Jonathan Li

AAAI Conference 2026 Conference Paper

BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction

• Zhengsen Xu
• Sibo Cheng
• Lanying Wang
• Hongjie He
• Wentao Sun
• Jonathan Li
• Lincoln Linlin Xu

Wildfire risk prediction remains a critical yet challenging task due to the complex interactions among fuel conditions, meteorology, topography, and human activity. Despite growing interest in data-driven approaches, publicly available benchmark datasets that support long-term temporal modeling, large-scale spatial coverage, and multimodal drivers remain scarce. To address this gap, we present a 25-year, daily-resolution wildfire dataset covering 240 million hectares across British Columbia and surrounding regions. The dataset includes 38 covariates, encompassing active fire detections, weather variables, fuel conditions, terrain features, and anthropogenic factors. Using this benchmark, we evaluate a diverse set of time-series forecasting models, including CNN-based, linear-based, Transformer-based, and Mamba-based architectures. We also investigate effectiveness of position embedding and the relative importance of different fire-driving factors.

TMLR Journal 2026 Journal Article

Muon Optimizes Under Spectral Norm Constraints

• Lizhang Chen
• Jonathan Li
• Qiang Liu

The pursuit of faster optimization algorithms remains an active and important research direction in deep learning. Recently, the Muon optimizer has demonstrated promising empirical performance, but its theoretical foundation remains less understood. In this paper, we bridge this gap and provide a theoretical analysis of Muon by placing it within the Lion-$\mathcal{K}$ family of optimizers. Specifically, we show that Muon corresponds to Lion-$\mathcal{K}$ when equipped with the nuclear norm, and we leverage the theoretical results of Lion-$\mathcal{K}$ to establish that Muon (with decoupled weight decay) implicitly solves an optimization problem that enforces a constraint on the spectral norm of weight matrices. This perspective not only demystifies the implicit regularization effects of Muon but also leads to natural generalizations through varying the choice of convex map $\mathcal{K}$, allowing for the exploration of a broader class of implicitly regularized and constrained optimization algorithms.

NeurIPS Conference 2025 Conference Paper

DISC: Dynamic Decomposition Improves LLM Inference Scaling

• Jonathan Li
• Wei Cheng
• Benjamin Riviere
• Yue Wu
• Masafumi Oyamada
• Mengdi Wang
• Yisong Yue
• Santiago Paternain

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually designed based on domain knowledge. We propose dynamic decomposition, a method that adaptively and automatically partitions solution and reasoning traces into manageable steps during inference. By more effectively allocating compute -- particularly through subdividing challenging steps and prioritizing their sampling -- dynamic decomposition significantly improves inference efficiency. Experiments on benchmarks such as APPS, MATH, and LiveCodeBench demonstrate that dynamic decomposition outperforms static approaches, including token-level, sentence-level, and single-step decompositions, reducing the pass@10 error rate by 5. 0%, 6. 7%, and 10. 5% respectively. These findings highlight the potential of dynamic decomposition to improve a wide range of inference scaling techniques.

AAAI Conference 2025 Conference Paper

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

• Xun Huang
• Ziyu Xu
• Hai Wu
• Jinlong Wang
• Qiming Xia
• Yan Xia
• Jonathan Li
• Kyle Gao

LiDAR-based 3D object detection is crucial for autonomous driving. However, due to the quality deterioration of LiDAR point clouds, it suffers from performance degradation in adverse weather conditions. Fusing LiDAR with the weatherrobust 4D radar sensor is expected to solve this problem; however, it faces challenges of significant differences in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR proposes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) modules to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and IntraModal ({IM}2) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in realworld adverse weather conditions.

AAAI Conference 2025 Short Paper

Robust and Adaptive AI Models for Medication Usage Forecasting Using ICD-9/10 Code (Student Abstract)

• Jonathan Li

Accurate forecasting of medication usage and ICD-9/10 code streams is critical for optimizing medical logistics, especially during periods of high demand, such as pandemics, disease outbreaks, wartime, or natural disasters. In this study, we develop a novel and robust forecasting framework using unsupervised learning techniques and Natural Language Processing (NLP) methods to build vector representations of daily ICD-9/10 codes and medication daily usage from Electronic Health Record (EHR) data. Multiple forecasting models, including Linear Drift Model, Vector Autoregression (VAR), Temporal Fusion Transformer (TFT), and Autoregressive Long Short-Term Memory (AR-LSTM) are trained, tested and evaluated. Finally multiple TFT and AR-LSTM models with different lookback horizon are trained and ensembled together to achieve better forecasting accuracy in near further (10 days). The AI framework is validated using MIMIC-IV ER and MIMIC-III datasets, resulting in the average forecasting error 5.2% at 5-th day and 18.1% at the 10-th day. The results demonstrate the ensemble model’s superior performance on near-future medication usage forecasting and ICD code progression, offering valuable insights for healthcare logistics and decision making. The framework also provides the mechanism to detect the model drift and finetune the model if necessary, which offers a robust tool for managing healthcare logistics under extreme and fluctuating conditions.

