arXiv subjects

Yin Yang

Publications and source records attributed to Yin Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation

Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observation window, which renders long-horizon manipulation non-Markovian when the correct action depends on earlier events that are no longer visible. We present MemoryVAM, an episodic memory mechanism for video-world-model policies. We employ a Recap-Cue (RC) module, in which a Perceiver-based Recap Compressor maps per-frame CLIP embeddings into compact memory tokens, and a lightweight Cue Gate estimates task completion from memory and language. These tokens are injected into both the video backbone and the action decoder, aligning policy imagination with episode progress and conditioning actions on history. Our model trains the memory module with video prediction, a delta-reconstruction auxiliary loss, and episode-boundary supervision, requiring no per-frame progress labels. The same mechanism applies to UNet and Diffusion Transformer (DiT) backbones by changing only the cross-attention injection interface. On LIBERO-Mem, our model improves average success from 5% to 42.5%. On real robots, it achieves 78.3% success on counting tasks, 80.0% on spatial recall, and 75.0% on sequential tracking. Project page: https://MemoryVAM.github.io/

cs.RO↗

arXiv2026

TacCoRL: Integrating Tactile Feedback into VLA via Simulation

Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks. We present TacCoRL, a scalable framework that injects Tactile feedback into VLA policies and improves them through sim-real Co-training and simulation-based reinforcement learning (RL), without requiring large-scale tactile pretraining or extensive real-world contact exploration. The key idea is not only adding touch as an input, but learning how contact readings should modulate action responses in near-failure states that are rare in demonstrations and risky to collect on hardware. We use a real-aligned simulator as a closed-loop training environment for contact interaction. Mixed simulated and real trajectories first warm-start tactile-conditioned actions in the pretrained policy. Reinforcement learning with verifiable task rewards then optimizes the policy using simulated contact rollouts. It reinforces tactile-conditioned actions that lead to task completion, while a supervised objective on real trajectories keeps the refined policy anchored to deployment visual, tactile, and action distributions. The resulting policy transfers directly to the real robot without privileged simulation state or online real-world RL. Across four bimanual contact-rich tasks, the final visuo-tactile policy achieves an average success rate of 72.5%, compared to baseline of 50.0%. Result videos and more details are available at https://tac-corl.github.io/

cs.RO↗

arXiv2026

Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation

Explicit 3D representations are attractive for manipulation because they expose object shape, workspace geometry, and robot-object relations in metric coordinates. However, sparse 3D encoders are often learned through downstream task objectives, tying the representation to a particular data distribution, policy architecture, and action parameterization. We introduce Sparse2Act, an observation-action alignment framework for pretraining sparse point-cloud encoders. The key idea is to use task-space end-effector actions as geometric supervision: masked sparse 3D tokens are trained to organize scene features around the workspace motion paired with the observation. After pretraining, only the encoder initialization is reused by downstream policies, allowing them to retain their own architectures and action spaces, including joint-space commands. On the LIBERO-10 benchmark, our method achieves 86.9% average success after 500 fine-tuning steps. The same pretrained encoder supports LIBERO-to-Meta-World cross-domain transfer, achieving 73.4% average success on the Meta-World-5 benchmark. Ablations on the objective and decoder capacity show that the gains come from the masked action-alignment signal and remain useful across downstream action decoders. In real-world experiments, simulation pretraining followed by limited real-data fine-tuning achieves an average success rate of 72.5% across four tasks, demonstrating effective sim-to-real transfer. These results suggest that robot actions can provide compact geometric supervision for reusable sparse 3D representations.

cs.RO↗

arXiv2026

Adaptive multiscale model reduction for linear elasticity equation in perforated domains

In this paper, we develop a Constraint Energy Minimizing Generalized Multiscale Finite Element Method (CEM-GMsFEM) for solving linear elasticity problems in heterogeneous perforated domains. The presence of numerous perforations introduces multiple scales into the computational domain, making direct fine-grid simulations computationally expensive. The proposed method follows the standard offline--online decomposition of CEM-GMsFEM. In the offline stage, local spectral problems are solved on coarse elements to construct auxiliary spaces, and localized energy-minimizing basis functions are then computed on oversampled regions to capture fine-scale geometric information induced by the perforations. In the online stage, residual-driven basis functions are constructed in enlarged coarse neighborhoods to incorporate source-term information and improve the accuracy of the multiscale approximation adaptively. We establish convergence results for both the offline and online stages. In particular, we derive error estimates for the localized multiscale approximation and prove the convergence of the adaptive online enrichment algorithm. Moreover, we show that the oversampling regions used in the online stage can be determined locally, leading to a reduction in computational cost while maintaining convergence properties. Numerical experiments on perforated media with different geometric configurations demonstrate the accuracy and efficiency of the proposed method.

