arXiv subjects

Rui Ma

Publications and source records attributed to Rui Ma.

At least 55 records · Page 3Linked to original sources

arXiv2025

PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during training, limiting their ability to adapt to novel structural patterns and sensor-induced distortions at test time. To address this limitation, we propose PointMAC, a meta-learned framework for robust test-time adaptation in point cloud completion. It enables sample-specific refinement without requiring additional supervision. Our method optimizes the completion model under two self-supervised auxiliary objectives that simulate structural and sensor-level incompleteness. A meta-auxiliary learning strategy based on Model-Agnostic Meta-Learning (MAML) ensures that adaptation driven by auxiliary objectives is consistently aligned with the primary completion task. During inference, we adapt the shared encoder on-the-fly by optimizing auxiliary losses, with the decoder kept fixed. To further stabilize adaptation, we introduce Adaptive $λ$-Calibration, a meta-learned mechanism for balancing gradients between primary and auxiliary objectives. Extensive experiments on synthetic, simulated, and real-world datasets demonstrate that PointMAC achieves state-of-the-art results by refining each sample individually to produce high-quality completions. To the best of our knowledge, this is the first work to apply meta-auxiliary test-time adaptation to point cloud completion.

cs.CV↗

arXiv2025

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model accuracy. Conventional LLM inference platforms (e.g GPUs) cannot capitalize on its benefits, as they (i) lack native support for ternary arithmetic and memory specialization and (ii) remain severely under-utilized in low-batch, real-time scenarios. In this work, we propose TENET, a sparse-aware LUT-centric architecture that co-optimizes algorithm, compute, and memory for ternary LLM inference. To maximize the efficiency of Ternary Linear layer, TENET introduces a Sparse Ternary LUT (STL) core that optimizes ternary mixed-precision GEMM using a symmetric precompute lookup table. It also features Dynamic Activation N:M Sparsity to exploit the sparsity within the activation of each token. Additionally, we propose a LUT-based 64B:80B ternary weight decompression module to fully exploit the memory efficiency of ternary values. At the system level, we design a heterogeneous TENET accelerator with full programmability that integrates STL cores with high-precision cores. An associated Linear-Projection-aware Sparse Attention dataflow is introduced to optimize memory access and hardware utilization. We implement TENET accelerator prototype on both FPGA and ASIC platforms. Experiments across various model sizes and workloads demonstrate that TENET-FPGA and TENET-ASIC improve energy efficiency by 4.3$\times$ and 21.1$\times$, respectively, compared to the A100 GPU. Furthermore, TENET-ASIC achieves a 2.7$\times$ average speedup compared to the A100 GPU in end-to-end inference latency.

cs.AR↗

arXiv2025

The coupling of mixed and primal finite element methods for the coupled body-plate problem

This paper considers the coupled problem of a three-dimensional elastic body and a two-dimensional plate, which are rigidly connected at their interface. The plate consists of a plane elasticity model along the longitudinal direction and a plate bending model with Kirchhoff assumptions along the transverse direction. The Hellinger-Reissner formulation is adopted for the body by introducing the stress as an auxiliary variable, while the primal formulation is employed for the plate. The well-posedness of the weak formulation is established. This approach enables direct stress approximations and allows for non-matching meshes at the interface since the continuity condition of displacements acts as a natural boundary condition for the body. Under certain assumptions, discrete stability and error estimates are derived for both conforming and nonconforming finite element methods. Two specific pairs of conforming and nonconforming finite elements are shown to satisfy the required assumptions, respectively. Furthermore, the problem is reduced to an interface problem based on the domain decomposition, which can be solved effectively by a conjugate gradient iteration. Numerical experiments are conducted to validate the theoretical results.

math.NA↗

arXiv2025

TexVerse: A Universe of 3D Objects with High-Resolution Textures

We introduce TexVerse, a large-scale 3D dataset featuring high-resolution textures. While recent advances in large-scale 3D datasets have enhanced high-resolution geometry generation, creating high-resolution textures end-to-end remains underexplored due to the lack of suitable datasets. TexVerse fills this gap with a curated collection of over 858K unique high-resolution 3D models sourced from Sketchfab, including more than 158K models with physically based rendering (PBR) materials. Each model encompasses all of its high-resolution variants, bringing the total to 1.6M 3D instances. TexVerse also includes specialized subsets: TexVerse-Skeleton, with 69K rigged models, and TexVerse-Animation, with 54K animated models, both preserving original skeleton and animation data uploaded by the user. We also provide detailed model annotations describing overall characteristics, structural components, and intricate features. TexVerse offers a high-quality data resource with wide-ranging potential applications in texture synthesis, PBR material development, animation, and various 3D vision and graphics tasks.

