Weidong Yang

AAAI Conference 2026 Conference Paper

La La LiDAR: Large-Scale Layout Generation from LiDAR Data

• Youquan Liu
• Lingdong Kong
• Weidong Yang
• Xin Li
• Alan Liang
• Runnan Chen
• Ben Fei
• Tongliang Liu

Controllable generation of realistic LiDAR scenes is crucial for applications such as autonomous driving and robotics. While recent diffusion-based models achieve high-fidelity LiDAR generation, they lack explicit control over foreground objects and spatial relationships, limiting their usefulness for scenario simulation and safety validation. To address these limitations, we propose Large-scale Layout-guided LiDAR generation model ("La La LiDAR"), a novel layout-guided generative framework that introduces semantic-enhanced scene graph diffusion with relation-aware contextual conditioning for structured LiDAR layout generation, followed by foreground-aware control injection for complete scene generation. This enables customizable control over object placement while ensuring spatial and semantic consistency. To support our structured LiDAR generation, we introduce Waymo-SG and nuScenes-SG, two large-scale LiDAR scene graph datasets, along with new evaluation metrics for layout synthesis. Extensive experiments demonstrate that La La LiDAR achieves state-of-the-art performance in both LiDAR generation and downstream perception tasks, establishing a new benchmark for controllable 3D scene generation.

AAAI Conference 2025 Conference Paper

3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering

• Qingyuan Zhou
• Weidong Yang
• Ben Fei
• Jingyi Xu
• Rui Zhang
• Keyi Liu
• Yeqi Luo
• Ying He

Noise is an inevitable aspect of point cloud acquisition, necessitating filtering as a fundamental task within the realm of 3D vision. Existing learning-based filtering methods have shown promising capabilities on commonly used datasets. Nonetheless, the effectiveness of these methods is constrained when dealing with a substantial quantity of point clouds. This limitation primarily stems from their limited denoising capabilities for dense and large-scale point clouds and their inclination to generate noisy outliers after denoising. To deal with this challenge, we introduce 3DMambaIPF, for the first time, exploiting Selective State Space Models (SSMs) architecture to handle highly-dense and large-scale point clouds, capitalizing on its strengths in selective input processing and large context modeling capabilities. Additionally, we present a robust and fast differentiable rendering loss to constrain the noisy points around the surface. In contrast to previous methodologies, this differentiable rendering loss enhances the visual realism of denoised geometric structures and aligns point cloud boundaries more closely with those observed in real-world objects. Extensive evaluations on commonly used datasets (typically with up to 50K points) demonstrate that 3DMambaIPF achieves state-of-the-art results. Moreover, we showcase the superior scalability and efficiency of 3DMambaIPF on highly dense and large-scale point clouds with up to 500K points compared to off-the-shelf methods.

AAAI Conference 2025 Conference Paper

Adaptive Prototype Replay for Class Incremental Semantic Segmentation

• Guilin Zhu
• Dongyue Wu
• Changxin Gao
• Runmin Wang
• Weidong Yang
• Nong Sang

Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously learned classes using stored prototypes or features. However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes. This mismatch between updated representation and fixed prototypes limits the effectiveness of the prototype replay strategy. To address this issue, we propose the Adaptive prototype replay (Adapter) for CISS in this paper. Adapter comprises an adaptive deviation compensation (ADC) strategy and an uncertainty-aware constraint (UAC) loss. Specifically, the ADC strategy dynamically updates the stored prototypes based on the estimated representation shift distance to match the updated representation of old class. The UAC loss reduces prediction uncertainty, aggregating discriminative features to aid in generating compact prototypes. Additionally, we introduce a compensation-based prototype similarity discriminative (CPD) loss to ensure adequate differentiation between similar prototypes, thereby enhancing the efficiency of the adaptive prototype replay strategy. Extensive experiments on Pascal VOC and ADE20K datasets demonstrate that Adapter achieves state-of-the-art results and proves effective across various CISS tasks, particularly in challenging multi-step scenarios.

