arXiv subjects

Xiangyang Zhu

Publications and source records attributed to Xiangyang Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2025

VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results

This paper presents a summary of the VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models (LMMs), hosted as part of the ICCV 2025 Workshop on Visual Quality Assessment. The challenge aims to evaluate and enhance the ability of state-of-the-art LMMs to perform open-ended and detailed reasoning about visual quality differences across multiple images. To this end, the competition introduces a novel benchmark comprising thousands of coarse-to-fine grained visual quality comparison tasks, spanning single images, pairs, and multi-image groups. Each task requires models to provide accurate quality judgments. The competition emphasizes holistic evaluation protocols, including 2AFC-based binary preference and multi-choice questions (MCQs). Around 100 participants submitted entries, with five models demonstrating the emerging capabilities of instruction-tuned LMMs on quality assessment. This challenge marks a significant step toward open-domain visual quality reasoning and comparison and serves as a catalyst for future research on interpretable and human-aligned quality evaluation systems.

cs.CV↗

arXiv2025

A Geometric Method for Base Parameter Analysis in Robot Inertia Identification Based on Projective Geometric Algebra

This paper proposes a novel geometric method for analytically determining the base inertial parameters of robotic systems. The rigid body dynamics is reformulated using projective geometric algebra, leading to a new identification model named ``tetrahedral-point (TP)" model. Based on the rigid body TP model, coefficients in the regresoor matrix of the identification model are derived in closed-form, exhibiting clear geometric interpretations. Building directly from the dynamic model, three foundational principles for base parameter analysis are proposed: the shared points principle, fixed points principle, and planar rotations principle. With these principles, algorithms are developed to automatically determine all the base parameters. The core algorithm, referred to as Dynamics Regressor Nullspace Generator (DRNG), achieves $O(1)$-complexity theoretically following an $O(N)$-complexity preprocessing stage, where $N$ is the number of rigid bodies. The proposed method and algorithms are validated across four robots: Puma560, Unitree Go2, a 2RRU-1RRS parallel kinematics mechanism (PKM), and a 2PRS-1PSR PKM. In all cases, the algorithms successfully identify the complete set of base parameters. Notably, the approach demonstrates high robustness and computational efficiency, particularly in the cases of PKMs. Through the comprehensive demonstrations, the method is shown to be general, robust, and efficient.

cs.RO↗

arXiv2025

VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.

cs.CV↗

arXiv2025

MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine

With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reasoning. Two key risks are Chain-of-Thought (CoT) faithfulness -- whether reasoning aligns with responses and medical facts -- and sycophancy, where models follow misleading cues over correctness. Existing benchmarks often collapse such vulnerabilities into single accuracy scores. To address this, we introduce MedOmni-45 Degrees, a benchmark and workflow designed to quantify safety-performance trade-offs under manipulative hint conditions. It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA. Each question is paired with seven manipulative hint types and a no-hint baseline, producing about 27K inputs. We evaluate seven LLMs spanning open- vs. closed-source, general-purpose vs. medical, and base vs. reasoning-enhanced models, totaling over 189K inferences. Three metrics -- Accuracy, CoT-Faithfulness, and Anti-Sycophancy -- are combined into a composite score visualized with a 45 Degrees plot. Results show a consistent safety-performance trade-off, with no model surpassing the diagonal. The open-source QwQ-32B performs closest (43.81 Degrees), balancing safety and accuracy but not leading in both. MedOmni-45 Degrees thus provides a focused benchmark for exposing reasoning vulnerabilities in medical LLMs and guiding safer model development.