cs.CV↗

arXiv2025

Stationarity Exploration for Multivariate Time Series Forecasting

Deep learning-based time series forecasting has found widespread applications. Recently, converting time series data into the frequency domain for forecasting has become popular for accurately exploring periodic patterns. However, existing methods often cannot effectively explore stationary information from complex intertwined frequency components. In this paper, we propose a simple yet effective Amplitude-Phase Reconstruct Network (APRNet) that models the inter-relationships of amplitude and phase, which prevents the amplitude and phase from being constrained by different physical quantities, thereby decoupling the distinct characteristics of signals for capturing stationary information. Specifically, we represent the multivariate time series input across sequence and channel dimensions, highlighting the correlation between amplitude and phase at multiple interaction frequencies. We propose a novel Kolmogorov-Arnold-Network-based Local Correlation (KLC) module to adaptively fit local functions using univariate functions, enabling more flexible characterization of stationary features across different amplitudes and phases. This significantly enhances the model's capability to capture time-varying patterns. Extensive experiments demonstrate the superiority of our APRNet against the state-of-the-arts (SOTAs).

cs.LG↗

arXiv2025

Optimality of adaptive $H(\operatorname{div}\operatorname{div})$ mixed finite element methods for the Kirchhoff-Love plate bending problem

This paper presents a reliable and efficient residual-based a posteriori error analysis for the symmetric $H(\operatorname{div}\operatorname{div})$ mixed finite element method for the Kirchhoff-Love plate bending problem with mixed boundary conditions. The key ingredient lies in the construction of boundary-condition-preserving complexes at both continuous and discrete levels. Additionally, the discrete symmetric $H(\operatorname{div}\operatorname{div})$ space is extended to ensure nestedness, which leads to optimality for the adaptive algorithm. Numerical examples confirm the effectiveness of the a posteriori error estimator and demonstrate the optimal convergence rate under adaptive refinements.

math.NA↗

arXiv2025

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual generation models inherently introduces information loss that degrades image fidelity. To mitigate this limitation, recent studies have explored to autoregressively predict continuous tokens. Unlike discrete tokens that reside in a structured and bounded space, continuous representations exist in an unbounded, high-dimensional space, making density estimation more challenging and increasing the risk of generating out-of-distribution artifacts. Based on the above findings, this work introduces DisCon (Discrete-Conditioned Continuous Autoregressive Model), a novel framework that reinterprets discrete tokens as conditional signals rather than generation targets. By modeling the conditional probability of continuous representations conditioned on discrete tokens, DisCon circumvents the optimization challenges of continuous token modeling while avoiding the information loss caused by quantization. DisCon achieves a gFID score of 1.38 on ImageNet 256$\times$256 generation, outperforming state-of-the-art autoregressive approaches by a clear margin. Project page: https://pengzheng0707.github.io/DisCon.

cs.CV↗

arXiv2025

Self-organized dynamics and emergent shape spaces of active isotropic fluid surfaces

Theories of self-organized active fluid surfaces have emerged as an important class of minimal models for the shape dynamics of biological membranes, cells and tissues. However, due to their inherent geometric nonlinearities and the absence of general minimization principles in active systems, it remains a major challenge to systematically study the emergent shape spaces such theories give rise to. Here, we introduce a novel variational approach that allows for a direct computation of stationary surface geometries and flows, which enables the classification of non-equilibrium phase transitions in shape spaces described by active surface theories. To achieve this, we construct a dissipation functional systematically from the entropy production in active surfaces and show how generic symmetries imposed by Onsager relations can be exploited to also account for reactive non-dissipative terms in constitutive laws. This functional is supplemented by Lagrange multipliers that relax nonlinear geometric constraints, which leads to a tractable variational problem suitable for implicit dynamic simulations and explicit calculations of non-trivial steady state geometries and flows. We apply this framework to study the dynamics of open fluid membranes and closed active fluid surfaces, and characterize the space of stationary solutions that corresponding surfaces and flows occupy. These analyses rationalize the interplay of first-order shape transitions of internally and externally forced fluid membranes, reveal degenerate regions in stationary shape spaces of mechanochemically active surfaces and identify a mechanism by which hydrodynamic screening controls the geometry of active surfaces undergoing cell division-like shape transformations.

cond-mat.soft↗

arXiv2025

FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization

Subject-driven image generation plays a crucial role in applications such as virtual try-on and poster design. Existing approaches typically fine-tune pretrained generative models or apply LoRA-based adaptations for individual subjects. However, these methods struggle with multi-subject personalization, as combining independently adapted modules often requires complex re-tuning or joint optimization. We present FreeLoRA, a simple and generalizable framework that enables training-free fusion of subject-specific LoRA modules for multi-subject personalization. Each LoRA module is adapted on a few images of a specific subject using a Full Token Tuning strategy, where it is applied across all tokens in the prompt to encourage weakly supervised token-content alignment. At inference, we adopt Subject-Aware Inference, activating each module only on its corresponding subject tokens. This enables training-free fusion of multiple personalized subjects within a single image, while mitigating overfitting and mutual interference between subjects. Extensive experiments show that FreeLoRA achieves strong performance in both subject fidelity and prompt consistency.