NeurIPS Conference 2024 Conference Paper

Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration

• Kezheng Xiong
• Haoen Xiang
• Qingshan Xu
• Chenglu Wen
• Siqi Shen
• Jonathan Li
• Cheng Wang

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for costly pose annotations. However, they fail to establish reliable optimization objectives for unsupervised training, either relying on overly strong geometric assumptions, or suffering from poor-quality pseudo-labels due to inadequate integration of low-level geometric and high-level contextual information. We have observed that in the feature space, latent new inlier correspondences tend to clusteraround respective positive anchors that summarize features of existing inliers. Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining. Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels by considering both high-level feature representations and low-level geometric cues. Furthermore, we propose Anchor-Based Contrastive Learning to facilitate contrastive learning with anchors for a robust feature space. Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario. Extensive experiments on KITTI and nuScenes datasets demonstrate that our INTEGER achieves competitive performance in terms of accuracy and generalizability.

IJCAI Conference 2022 Conference Paper

TopoSeg: Topology-aware Segmentation for Point Clouds

• Weiquan Liu
• Hanyun Guo
• Weini Zhang
• Yu Zang
• Cheng Wang
• Jonathan Li

Point cloud segmentation plays an important role in AI applications such as autonomous driving, AR, and VR. However, previous point cloud segmentation neural networks rarely pay attention to the topological correctness of the segmentation results. In this paper, focusing on the perspective of topology awareness. First, to optimize the distribution of segmented predictions from the perspective of topology, we introduce the persistent homology theory in topology into a 3D point cloud deep learning framework. Second, we propose a topology-aware 3D point cloud segmentation module, TopoSeg. Specifically, we design a topological loss function embedded in TopoSeg module, which imposes topological constraints on the segmentation of 3D point clouds. Experiments show that our proposed TopoSeg module can be easily embedded into the point cloud segmentation network and improve the segmentation performance. In addition, based on the constructed topology loss function, we propose a topology-aware point cloud edge extraction algorithm, which is demonstrated that has strong robustness.

IJCAI Conference 2021 Conference Paper

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

• Sen Deng
• Yidan Feng
• Mingqiang Wei
• Haoran Xie
• Yiping Chen
• Jonathan Li
• Xiao-Ping Zhang
• Jing Qin

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.

IJCAI Conference 2019 Conference Paper

Generalized Zero-Shot Vehicle Detection in Remote Sensing Imagery via Coarse-to-Fine Framework

• Hong Chen
• Yongtan Luo
• Liujuan Cao
• Baochang Zhang
• Guodong Guo
• Cheng Wang
• Jonathan Li
• Rongrong Ji

Vehicle detection and recognition in remote sensing images are challenging, especially when only limited training data are available to accommodate various target categories. In this paper, we introduce a novel coarse-to-fine framework, which decomposes vehicle detection into segmentation-based vehicle localization and generalized zero-shot vehicle classification. Particularly, the proposed framework can well handle the problem of generalized zero-shot vehicle detection, which is challenging due to the requirement of recognizing vehicles that are even unseen during training. Specifically, a hierarchical DeepLab v3 model is proposed in the framework, which fully exploits fine-grained features to locate the target on a pixel-wise level, then recognizes vehicles in a coarse-grained manner. Additionally, the hierarchical DeepLab v3 model is beneficially compatible to combine the generalized zero-shot recognition. To the best of our knowledge, there is no publically available dataset to test comparative methods, we therefore construct a new dataset to fill this gap of evaluation. The experimental results show that the proposed framework yields promising results on the imperative yet difficult task of zero-shot vehicle detection and recognition.

AAAI Conference 2019 Short Paper

Geometric Multi-Model Fitting by Deep Reinforcement Learning

• Zongliang Zhang
• Hongbin Zeng
• Jonathan Li
• Yiping Chen
• Chenhui Yang
• Cheng Wang

This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e. g. , laser scanned point clouds). We formulate multi-model fitting problem as a sequential decision making process. We then use a deep reinforcement learning algorithm to learn the optimal decisions towards the best fitting result. In this paper, we have compared our method against the state-of-the-art on simulated data. The results demonstrated that our approach significantly reduced the number of fitting iterations.

