, demonstrating both accuracy and long-term stability. These results show a new, efficient surrogate for long-horizon prediction of unsteady flow-structure dynamics in energy-harvesting systems.

physics.flu-dyn↗
arXiv2025

On the Metric Dimension of Generalized Petersen Graphs $P(n,3)$

The metric dimension of a graph $G$ is defined as the minimum number of vertices in a subset $S\subset V(G)$ such that all other vertices are uniquely determined by their distances to the vertices in $S$, and is denoted by $\dim(G)$. In this paper, we study the metric dimension of generalized Petersen graphs $P(n,3)$. The notions of good and bad vertices, which are introduced in Imran et al. (2014, Ars. Combinatoria 117, 113-130), are instrumental in determining the lower bound of the metric dimension for certain types of graphs. We propose an approach, based on these notions, to determine the lower bound of $\dim(P(n,3))$. Moreover, we shall prove that $\dim(P(n,3))=4$, where $n\equiv2,3,4,5 \,\,(\text{mod}\,\, 6)$ and is sufficiently large.

math.CO↗
arXiv2025

Predicting Flow-Induced Vibration in Isolated and Tandem Cylinders Using Hypergraph Neural Networks

We present a finite element-inspired hypergraph neural network framework for predicting flow-induced vibrations in freely oscillating cylinders. The surrogate architecture transforms unstructured computational meshes into node-element hypergraphs that encode higher-order spatial relationships through element-based connectivity, preserving the geometric and topological structure of the underlying finite-element discretization. The temporal evolution of the fluid-structure interaction is modeled via a modular partitioned architecture: a complex-valued, proper orthogonal decomposition-based sub-network predicts mesh deformation using a low-rank representation of Arbitrary Lagrangian-Eulerian (ALE) grid displacements, while a hypergraph-based message-passing network predicts the unsteady flow field using geometry-aware node, element, and hybrid edge features. High-fidelity ALE-based simulations provide training and evaluation data across a range of Reynolds numbers and reduced velocities for isolated and tandem cylinder configurations. The framework demonstrates stable roll-outs and accurately captures the nonlinear variation of oscillation amplitudes with respect to reduced velocity, a key challenge in surrogate modeling of flow-induced vibrations. In the tandem configuration, the model successfully resolves complex wake-body interactions and multi-scale coupling effects, enabling accurate prediction of pressure and velocity fields under strong wake interference conditions. Our results show high fidelity in reproducing force statistics, dominant frequencies, and flow-field dynamics, supporting the framework's potential as a robust surrogate model for digital twin applications.

physics.flu-dyn↗
arXiv2025

Automatic Depression Assessment using Machine Learning: A Comprehensive Survey

Depression is a common mental illness across current human society. Traditional depression assessment relying on inventories and interviews with psychologists frequently suffer from subjective diagnosis results, slow and expensive diagnosis process as well as lack of human resources. Since there is a solid evidence that depression is reflected by various human internal brain activities and external expressive behaviours, early traditional machine learning (ML) and advanced deep learning (DL) models have been widely explored for human behaviour-based automatic depression assessment (ADA) since 2012. However, recent ADA surveys typically only focus on a limited number of human behaviour modalities. Despite being used as a theoretical basis for developing ADA approaches, existing ADA surveys lack a comprehensive review and summary of multi-modal depression-related human behaviours. To bridge this gap, this paper specifically summarises depression-related human behaviours across a range of modalities (e.g. the human brain, verbal language and non-verbal audio/facial/body behaviours). We focus on conducting an up-to-date and comprehensive survey of ML-based ADA approaches for learning depression cues from these behaviours as well as discussing and comparing their distinctive features and limitations. In addition, we also review existing ADA competitions and datasets, identify and discuss the main challenges and opportunities to provide further research directions for future ADA researchers.

q-bio.NC↗
arXiv2025

Sinkhorn Distributionally Robust Optimization

We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, we provide numerical examples using synthetic and real data to demonstrate its superior performance.

math.OC↗
arXiv2025

The Timepix4 Beam Telescope

The spatial and temporal performance of a telescope system comprising planar silicon sensors bump-bonded to Timepix4-v2 ASICs are assessed at the CERN SPS using a $180$~GeV/$c$ mixed hadron beam. The pointing resolution at the centre of the telescope is $2.3 \pm 0.1\;\mathrm{μm}$ and $2.4 \pm 0.1\mathrm{μm}$ in x and y directions, respectively. The temporal resolution for the combined timestamps on a track using only the information from the Timepix4 planes is found to be $92 \pm 5$~ps. The telescope is extensively described including its data acquisition system and dedicated software as well as the corrections applied to the raw measurements.

hep-ex↗
arXiv2025

FetalFlex: Anatomy-Guided Diffusion Model for Flexible Control on Fetal Ultrasound Image Synthesis

Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies. However, obtaining a comprehensive, multi-plane annotated fetal US dataset remains challenging, particularly for rare or complex anomalies owing to their low incidence and numerous subtypes. This poses difficulties in training novice radiologists and developing robust AI models, especially for detecting abnormal fetuses. In this study, we introduce a Flexible Fetal US image generation framework (FetalFlex) to address these challenges, which leverages anatomical structures and multimodal information to enable controllable synthesis of fetal US images across diverse planes. Specifically, FetalFlex incorporates a pre-alignment module to enhance controllability and introduces a repaint strategy to ensure consistent texture and appearance. Moreover, a two-stage adaptive sampling strategy is developed to progressively refine image quality from coarse to fine levels. We believe that FetalFlex is the first method capable of generating both in-distribution normal and out-of-distribution abnormal fetal US images, without requiring any abnormal data. Experiments on multi-center datasets demonstrate that FetalFlex achieved state-of-the-art performance across multiple image quality metrics. A reader study further confirms the close alignment of the generated results with expert visual assessments. Furthermore, synthetic images by FetalFlex significantly improve the performance of six typical deep models in downstream classification and anomaly detection tasks. Lastly, FetalFlex's anatomy-level controllable generation offers a unique advantage for anomaly simulation and creating paired or counterfactual data at the pixel level. The demo is available at: https://dyf1023.github.io/FetalFlex/.

eess.IV↗