cs.CV↗

arXiv2025

Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA

Large language models (LLMs), while increasingly used in domains requiring factual rigor, often display a troubling behavior: sycophancy, the tendency to align with user beliefs regardless of correctness. This tendency is reinforced by preference-based alignment techniques that optimize for user satisfaction but can undermine truthfulness. While relatively benign in casual dialogue, sycophancy poses serious risks in high-stakes settings such as scientific question answering (QA), where model outputs may shape collaborative reasoning, decision-making, and knowledge formation. Despite its importance, this phenomenon remains underexamined in factual QA contexts. We address this gap by introducing a unified evaluation framework to quantify the impact of sycophantic context on model behavior in scientific QA, measuring how much user-imposed social pressure distorts model outputs. The framework incorporates adversarial prompting setups and targeted metrics, such as misleading resistance and sycophancy resistance, that capture a model's ability to maintain factual consistency under misleading cues. Systematic evaluations across open-source and proprietary models reveal pervasive sycophantic tendencies, driven more by alignment strategy than by model size. To mitigate this issue, we propose Pressure-Tune, a lightweight post-training method that fine-tunes models on synthetic adversarial dialogues paired with chain-of-thought rationales. These rationales reject user misinformation while reinforcing factual commitments. Experiments on challenging scientific QA benchmarks show that Pressure-Tune significantly enhances sycophancy resistance without compromising accuracy or responsiveness to valid feedback, offering a practical pathway toward more truthful and principled model behavior.

cs.CL↗

arXiv2025

Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation

Face image quality assessment (FIQA) is essential for various face-related applications. Although FIQA has been extensively studied and achieved significant progress, the computational complexity of FIQA algorithms remains a key concern for ensuring scalability and practical deployment in real-world systems. In this paper, we aim to develop a computationally efficient FIQA method that can be easily deployed in real-world applications. Specifically, our method consists of two stages: training a powerful teacher model and distilling a lightweight student model from it. To build a strong teacher model, we adopt a self-training strategy to improve its capacity. We first train the teacher model using labeled face images, then use it to generate pseudo-labels for a set of unlabeled images. These pseudo-labeled samples are used in two ways: (1) to distill knowledge into the student model, and (2) to combine with the original labeled images to further enhance the teacher model through self-training. The enhanced teacher model is used to further pseudo-label another set of unlabeled images for distilling the student models. The student model is trained using a combination of labeled images, pseudo-labeled images from the original teacher model, and pseudo-labeled images from the enhanced teacher model. Experimental results demonstrate that our student model achieves comparable performance to the teacher model with an extremely low computational overhead. Moreover, our method achieved first place in the ICCV 2025 VQualA FIQA Challenge. The code is available at https://github.com/sunwei925/Efficient-FIQA.git.

cs.CV↗

arXiv2025

Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification

Medical imaging has significantly advanced computer-aided diagnosis, yet its re-identification (ReID) risks raise critical privacy concerns, calling for de-identification (DeID) techniques. Unfortunately, existing DeID methods neither particularly preserve medical semantics, nor are flexibly adjustable towards different privacy levels. To address these issues, we propose a divide-and-conquer framework comprising two steps: (1) Identity-Blocking, which blocks varying proportions of identity-related regions, to achieve different privacy levels; and (2) Medical-Semantics-Compensation, which leverages pre-trained Medical Foundation Models (MFMs) to extract medical semantic features to compensate the blocked regions. Moreover, recognizing that features from MFMs may still contain residual identity information, we introduce a Minimum Description Length principle-based feature decoupling strategy, to effectively decouple and discard such identity components. Extensive evaluations against existing approaches across seven datasets and three downstream tasks, demonstrates our state-of-the-art performance.

cs.CV↗

arXiv2025

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a unified architecture (Unified Next-DiT) that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and allowing seamless task expansion. Besides, since high-quality captioners can provide semantically well-aligned text-image training pairs, we introduce a unified captioning system, Unified Captioner (UniCap), specifically designed for T2I generation tasks. UniCap excels at generating comprehensive and accurate captions, accelerating convergence and enhancing prompt adherence. (2) Efficiency - to improve the efficiency of our proposed model, we develop multi-stage progressive training strategies and introduce inference acceleration techniques without compromising image quality. Extensive evaluations on academic benchmarks and public text-to-image arenas show that Lumina-Image 2.0 delivers strong performances even with only 2.6B parameters, highlighting its scalability and design efficiency. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-Image-2.0.