AAAI Conference 2018 Short Paper

Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification

• Zilong Zhong
• Jonathan Li

High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.

IJCAI Conference 2018 Conference Paper

H-Net: Neural Network for Cross-domain Image Patch Matching

• Weiquan Liu
• Xuelun Shen
• Cheng Wang
• Zhihong Zhang
• Chenglu Wen
• Jonathan Li

Describing the same scene with different imaging style or rendering image from its 3D model gives us different domain images. Different domain images tend to have a gap and different local appearances, which raise the main challenge on the cross-domain image patch matching. In this paper, we propose to incorporate AutoEncoder into the Siamese network, named as H-Net, of which the structural shape resembles the letter H. The H-Net achieves state-of-the-art performance on the cross-domain image patch matching. Furthermore, we improved H-Net to H-Net++. The H-Net++ extracts invariant feature descriptors in cross-domain image patches and achieves state-of-the-art performance by feature retrieval in Euclidean space. As there is no benchmark dataset including cross-domain images, we made a cross-domain image dataset which consists of camera images, rendering images from UAV 3D model, and images generated by CycleGAN algorithm. Experiments show that the proposed H-Net and H-Net++ outperform the existing algorithms. Our code and cross-domain image dataset are available at https: //github. com/Xylon-Sean/H-Net.

EAAI Journal 2018 Journal Article

Random Barzilai–Borwein step size for mini-batch algorithms

• Zhuang Yang
• Cheng Wang
• Zhemin Zhang
• Jonathan Li

AAAI Conference 2017 Short Paper

Auto-Annotation of 3D Objects via ImageNet

• Huan Luo
• Cheng Wang
• Jonathan Li

Automatic annotation of 3D objects in cluttered scenes shows its great importance to a variety of applications. Nowadays, 3D point clouds, a new 3D representation of real-world objects, can be easily and rapidly collected by mobile LiDAR systems, e. g. RIEGL VMX-450 system. Moreover, the mobile LiDAR system can also provide a series of consecutive multi-view images which are calibrated with 3D point clouds. This paper proposes to automatically annotate 3D objects of interest in point clouds of road scenes by exploiting a multitude of annotated images in image databases, such as LabelMe and ImageNet. In the proposed method, an object detector trained on the annotated images is used to locate the object regions in acquired multi-view images. Then, based on the correspondences between multi-view images and 3D point clouds, a probabilistic graphical model is used to model the temporal, spatial and geometric constraints to extract the 3D objects automatically. A new dataset was built for evaluation and the experimental results demonstrate a satisfied performance on 3D object extraction.

AAAI Conference 2016 Conference Paper

Towards Domain Adaptive Vehicle Detection in Satellite Image by Supervised Super-Resolution Transfer

• Liujuan Cao
• Rongrong Ji
• Cheng Wang
• Jonathan Li

Vehicle detection in satellite image has attracted extensive research attentions with various emerging applications. However, the detector performance has been significantly degenerated due to the low resolutions of satellite images, as well as the limited training data. In this paper, a robust domainadaptive vehicle detection framework is proposed to bypass both problems. Our innovation is to transfer the detector learning to the high-resolution aerial image domain, where rich supervision exists and robust detectors can be trained. To this end, we first propose a super-resolution algorithm using coupled dictionary learning to “augment” the satellite image region being tested into the aerial domain. Notably, linear detection loss is embedded into the dictionary learning, which enforces the augmented region to be sensitive to the subsequent detector training. Second, to cope with the domain changes, we propose an instance-wised detection using Exemplar Support Vector Machines (E-SVMs), which well handles the intra-class and imaging variations like scales, rotations, and occlusions. With comprehensive experiments on large-scale satellite image collections, we demonstrate that the proposed framework can significantly boost the detection accuracy over several state-of-the-arts.

NeurIPS Conference 1999 Conference Paper

Mixture Density Estimation

• Jonathan Li
• Andrew Barron

Gaussian mixtures (or so-called radial basis function networks) for density estimation provide a natural counterpart to sigmoidal neu(cid: 173) ral networks for function fitting and approximation. In both cases, it is possible to give simple expressions for the iterative improve(cid: 173) ment of performance as components of the network are introduced one at a time. In particular, for mixture density estimation we show that a k-component mixture estimated by maximum likelihood (or by an iterative likelihood improvement that we introduce) achieves log-likelihood within order 1/k of the log-likelihood achievable by any convex combination. Consequences for approximation and es(cid: 173) timation using Kullback-Leibler risk are also given. A Minimum Description Length principle selects the optimal number of compo(cid: 173) nents k that minimizes the risk bound.