Author name cluster

Hua Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

AAAI Conference 2026 Conference Paper

Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites

Pingrui Lai
Zihao Xie
Hua Yang

Vision-and-Language navigation on websites requires agents to navigate target webpages and answer questions based on human instructions. Current web agents primarily leverage Large Language Models (LLMs) for semantic understanding and reasoning, but still suffer from limited navigation performance and slow inference speed. Constructing a global map across webpages can effectively enhance both navigation accuracy and efficiency, however, this is challenged by the open structure of web navigation graphs and the dynamic nature of web layouts. In this paper, we propose ATLAS: Adaptive Topological Layout And Semantic mapping, a framework that adaptively constructs a time-varying, unbounded topological map across webpages and unifies heterogeneous elements through semantic representation. This enables both global path planning and local element selection for web-based navigation and question answering. As a lightweight approach, ATLAS significantly outperforms existing state-of-the-art methods on the WebVLN benchmark with a 10% improvement in success rate, and achieves the highest average task success rate on both the Mind2Web and WebArena benchmarks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OneLIP: Unlocking and Improving Long-Text Representations of CLIP via One-Stage Adaptation

Renjie Pan
Jiayan Song
Hua Yang

Contrastive Language-Image Pretraining (CLIP) has demonstrated impressive generalization on vision-language tasks by aligning images and short texts. However, its inherent 77-token length limits the capacity of capturing complex semantics in long captions. Existing long-text adaptations for CLIP typically rely on either multi-stage training or truncation-based alignment, both inevitably resulting in semantic degradation and cumbersome tuning. Therefore, we propose OneLIP, a unified framework that extends CLIP to understand long captions within a single training stage, eliminating the need for brittle truncation or multi-stage pipelines. OneLIP addresses semantic degradation by introducing two key innovations: (1) Token Refinement and Importance-guided Modeling (TRIM) module, which selects and refines informative tokens via SVD-based contribution scoring and cross-modal relevance modeling; (2) Per-sample Online Hard Negative Mining (PO-HNM) strategy dynamically maintains sample-specific negatives based on dual-consistency difficulty tracking, which is superior in long-text scenarios where key semantics are distributed in scattered positions. Extensive experiments on long-text image retrieval, short-text image retrieval, zero-shot classification, and text-to-image generation demonstrate OneLIP's robustness and versatility across diverse input lengths, offering a faithful solution for long-text representation learning of CLIP.

PDF Details DOI

IROS Conference 2025 Conference Paper

3D Vision-tactile Reconstruction from Infrared and Visible Images for Robotic Fine-grained Tactile Perception

Yuankai Lin
Xiaofan Lu
Jiahui Chen
Hua Yang

To achieve human-like haptic perception in anthropomorphic grippers, the compliant sensing surfaces of vision tactile sensor (VTS) must evolve from conventional planar configurations to biomimetically curved topographies with continuous surface gradients. However, planar VTSs have challenges when extended to curved surfaces, including insufficient lighting of surfaces, blurring in reconstruction, and complex spatial boundary conditions for surface structures. With an end goal of constructing a human-like fingertip, our research (i) develops GelSplitter3D by expanding imaging channels with a prism and a near-infrared (NIR) camera, (ii) proposes a photometric stereo neural network with a CAD-based normal ground truth generation method to calibrate tactile geometry, and (iii) devises a normal integration method with boundary constraints of depth prior information to correcting the cumulative error of surface integrals. We demonstrate better tactile sensing performance, a 40% improvement in normal estimation accuracy, and the benefits of sensor shapes in grasping and manipulation tasks.

Details

NeurIPS Conference 2025 Conference Paper

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Xiangyu Zhao
Peiyuan Zhang
Kexian Tang
Xiaorong Zhu
Hao Li
Wenhao Chai
Zicheng Zhang
Renqiu Xia

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-image-1, achieves an accuracy of merely 28. 8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https: //github. com/PhoenixZ810/RISEBench.