cs.CV↗

arXiv2025

3D surface profiling via photonic integrated geometric sensor

Measurements of microscale surface patterns are essential for process and quality control in industries across semiconductors, micro-machining, and biomedicines. However, the development of miniaturized and intelligent profiling systems remains a longstanding challenge, primarily due to the complexity and bulkiness of existing benchtop systems required to scan large-area samples. A real-time, in-situ, and fast detection alternative is therefore highly desirable for predicting surface topography on the fly. In this paper, we present an ultracompact geometric profiler based on photonic integrated circuits, which directly encodes the optical reflectance of the sample and decodes it with a neural network. This platform is free of complex interferometric configurations and avoids time-consuming nonlinear fitting algorithms. We show that a silicon programmable circuit can generate pseudo-random kernels to project input data into higher dimensions, enabling efficient feature extraction via a lightweight one-dimensional convolutional neural network. Our device is capable of high-fidelity, fast-scanning-rate thickness identification for both smoothly varying samples and intricate 3D printed emblem structures, paving the way for a new class of compact geometric sensors.

physics.optics↗

arXiv2025

MiMo-VL Technical Report

We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integrating diverse reward signals. We identify the importance of incorporating high-quality reasoning data with long Chain-of-Thought into pre-training stages, and the benefits of mixed RL despite challenges in simultaneous multi-domain optimization. We also contribute a comprehensive evaluation suite covering 50+ tasks to promote reproducibility and advance the field. The model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-VL.

cs.CL↗

arXiv2025

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based control, which offers better controllability but demands considerable knowledge for the cumbersome graph design process. To address these challenges, we present FreeScene, a user-friendly framework that enables both convenient and effective control for indoor scene synthesis.Specifically, FreeScene supports free-form user inputs including text description and/or reference images, allowing users to express versatile design intentions. The user inputs are adequately analyzed and integrated into a graph representation by a VLM-based Graph Designer. We then propose MG-DiT, a Mixed Graph Diffusion Transformer, which performs graph-aware denoising to enhance scene generation. Our MG-DiT not only excels at preserving graph structure but also offers broad applicability to various tasks, including, but not limited to, text-to-scene, graph-to-scene, and rearrangement, all within a single model. Extensive experiments demonstrate that FreeScene provides an efficient and user-friendly solution that unifies text-based and graph based scene synthesis, outperforming state-of-the-art methods in terms of both generation quality and controllability in a range of applications.

cs.CV↗

arXiv2025

Internal dynamics and fission of pure-quartic soliton molecules

We address the weak interaction of a pair of well-separated pure-quartic solitons (PQSs), which are solutions to a generalized nonlinear Schrodinger equation (NLSE) with the quartic-only dispersion. An asymptotic technique is applied to derive equations for the slow evolution of the temporal separation and phase difference of the PQSs interacting through the overlapping of their exponentially decaying oscillating tails. Based on this approach, various stationary states of bound PQS (soliton molecules) with distinct phase differences are predicted. Their stability is addressed via the numerical calculation of the eigenvalue spectrum of small perturbations, showing instability of the bound states. A systematic numerical analysis demonstrates that the parameter space of the PQS bound states is organized as a self-similar fractal structure, composed of regions populated by robustly oscillating or splitting two-soliton states. The analytical method and results reported here can be extended for bound states of two or several weakly interacting modes in other conservative and dissipative systems.

physics.optics↗

arXiv2025

Photonic chip-based high-efficiency soliton microcombs via electroopitc-Kerr synergy

Temporal soliton mode-locking in coherently pumped microcavities provides a promising platform for miniaturized frequency comb systems. While significant progress has been made, achieving high conversion efficiency in such microcombs remains a critical challenge. Soliton generation through pulse pumping has emerged as an effective strategy to improve conversion efficiency. However, the on-chip integration of pulse generation with dissipative Kerr soliton (DKS) formation within the photonic chip has not yet been realized. In this work, we demonstrate a photonic chip-based soliton microcomb with high conversion efficiency, achieved by integrating on-chip pulse generation and DKS generation. The pulsed laser, fabricated on a lithium niobate-on-insulator (LNOI) platform, delivers a 35.5GHz repetition rate with broadly tunable center frequencies. By coupling these on-chip pulses to a silicon nitride microresonator, we achieve stable DKS generation with a pump-to-soliton conversion efficiency of 43.9% under steady-state conditions. This integrated architecture establishes a viable pathway toward chip-scale soliton microcombs with unprecedented efficiency, opening up new possibilities for optical communications, precision spectroscopy, and photonic sensing.