math.NA↗

arXiv2026

Fishbone: From One 3D Asset to a Million Controllable Edits

Large-scale controllable 3D assets are critical for computer graphics, embodied AI, robotics, and interactive content creation, yet creating diverse 3D assets remains challenging due to the high cost of manual modeling and rigging. Shape deformation offers a natural way to generate variations from existing meshes, but existing data-driven methods often rely on sparse user inputs, while parametric editing frameworks require manually designed control structures and category-specific configurations. Inspired by natural creatures, where a central spine governs global shape and cross-sectional ribs control local variation, we introduce Fishbone, a unified rib-spine representation for general shapes that supports controllable parametric mesh deformation, reduced-space dynamics, and animation. Given an input mesh, Fishbone computes a geodesic scalar field with an adaptive heat method, extracts iso-contours as cross-sectional ribs, constructs a smooth geometry-aware spine through rib centers, and associates surface vertices with nearby rib and spine structures using Gaussian-weighted skinning. The resulting representation enables real-time and predictable deformation: ribs control local profiles such as thickness, orientation, and cross-sectional variation, while the spine controls global bending, twisting, and stretching. The same structure also supports reduced-space simulation and keyframe animation. We further construct Fishbone-136K by augmenting Hunyuan3D with rib-spine structures, and demonstrate applications in controllable 3D generation, deformation-based data augmentation for robot learning, interactive mesh editing, and agentic generation. Experiments demonstrate the effectiveness, efficiency, and versatility of the proposed framework.

cs.CV↗

arXiv2026

WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer

A unified simulator that can model diverse physical phenomena without solver-specific redesign is a long-standing goal across simulation science. We present a learning-based particle simulator built on a single transformer architecture to model cloth, elastic solds, Newtonian and non-Newtonian fluids, granular materials, and molecular dynamics. Our model follows a prediction-correction design on a shared Lagrangian particle representation. An explicit predictor first advances particles under the known external forces, producing an intermediate state that captures externally driven motion but not inter-particle interactions. A learned corrector then predicts the residual position and velocity updates through three stages: a particle tokenizer that encodes local particle-particle, particle-boundary, and topology-guided interactions; a super-token encoder that hierarchically merges particle tokens into a compact set of super tokens via alternating self-attention and token merging; and a super-token decoder that lifts these super tokens back to particle resolution through cross-attention to predict per-particle position and velocity corrections. Progressive token merging reduces the attention cost at successive encoder layers by halving the token count at each level, and the decoder communicates through the compact super-token set rather than full particle-to-particle attention. Across the six dynamics categories, the same architecture generalizes to unseen materials, boundary configurations, initial conditions, and external forces. We further demonstrate downstream interactive control, inverse design, and learning from real-world manipulation data, reducing the need for per-phenomenon solver engineering.

cs.GR↗

arXiv2026

DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes

Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage assessment and response. While Visual Question Answering (VQA) has shown strong performance in general-purpose domains, its suitability for the complex and safety-critical reasoning required in disaster response remains unclear. We introduce DisasterVQA, a benchmark dataset designed for perception and reasoning in crisis contexts. DisasterVQA consists of 1,395 real-world images and 4,405 expert-curated question-answer pairs spanning diverse events such as floods, wildfires, and earthquakes. Grounded in humanitarian frameworks including FEMA ESF and OCHA MIRA, the dataset includes binary, multiple-choice, and open-ended questions covering situational awareness and operational decision-making tasks. We benchmark seven state-of-the-art vision-language models and find performance variability across question types, disaster categories, regions, and humanitarian tasks. Although models achieve high accuracy on binary questions, they struggle with fine-grained quantitative reasoning, object counting, and context-sensitive interpretation, particularly for underrepresented disaster scenarios. DisasterVQA provides a challenging and practical benchmark to guide the development of more robust and operationally meaningful vision-language models for disaster response. The dataset is publicly available at https://doi.org/10.5281/zenodo.18267769.

cs.CV↗

arXiv2026

Distributed Affine Body Dynamics with Adaptive Consensus

Affine Body Dynamics (ABD) within the Incremental Potential Contact (IPC) framework provides accurate simulation of extremely stiff solids exhibiting near-rigid behavior, with strict non-penetration guarantees. However, IPC's globally coupled barrier constraints hinder scalable execution across multiple GPUs and compute nodes. We propose a distributed formulation of ABD using a consensus-based ADMM scheme. Each compute node solves its local ABD subproblem in parallel, followed by a global consensus step that enforces consistency among shared boundary bodies. The proposed method preserves IPC-level robustness and global consistency under distributed execution. Experiments demonstrate stable convergence, non-penetration, and efficient scaling on large-scale scenes across multiple nodes.