PDF Details

EAAI Journal 2025 Journal Article

Multi-pulse superposition for droplet volume control in inkjet printing based on model and data fusion

Xiao Yue
Xin Li
Jiankui Chen
Wei Chen
Hua Yang
Jincheng Gao
Zhouping Yin

Inkjet printing technology for fabricating organic light-emitting diode display panels offers advantages such as high material utilization and the capability for large-area manufacturing. When printing display panels with varying resolutions, ejecting droplets of different sizes from the nozzle is often necessary to balance print quality and efficiency. However, due to nozzle size limitations, the volume range of stable droplets produced by a single-pulse driving waveform is relatively narrow, with the maximum volume being less than twice the minimum volume. Therefore, approaches based on superposition of multi-pulse waveforms have attracted attention, but existing studies only implement manual design of waveforms based on experimental laws and rarely involve automatic regulation of multi-pulse waveform parameters, which is not favorable for industrial applications. Based on combining a meniscus vibration model with industrial ejection data, this paper extracts control strategies from historical data using deep reinforcement learning, and recommends initial waveform parameters through a fuzzy system. Then, the multi-pulse waveform parameters are automatically adjusted in real-time based on the observed droplet volume to fuse the droplets at the nozzle, enabling a wider range of droplet volume closed-loop control. Experiments on industrial inkjet printing equipment implemented intelligent closed-loop regulation of multi-pulse driving waveforms, successfully controlling droplets of different sizes such as 2, 4, and 8 picoliter with an error accuracy of less than ± 4 %. This approach applies artificial intelligence algorithms to inkjet printing engineering and intelligently adjusts the multi-pulse waveform parameters to enhance the controllable range of droplet volumes.

Details DOI

IJCAI Conference 2023 Conference Paper

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

Zhiqiang Shen
Peng Cao
Hua Yang
Xiaoli Liu
Jinzhu Yang
Osmar R. Zaiane

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, degenerating to the self-training ones, and produce low-confidence pseudo labels from the perturbed inputs during training. To address these issues, we propose an Uncertainty-guided Collaborative Mean-Teacher (UCMT) for semi-supervised semantic segmentation with the high-confidence pseudo labels. Concretely, UCMT consists of two main components: 1) collaborative mean-teacher (CMT) for encouraging model disagreement and performing co-training between the sub-networks, and 2) uncertainty-guided region mix (UMIX) for manipulating the input images according to the uncertainty maps of CMT and facilitating CMT to produce high-confidence pseudo labels. Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation. Extensive experiments on four public medical image datasets including 2D and 3D modalities demonstrate the superiority of UCMT over the state-of-the-art. Code is available at: https: //github. com/Senyh/UCMT.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Dynamic Spatial Propagation Network for Depth Completion

Yuankai Lin
Tao Cheng
Qi Zhong
Wending Zhou
Hua Yang

Image-guided depth completion aims to generate dense depth maps with sparse depth measurements and corresponding RGB images. Currently, spatial propagation networks (SPNs) are the most popular affinity-based methods in depth completion, but they still suffer from the representation limitation of the fixed affinity and the over smoothing during iterations. Our solution is to estimate independent affinity matrices in each SPN iteration, but it is over-parameterized and heavy calculation. This paper introduces an efficient model that learns the affinity among neighboring pixels with an attention-based, dynamic approach. Specifically, the Dynamic Spatial Propagation Network (DySPN) we proposed makes use of a non-linear propagation model (NLPM). It decouples the neighborhood into parts regarding to different distances and recursively generates independent attention maps to refine these parts into adaptive affinity matrices. Furthermore, we adopt a diffusion suppression (DS) operation so that the model converges at an early stage to prevent oversmoothing of dense depth. Finally, in order to decrease the computational cost required, we also introduce three variations that reduce the amount of neighbors and attentions needed while still retaining similar accuracy. In practice, our method requires less iteration to match the performance of other SPNs and yields better results overall. DySPN outperforms other state-of-the-art (SoTA) methods on KITTI Depth Completion (DC) evaluation by the time of submission and is able to yield SoTA performance in NYU Depth v2 dataset as well.