physics.optics↗

arXiv2025

OmniStyle: Filtering High Quality Style Transfer Data at Scale

In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-quality triplets based on content preservation, style consistency, and aesthetic appeal. Building upon this foundation, we propose OmniStyle, a framework based on the Diffusion Transformer (DiT) architecture designed for high-quality and efficient style transfer. This framework supports both instruction-guided and image-guided style transfer, generating high resolution outputs with exceptional detail. Extensive qualitative and quantitative evaluations demonstrate OmniStyle's superior performance compared to existing approaches, highlighting its efficiency and versatility. OmniStyle-1M and its accompanying methodologies provide a significant contribution to advancing high-quality style transfer, offering a valuable resource for the research community.

cs.CV↗

arXiv2025

BOOTPLACE: Bootstrapped Object Placement with Detection Transformers

In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the reliance for dense supervision. However, this often limits their capacity to model complex data distributions. Alternatively, transformer networks with a sparse contrastive loss have been explored, but their over-relaxed regularization often leads to imprecise object placement. We introduce BOOTPLACE, a novel paradigm that formulates object placement as a placement-by-detection problem. Our approach begins by identifying suitable regions of interest for object placement. This is achieved by training a specialized detection transformer on object-subtracted backgrounds, enhanced with multi-object supervisions. It then semantically associates each target compositing object with detected regions based on their complementary characteristics. Through a boostrapped training approach applied to randomly object-subtracted images, our model enforces meaningful placements through extensive paired data augmentation. Experimental results on established benchmarks demonstrate BOOTPLACE's superior performance in object repositioning, markedly surpassing state-of-the-art baselines on Cityscapes and OPA datasets with notable improvements in IOU scores. Additional ablation studies further showcase the compositionality and generalizability of our approach, supported by user study evaluations.

cs.CV↗

arXiv2025

ZenSVI: An Open-Source Software for the Integrated Acquisition, Processing and Analysis of Street View Imagery Towards Scalable Urban Science

Street view imagery (SVI) has been instrumental in many studies in the past decade to understand and characterize street features and the built environment. Researchers across a variety of domains, such as transportation, health, architecture, human perception, and infrastructure have employed different methods to analyze SVI. However, these applications and image-processing procedures have not been standardized, and solutions have been implemented in isolation, often making it difficult for others to reproduce existing work and carry out new research. Using SVI for research requires multiple technical steps: accessing APIs for scalable data collection, preprocessing images to standardize formats, implementing computer vision models for feature extraction, and conducting spatial analysis. These technical requirements create barriers for researchers in urban studies, particularly those without extensive programming experience. We developed ZenSVI, a free and open-source Python package that integrates and implements the entire process of SVI analysis, supporting a wide range of use cases. Its end-to-end pipeline includes downloading SVI from multiple platforms (e.g., Mapillary and KartaView) efficiently, analyzing metadata of SVI, applying computer vision models to extract target features, transforming SVI into different projections (e.g., fish-eye and perspective) and different formats (e.g., depth map and point cloud), visualizing analyses with maps and plots, and exporting outputs to other software tools. We demonstrated its use in Singapore through a case study of data quality assessment and clustering analysis in a streamlined manner. Our software improves the transparency, reproducibility, and scalability of research relying on SVI and supports researchers in conducting urban analyses efficiently. Its modular design facilitates extensions of the package for new use cases.

cs.CV↗

arXiv2025

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

3D sketches are widely used for visually representing the 3D shape and structure of objects or scenes. However, the creation of 3D sketch often requires users to possess professional artistic skills. Existing research efforts primarily focus on enhancing the ability of interactive sketch generation in 3D virtual systems. In this work, we propose Diff3DS, a novel differentiable rendering framework for generating view-consistent 3D sketch by optimizing 3D parametric curves under various supervisions. Specifically, we perform perspective projection to render the 3D rational Bézier curves into 2D curves, which are subsequently converted to a 2D raster image via our customized differentiable rasterizer. Our framework bridges the domains of 3D sketch and raster image, achieving end-toend optimization of 3D sketch through gradients computed in the 2D image domain. Our Diff3DS can enable a series of novel 3D sketch generation tasks, including textto-3D sketch and image-to-3D sketch, supported by the popular distillation-based supervision, such as Score Distillation Sampling (SDS). Extensive experiments have yielded promising results and demonstrated the potential of our framework. Project page is at https://yiboz2001.github.io/Diff3DS/.

cs.CV↗