cs.GR↗

arXiv2026

Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes

We introduce S2C-3D, a novel sparse-view 3D reconstruction framework for high-fidelity and complete scene reconstruction from as few as six to eight images. Our framework features three components: a specialized diffusion model for scene-specific image restoration, a training-free view-consistency conditioned sampling process in the diffusion model for refined Gaussian optimization, and a camera trajectory planning scheme to ensure comprehensive scene coverage. The specialized diffusion model is developed by finetuning a pretrained architecture on the input views and their corresponding degraded counterparts. The adaptation to the scene distribution allows the model to repair Gaussian renderings while effectively eliminating domain gaps. Meanwhile, the trajectory planning scheme optimizes scene coverage by connecting each newly sampled camera to its two nearest neighbors. By iteratively constructing paths and retaining only those that significantly enhance visibility, the scheme establishes a trajectory that covers the entire scene. To address multi-view conflicts, the view-consistency conditioned sampling process quantifies the consistency between neighboring repaired images. This information is injected as a condition into the sampling process of the frozen diffusion model, facilitating the generation of view-consistent images without additional training. Consequently, our approach produces high-fidelity 3D Gaussians that are robust to artifacts. Experimental results demonstrate that S2C-3D outperforms state-of-the-art methods, constructing high-quality scenes that are free from missing regions, blurring, or other artifacts with very sparse inputs. The source code and data are available at https://gapszju.github.io/S2C-3D.

cs.CV↗

arXiv2026

Efficient B-Spline Finite Elements for Cloth Simulation

We present an efficient B-spline finite element method (FEM) for cloth simulation. While higher-order FEM has long promised higher accuracy, its adoption in cloth simulators has been limited by its larger computational costs while generating results with similar visual quality. Our contribution is a full algorithmic pipeline that makes cloth simulation using quadratic B-spline surfaces faster than standard linear FEM in practice while consistently improving accuracy and visual fidelity. Using quadratic B-spline basis functions, we obtain a globally $C^1$-continuous displacement field that supports consistent discretization of both membrane and bending energies, effectively reducing locking artifacts and mesh dependence common to linear elements. To close the performance gap, we introduce a reduced integration scheme that separately optimizes quadrature rules for membrane and bending energies, an accelerated Hessian assembly procedure tailored to the spline structure, and an optimized linear solver based on partial factorization. Together, these optimizations make high-order, smooth cloth simulation competitive at scale, yielding an average $2\times$ speedup over linear FEM in our tests. Extensive experiments demonstrate improved accuracy, wrinkle detail, and robustness, including contact-rich scenarios, relative to linear FEM and recent higher-order approaches. Our method enables realistic wrinkling dynamics across a wide range of material parameters and supports practical garment animation, providing a new promising spatial discretization for high-quality cloth simulation.

cs.GR↗

arXiv2026

Penetration-free Solid-Fluid Interaction on Shells and Rods

We introduce a novel approach to simulate the interaction between fluids and thin elastic solids without any penetration. Our approach is centered around an optimization system augmented with barriers, which aims to find a configuration that ensures the absence of penetration while enforcing incompressibility for the fluids and minimizing elastic potentials for the solids. Unlike previous methods that primarily focus on velocity coherence at the fluid-solid interfaces, we demonstrate the effectiveness and flexibility of explicitly resolving positional constraints, including both explicit representation of solid positions and the implicit representation of fluid level-set interface. To preserve the volume of the fluid, we propose a simple yet efficient approach that adjusts the associated level-set values. Additionally, we develop a distance metric capable of measuring the separation between an implicitly represented surface and a Lagrangian object of arbitrary codimension. By integrating the inertia, solid elastic potential, damping, barrier potential, and fluid incompressibility within a unified system, we are able to robustly simulate a wide range of processes involving fluid interactions with lower-dimensional objects such as shells and rods. These processes include topology changes, bouncing, splashing, sliding, rolling, floating, and more.

cs.GR↗

arXiv2026

Unconditional energy stable hybrid IEQ-FEMs for the Cahn-Hilliard-Navier-Stokes equations