cs.CV↗

arXiv2025

A Novel Semi-Coupled Hierarchical Motion Planning Framework for Cooperative Transportation of Multiple Mobile Manipulators

Multiple mobile manipulators show superiority in the tasks requiring mobility and dexterity compared with a single robot, especially when manipulating/transporting bulky objects. However, closed-chain of the system, redundancy of each mobile manipulator and obstacles in the environment bring challenges to the motion planning problem. In this paper, we propose a novel semi-coupled hierarchical framework (SCHF), which decomposes the problem into two semi-coupled sub-problems.To be specific, the centralized layer plans the object's motion first and then the decentralized layer independently explores the redundancy of each robot in real-time. A notable feature is that the lower bound of the redundancy constraint metric is ensured besides the closed-chain and obstacle-avoidance constraints in the centralized layer, which ensures the object's motion can be executed by each robot in the decentralized layer. Simulated results show that the success rate and time cost of SCHF outperforms the fully centralized planner and fully decoupled hierarchical planner significantly. In addition, cluttered real-world experiments also show the feasibility of the SCHF in the transportation tasks. A video clip in various scenarios can be found at https://youtu.be/Y8ZrnspIuBg.

cs.RO↗

arXiv2025

Oblique rotational axis detection using elliptical optical vortex based on rotational Doppler effect

The rotational Doppler effect (RDE) of structured light carrying orbital angular momentum (OAM) has attracted widespread attention for applications in optical sensors and OAM spectrum detection. These studies, however, based on RDE, are mostly focused on the motion parameters of rotating objects; other equally important attitude characteristics, e.g., the tilt angle of the axis of rotation, have rarely been considered. We observed an interesting phenomenon in the experiments: the rotational Doppler spectral distribution varies with the ellipticity of the elliptical optical vortex (EOV) and the tilt angle between the rotational axis and optical axis, which inspired us to wonder if it is possible to detect oblique rotational axis or compensate the rotational Doppler broadening effect induced by oblique incidence by utilizing the EOV. Here, we reveal the RDE quantitative relationship with tilt angle and ellipticity for the first time and report a novel approach for tilt angle measurement. By employing a series of EOV with periodically varying ellipticity to illuminate a rotating object and analyze the time-frequency spectral distribution of scattered light associated with ellipticity and tilt angle, the tilt angle can be acquired accurately based on the specific relationship between the tilt angle and ellipticity of the EOV. Furthermore, the spectrum broadening effect arising from oblique incidence in the actual scenario may be addressed through our scheme. The method may find applications in industrial manufacturing and target attitude measurement, and our results provide new insights for obtaining more information about objects.

physics.optics↗

arXiv2024

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners

We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as a series of multi-directional videos, and leverages SAM 2 for 3D-space segmentation, without further training or 2D-3D projection. Our framework supports various prompt types, including 3D points, boxes, and masks, and can generalize across diverse scenarios, such as 3D objects, indoor scenes, outdoor environments, and raw sparse LiDAR. Demonstrations on multiple 3D datasets, e.g., Objaverse, S3DIS, ScanNet, Semantic3D, and KITTI, highlight the robust generalization capabilities of SAM2Point. To our best knowledge, we present the most faithful implementation of SAM in 3D, which may serve as a starting point for future research in promptable 3D segmentation. Online Demo: https://huggingface.co/spaces/ZiyuG/SAM2Point . Code: https://github.com/ZiyuGuo99/SAM2Point .

cs.CV↗

arXiv2024

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification

Predicting cardiac indices has long been a focal point in the medical imaging community. While various deep learning models have demonstrated success in quantifying cardiac indices, they remain susceptible to mild input perturbations, e.g., spatial transformations, image distortions, and adversarial attacks. This vulnerability undermines confidence in using learning-based automated systems for diagnosing cardiovascular diseases. In this work, we describe a simple yet effective method to learn robust models for left ventricle (LV) quantification, encompassing cavity and myocardium areas, directional dimensions, and regional wall thicknesses. Our success hinges on employing the biologically inspired steerable pyramid transform (SPT) for fixed front-end processing, which offers three main benefits. First, the basis functions of SPT align with the anatomical structure of LV and the geometric features of the measured indices. Second, SPT facilitates weight sharing across different orientations as a form of parameter regularization and naturally captures the scale variations of LV. Third, the residual highpass subband can be conveniently discarded, promoting robust feature learning. Extensive experiments on the Cardiac-Dig benchmark show that our SPT-augmented model not only achieves reasonable prediction accuracy compared to state-of-the-art methods, but also exhibits significantly improved robustness against input perturbations.