PDF Details

ECAI Conference 2020 Conference Paper

Derivative-Free Optimization with Adaptive Experience for Efficient Hyper-Parameter Tuning

Yi-Qi Hu
Zelin Liu
Hua Yang
Yang Yu 0001
Yunfeng Liu

Hyper-parameter tuning is a core part of automatic machine learning (AutoML), which aims to automatically configure machine learning systems in deployed applications. Previously, hyper-parameter tuning is usually formulated as a black-box optimization problem, for which derivative-free optimization (DFO) solver is often employed. Such solvers often suffered from low-efficiency. Thus experienced DFO was proposed, which utilizes historical optimization process data to guide the optimization on new problems. However, the effectiveness of experienced DFO is sensitive to the relevance between the experienced tasks and the target tasks. Relevant experience can accelerate the convergence, while irrelevant experience could injure the convergence. This paper proposes an adaptation mechanism for the experienced DFO. It learns a set of experience models to guide the DFO processes, and exams these models on a few labeled samples from the target task. By comparing model predictions with the ground-truth labels, it adaptively learns the relevant experience by weighting those models. The experiments on synthetic tasks verify that the proposed method can effectively adopt the relevant experience for a range of target tasks. Furthermore, we apply the proposed method to the tasks of configuring LightGBM hyper-parameters. The empirical results show that the proposed method effectively selects the relevant experience and significantly improves the performance of hyper-parameter tuning in only a few iterations.

Details

YNIMG Journal 2017 Journal Article

Meditation is associated with increased brain network integration

Remko van Lutterveld
Edwin van Dellen
Prasanta Pal
Hua Yang
Cornelis Jan Stam
Judson Brewer

Introduction This study aims to identify novel quantitative EEG measures associated with mindfulness meditation. As there is some evidence that meditation is associated with higher integration of brain networks, we focused on EEG measures of network integration. Methods Sixteen novice meditators and sixteen experienced meditators participated in the study. Novice meditators performed a basic meditation practice that supported effortless awareness, which is an important quality of experience related to mindfulness practices, while their EEG was recorded. Experienced meditators performed a self-selected meditation practice that supported effortless awareness. Network integration was analyzed with maximum betweenness centrality and leaf fraction (which both correlate positively with network integration) as well as with diameter and average eccentricity (which both correlate negatively with network integration), based on a phase-lag index (PLI) and minimum spanning tree (MST) approach. Differences between groups were assessed using repeated-measures ANOVA for the theta (4–8 Hz), alpha (8–13 Hz) and lower beta (13–20 Hz) frequency bands. Results Maximum betweenness centrality was significantly higher in experienced meditators than in novices (P = 0. 012) in the alpha band. In the same frequency band, leaf fraction showed a trend toward being significantly higher in experienced meditators than in novices (P = 0. 056), while diameter and average eccentricity were significantly lower in experienced meditators than in novices (P = 0. 016 and P = 0. 028 respectively). No significant differences between groups were observed for the theta and beta frequency bands. Conclusion These results show that alpha band functional network topology is better integrated in experienced meditators than in novice meditators during meditation. This novel finding provides the rationale to investigate the temporal relation between measures of functional connectivity network integration and meditation quality, for example using neurophenomenology experiments.

Details DOI

ICRA Conference 2011 Conference Paper

Dynamics-based visual inspection through real-time modal analysis

Hua Yang
Takeshi Takaki
Idaku Ishii

In this study, we propose the concept of dynamics-based visual inspection for the verification of structural dynamic properties of a vibrating object; the inspection method involves the analysis of the vibration distribution of the object by using a high-frame-rate video. Under unknown ambient excitation, modal parameters of an excited object are simultaneously estimated to determine its input-invariant dynamic properties by using a fast output-only modal analysis algorithm, SSI-CPAST. The algorithm was implemented on a 2000-fps vision platform, and it facilitates non-destructive monitoring of the structure of beam-shaped objects vibrating at dozens of hertz; the algorithm detects small changes in the dynamic properties of the objects caused by internal defects such as fatigue cracks. The modal parameters resonant frequency and mode shape were actually estimated for beam-shaped objects excited by human finger tapping to verify the performance of 2000-fps real-time dynamics-based visual inspection.

Details