We investigate two unconditionally energy stable invariant energy quadratization (IEQ) finite element methods (FEMs) [Chen et al. Numerical Algorithms, DOI: 10.1007/s11075-024-01910-z, 2024] for solving the Cahn-Hilliard-Navier-Stokes (CHNS) equations. The time discretization of these IEQ-FEMs is based on the first- and second-order backward differentiation methods. \textcolor{black}{The auxiliary energy function introduced by the IEQ approach, modeling the square root of the nonlinear part of the energy, does not belong to the finite element space used for the spatial discretization.} These methods offer distinct advantages. Consequently, we propose a new hybrid IEQ-FEM that combines the strengths of both schemes, offering computational efficiency and unconditional energy stability in the finite element space. We provide rigorous proofs of mass conservation and energy dissipation for the proposed IEQ-FEMs. Several numerical experiments are presented to validate the accuracy, efficiency, and solution properties of the proposed method.

math.NA↗

arXiv2026

An Efficient Multilevel Preconditioned Nonlinear Conjugate Gradient Method for Incremental Potential Contact

Incremental Potential Contact (IPC) guarantees intersection-free simulation but suffers from high computational costs due to the expensive Hessian assembly and linear solves required by Newton's method. While Preconditioned Nonlinear Conjugate Gradient (PNCG) avoids Hessian assembly, it has historically struggled with poor convergence in stiff, contact-rich scenarios due to the lack of effective preconditioners; simple Jacobi preconditioners fail to capture the global coupling, while advanced hierarchy-based preconditioners like Multilevel Additive Schwarz (MAS) are computationally prohibitive to rebuild at every nonlinear iteration. We present MAS-PNCG, a method that unlocks the power of hierarchical preconditioning for nonlinear optimization. Our key technical innovation is a Sparse-Input Woodbury update algorithm that incrementally adapts the fine-level MAS components to rapidly evolving contact sets. This bypasses the need for full preconditioner rebuilds, reducing maintenance cost to near-zero while capturing the complex spectral properties of the contact system. Furthermore, we replace heuristic PNCG search directions with a Hessian-aware 2D subspace minimization that optimally combines the preconditioned gradient and previous direction. We also apply a fast per-subdomain conservative CCD method that ensures penetration-free trajectories while avoiding overly restrictive global step sizes. Experiments demonstrate that our MAS-PNCG outperforms state-of-the-art Newton-PCG solvers, GIPC and StiffGIPC, both preconditioned with MAS up to 5.66$\times$ and 2.07$\times$ respectively.

cs.GR↗

arXiv2026

Schrödingerization for quantum linear systems problems with near-optimal dependence on matrix queries

We develop a quantum algorithm for linear algebraic equations $ A\bb{x} = \bb{b} $ from the perspective of Schrödingerization-form problems, which are characterized by a system of linear convection equations in one higher dimension. When $ A $ is positive definite, the solution $ \bb{x} $ can be interpreted as the steady-state solution to a system of linear ordinary differential equations (ODEs). This ODE system can be solved by using the linear combination of Hamiltonian simulation (LCHS) method in \cite{ACL2023LCH2}, which serves as the continuous implementation of the Fourier transform in the Schrödingerization method from \cite{JLY22SchrShort, JLY22SchrLong}. Schrödingerization transforms linear partial differential equations (PDEs) and ODEs with non-unitary dynamics into Schrödinger-type systems via the so-called warped phase transformation that maps the equation into one higher dimension. When $ A $ is a general Hermitian matrix, the inverse matrix can still be represented in the LCHS form in \cite{ACL2023LCH2}, but with a kernel function based on the Fourier approach in \cite{Childs2017QLSA}. Although this LCHS form provides the steady-state solution to a system of linear ODEs associated with the least-squares equation, applying Schrödingerization to this least-squares system is not appropriate, as it results in a much larger condition number. We demonstrate that in both cases, the solution $ \bb{x} $ can be expressed as the LCHS of Schrödingerization-form problems. We provide a detailed implementation and error analysis. Furthermore, we incorporate a block preconditioning technique to achieve nearly linear scaling in the condition number, thereby attaining near-optimal query complexity.