NeurIPS Conference 2025 Conference Paper

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

• Junchao Gong
• Jingyi Xu
• Ben Fei
• Fenghua Ling
• Wenlong Zhang
• Kun Chen
• Wanghan Xu
• Weidong Yang

Weather prediction is a critical task for human society, where impressive progress has been made by training artificial intelligence weather prediction (AIWP) methods with reanalysis data. However, reliance on reanalysis data limits the AIWPs with shortcomings, including data assimilation biases and temporal discrepancies. To liberate AIWPs from the reanalysis data, observation forecasting emerges as a transformative paradigm for weather prediction. One of the key challenges in observation forecasting is learning spatiotemporal dynamics across disparate measurement systems with irregular high-resolution observation data, which constrains the design and prediction of AIWPs. To this end, we propose our DAWP as an innovative framework to enable AIWPs to operate in a complete observation space by initialization with an artificial intelligence data assimilation (AIDA) module. Specifically, our AIDA module applies a mask multi-modality autoencoder (MMAE) for assimilating irregular satellite observation tokens encoded by mask ViT-VAEs. For AIWP, we introduce a spatiotemporal decoupling transformer with cross-regional boundary conditioning (CBC), learning the dynamics in observation space, to enable sub-image-based global observation forecasting. Comprehensive experiments demonstrate that AIDA initialization significantly improves the roll-out and efficiency of AIWP. Additionally, we show that DAWP holds promising potential to be applied in global precipitation forecasting.

NeurIPS Conference 2025 Conference Paper

SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting

• Jingyi Xu
• Shengnan Wang
• Weidong Yang
• Keyi Liu
• Yeqi Luo
• Ben Fei
• Lei Bai

Arctic sea ice performs a vital role in global climate and has paramount impacts on both polar ecosystems and coastal communities. In the last few years, multiple deep learning based pan-Arctic sea ice concentration (SIC) forecasting methods have emerged and showcased superior performance over physics-based dynamical models. However, previous methods forecast SIC at a fixed temporal granularity, e. g. sub-seasonal or seasonal, thus only leveraging inter-granularity information and overlooking the plentiful inter-granularity correlations. SIC at various temporal granularities exhibits cumulative effects and are naturally consistent, with short-term fluctuations potentially impacting long-term trends and long-term trends provides effective hints for facilitating short-term forecasts in Arctic sea ice. Therefore, in this study, we propose to cultivate temporal multi-granularity that naturally derived from Arctic sea ice reanalysis data and provide a unified perspective for modeling SIC via our Sea Ice Fusion framework. SIFusion is delicately designed to leverage both intra-granularity and inter-granularity information for capturing granularity-consistent representations that promote forecasting skills. Our extensive experiments show that SIFusion outperforms off-the-shelf deep learning models for their specific temporal granularity.

NeurIPS Conference 2024 Conference Paper

Taming Generative Diffusion Prior for Universal Blind Image Restoration

• Siwei Tu
• Weidong Yang
• Ben Fei

Diffusion models have been widely utilized for image restoration. However, previous blind image restoration methods still need to assume the type of degradation model while leaving the parameters to be optimized, limiting their real-world applications. Therefore, we aim to tame generative diffusion prior for universal blind image restoration dubbed BIR-D, which utilizes an optimizable convolutional kernel to simulate the degradation model and dynamically update the parameters of the kernel in the diffusion steps, enabling it to achieve blind image restoration results even in various complex situations. Besides, based on mathematical reasoning, we have provided an empirical formula for the chosen of adaptive guidance scale, eliminating the need for a grid search for the optimal parameter. Experimentally, Our BIR-D has demonstrated superior practicality and versatility than off-the-shelf unsupervised methods across various tasks both on real-world and synthetic datasets, qualitatively and quantitatively. BIR-D is able to fulfill multi-guidance blind image restoration. Moreover, BIR-D can also restore images that undergo multiple and complicated degradations, demonstrating the practical applications. The code is available at https: //github. com/Tusiwei/BIR-D.

EAAI Journal 2015 Journal Article

Research of semantic understanding on target region of interest for fuzzy image

• QingE Wu
• Weidong Yang
• Zhiwu Chen
• Ping Zhang

IJCAI Conference 2013 Conference Paper

A Probabilistic Approach to Latent Cluster Analysis

• Zhipeng Xie
• Rui Dong
• Zhengheng Deng
• Zhenying He
• Weidong Yang

Facing a large number of clustering solutions, cluster ensemble method provides an effective approach to aggregating them into a better one. In this paper, we propose a novel cluster ensemble method from probabilistic perspective. It assumes that each clustering solution is generated from a latent cluster model, under the control of two probabilistic parameters. Thus, the cluster ensemble problem is reformulated into an optimization problem of maximum likelihood. An EM-style algorithm is designed to solve this problem. It can determine the number of clusters automatically. Experimenal results have shown that the proposed algorithm outperforms the state-of-the-art methods including EAC-AL, CSPA, HGPA, and MCLA. Furthermore, it has been shown that our algorithm is stable in the predicted numbers of clusters.