eess.IV↗

arXiv2024

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduced a sigmoid time discretization schedule to reduce sampling steps in solving the Flow ODE and the Context Drop method to merge redundant visual tokens for faster network evaluation, effectively boosting the overall sampling speed. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities and multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-view, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights, we aim to advance the development of next-generation generative AI capable of universal modeling.

cs.CV↗

arXiv2024

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Non-parametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency.

cs.CV↗

arXiv2023

Continuous Occupancy Mapping in Dynamic Environments Using Particles

Particle-based dynamic occupancy maps were proposed in recent years to model the obstacles in dynamic environments. Current particle-based maps describe the occupancy status in discrete grid form and suffer from the grid size problem, wherein a large grid size is unfavorable for motion planning, while a small grid size lowers efficiency and causes gaps and inconsistencies. To tackle this problem, this paper generalizes the particle-based map into continuous space and builds an efficient 3D egocentric local map. A dual-structure subspace division paradigm, composed of a voxel subspace division and a novel pyramid-like subspace division, is proposed to propagate particles and update the map efficiently with the consideration of occlusions. The occupancy status of an arbitrary point in the map space can then be estimated with the particles' weights. To further enhance the performance of simultaneously modeling static and dynamic obstacles and minimize noise, an initial velocity estimation approach and a mixture model are utilized. Experimental results show that our map can effectively and efficiently model both dynamic obstacles and static obstacles. Compared to the state-of-the-art grid-form particle-based map, our map enables continuous occupancy estimation and substantially improves the performance in different resolutions.

cs.RO↗

arXiv2023

Conditional Generative Models for Simulation of EMG During Naturalistic Movements

Numerical models of electromyographic (EMG) signals have provided a huge contribution to our fundamental understanding of human neurophysiology and remain a central pillar of motor neuroscience and the development of human-machine interfaces. However, whilst modern biophysical simulations based on finite element methods are highly accurate, they are extremely computationally expensive and thus are generally limited to modelling static systems such as isometrically contracting limbs. As a solution to this problem, we propose a transfer learning approach, in which a conditional generative model is trained to mimic the output of an advanced numerical model. To this end, we present BioMime, a conditional generative neural network trained adversarially to generate motor unit activation potential waveforms under a wide variety of volume conductor parameters. We demonstrate the ability of such a model to predictively interpolate between a much smaller number of numerical model's outputs with a high accuracy. Consequently, the computational load is dramatically reduced, which allows the rapid simulation of EMG signals during truly dynamic and naturalistic movements.

cs.LG↗

arXiv2023

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

cs.CV↗

arXiv2023

PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classification task. In this paper, we first collaborate CLIP and GPT to be a unified 3D open-world learner, named as PointCLIP V2, which fully unleashes their potential for zero-shot 3D classification, segmentation, and detection. To better align 3D data with the pre-trained language knowledge, PointCLIP V2 contains two key designs. For the visual end, we prompt CLIP via a shape projection module to generate more realistic depth maps, narrowing the domain gap between projected point clouds with natural images. For the textual end, we prompt the GPT model to generate 3D-specific text as the input of CLIP's textual encoder. Without any training in 3D domains, our approach significantly surpasses PointCLIP by +42.90%, +40.44%, and +28.75% accuracy on three datasets for zero-shot 3D classification. On top of that, V2 can be extended to few-shot 3D classification, zero-shot 3D part segmentation, and 3D object detection in a simple manner, demonstrating our generalization ability for unified 3D open-world learning.

cs.CV↗