quant-ph↗

arXiv2026

Learn2Fold: Structured Origami Generation with World Model Planning

The ability to transform a flat sheet into a complex three-dimensional structure is a fundamental test of physical intelligence. Unlike cloth manipulation, origami is governed by strict geometric axioms and hard kinematic constraints, where a single invalid crease or collision can invalidate the entire folding sequence. As a result, origami demands long-horizon constructive reasoning that jointly satisfies precise physical laws and high-level semantic intent. Existing approaches fall into two disjoint paradigms: optimization-based methods enforce physical validity but require dense, precisely specified inputs, making them unsuitable for sparse natural language descriptions, while generative foundation models excel at semantic and perceptual synthesis yet fail to produce long-horizon, physics-consistent folding processes. Consequently, generating valid origami folding sequences directly from text remains an open challenge. To address this gap, we introduce Learn2Fold, a neuro-symbolic framework that formulates origami folding as conditional program induction over a crease-pattern graph. Our key insight is to decouple semantic proposal from physical verification. A large language model generates candidate folding programs from abstract text prompts, while a learned graph-structured world model serves as a differentiable surrogate simulator that predicts physical feasibility and failure modes before execution. Integrated within a lookahead planning loop, Learn2Fold enables robust generation of physically valid folding sequences for complex and out-of-distribution patterns, demonstrating that effective spatial intelligence arises from the synergy between symbolic reasoning and grounded physical simulation.

cs.GR↗

arXiv2026

Quantum algorithms for the fractional Poisson equation via rational approximation

This paper presents a quantum algorithm for solving the fractional Poisson equation $(-Δ)^s u = f$ with $s \in (0,1)$ on bounded domains. The proposed approach combines rational approximation techniques with quantum linear system solvers to achieve exponential quantum advantage. The rational approximation represents the inverse fractional Laplacian as a weighted sum of standard resolvents, transforming the original nonlocal problem into a collection of shifted integer-order partial differential equations. These equations are consolidated into a single large linear system through a modified right-hand side construction that simplifies the quantum implementation. To enable practical implementation, we develop explicit quantum circuits via the Schrödingerization technique, which converts the non-unitary dynamics of the linear system into a higher-dimensional Schrödinger-type equation, allowing the use of standard Hamiltonian simulation. The circuit construction leverages the decomposition of shift operators to realize the discrete Laplacian and employs controlled operations to implement the select oracle. Under finite difference discretization, we provide detailed algorithmic procedures utilizing block-encoding techniques for the coefficient matrices. A comprehensive complexity analysis demonstrates that the quantum algorithm achieves a dependence on the inverse mesh size $h^{-1}$ that is independent of the spatial dimension $d$, in stark contrast to classical methods which suffer from exponential growth in high dimensions. This establishes an exponential quantum advantage for high-dimensional fractional problems, effectively overcoming the curse of dimensionality that limits classical approaches.

quant-ph↗

arXiv2026

A fully decoupled and structure-preserving relaxation Crank--Nicolson finite element method for Gross--Pitaevskii--Poisson model

We propose a fully decoupled, structure-preserving relaxation Crank--Nicolson finite element method (FEM) for the coupled Gross--Pitaevskii--Poisson (GPP) system modeling ultracold plasmas. By introducing suitable auxiliary variables to reformulate the nonlinear interaction and charge density terms, the original system is recast into an equivalent form that enables a linear, fully decoupled numerical scheme. The proposed method preserves key physical invariants, including the mass of each component and a modified discrete energy, at the fully discrete level. We establish the well-posedness and uniqueness of the scheme and rigorously derive optimal error estimates, achieving second-order accuracy in time and optimal $(k+1)$-th order convergence in space for $P^k$ finite element approximations. Numerical experiments confirm the theoretical results and demonstrate the effectiveness of the method in preserving conservation properties and accurately capturing complex dynamical behaviors of the coupled GPP system.

math.NA↗

arXiv2026

VoroLight: Learning Voronoi Surface Meshes via Sphere Intersection

Voronoi diagrams naturally produce convex, watertight, and topologically consistent cells, making them an appealing representation for 3D shape reconstruction. However, standard differentiable Voronoi approaches typically optimize generator positions in stable configurations, which can lead to locally uneven surface geometry. We present VoroLight, a differentiable framework that promotes controlled Voronoi degeneracy for smooth surface reconstruction. Instead of optimizing generator positions alone, VoroLight associates each Voronoi surface vertex with a trainable sphere and introduces a sphere--intersection loss that encourages higher-order equidistance among face-incident generators. This formulation improves surface regularity while preserving intrinsic Voronoi properties such as watertightness and convexity. Because losses are defined directly on surface vertices, VoroLight supports multimodal shape supervision from implicit fields, point clouds, meshes, and multi--view images. By introducing additional interior generators optimized under a centroidal Voronoi tessellation objective, the framework naturally extends to volumetric Voronoi meshes with consistent surface--interior topology. Across diverse input modalities, VoroLight achieves competitive reconstruction fidelity while producing smoother and more geometrically regular Voronoi surfaces. Project page: https://jiayinlu19960224.github.io/vorolight/

cs.CG↗