Author name cluster

Jingwei Xu

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.

9 papers

2 author rows

ICLR Conference 2025 Conference Paper

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

Jingwei Xu
Yikai Wang 0002
Yiqun Zhao
Yanwei Fu 0001
Shenghua Gao

Unveiling an empty street from crowded observations captured by in-car cameras is crucial for autonomous driving. However, removing all temporarily static objects, such as stopped vehicles and standing pedestrians, presents a significant challenge. Unlike object-centric 3D inpainting, which relies on thorough observation in a small scene, street scene cases involve long trajectories that differ from previous 3D inpainting tasks. The camera-centric moving environment of captured videos further complicates the task due to the limited degree and time duration of object observation. To address these obstacles, we introduce StreetUnveiler to reconstruct an empty street. StreetUnveiler learns a 3D representation of the empty street from crowded observations. Our representation is based on the hard-label semantic 2D Gaussian Splatting (2DGS) for its scalability and ability to identify Gaussians to be removed. We inpaint rendered image after removing unwanted Gaussians to provide pseudo-labels and subsequently re-optimize the 2DGS. Given its temporal continuous movement, we divide the empty street scene into observed, partial-observed, and unobserved regions, which we propose to locate through a rendered alpha map. This decomposition helps us to minimize the regions that need to be inpainted. To enhance the temporal consistency of the inpainting, we introduce a novel time-reversal framework to inpaint frames in reverse order and use later frames as references for earlier frames to fully utilize the long-trajectory observations. Our experiments conducted on the street scene dataset successfully reconstructed a 3D representation of the empty street. The mesh representation of the empty street can be extracted for further applications.

Details

NeurIPS Conference 2025 Conference Paper

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving

Yuchen Zhang
Hanyue Du
Chun Cao
Jingwei Xu

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and serving, there still remains a gap in unifying fine-tuning and inference for LoRA-based models. We present **Loquetier**, a virtualized multi-LoRA framework that seamlessly integrates LoRA fine-tuning and serving within a single runtime. Loquetier introduces two key components: (1) a Virtualized Module that isolates PEFT-based modifications and supports multiple adapters on a shared base model, and (2) an optimized computation flow with a kernel design that merges fine-tuning and inference paths in forward propagation, enabling efficient batching and minimizing kernel invocation overhead. Extensive experiments across three task settings show that Loquetier consistently outperforms existing baselines in both performance and flexibility, achieving up to $3. 0\times$ the throughput of the state-of-the-art co-serving system on inference-only tasks and $46. 4\times$ higher SLO attainment than PEFT on unified fine-tuning and inference tasks. The implementation of Loquetier is publicly available at https: //github. com/NJUDeepEngine/Loquetier.

PDF Details

NeurIPS Conference 2023 Conference Paper

Neuro-symbolic Learning Yielding Logical Constraints

Zenan Li
Yunpeng Huang
Zhaoyu Li
Yuan Yao
Jingwei Xu
Taolue Chen
Xiaoxing Ma
Jian Lu

Neuro-symbolic systems combine the abilities of neural perception and logical reasoning. However, end-to-end learning of neuro-symbolic systems is still an unsolved challenge. This paper proposes a natural framework that fuses neural network training, symbol grounding, and logical constraint synthesis into a coherent and efficient end-to-end learning process. The capability of this framework comes from the improved interactions between the neural and the symbolic parts of the system in both the training and inference stages. Technically, to bridge the gap between the continuous neural network and the discrete logical constraint, we introduce a difference-of-convex programming technique to relax the logical constraints while maintaining their precision. We also employ cardinality constraints as the language for logical constraint learning and incorporate a trust region method to avoid the degeneracy of logical constraint in learning. Both theoretical analyses and empirical evaluations substantiate the effectiveness of the proposed framework.

PDF Details

NeurIPS Conference 2022 Conference Paper

A Deep Learning Dataloader with Shared Data Preparation

Jian Xie
Jingwei Xu
Guochang Wang
Yuan Yao
Zenan Li
Chun Cao
Hanghang Tong

Executing a family of Deep Neural Networks (DNNs) training jobs on the same or similar datasets in parallel is typical in current deep learning scenarios. It is time-consuming and resource-intensive because each job repetitively prepares (i. e. , loads and preprocesses) the data independently, causing redundant consumption of I/O and computations. Although the page cache or a centralized cache component can alleviate the redundancies by reusing the data prep work, each job's data sampled uniformly at random presents a low sampling locality in the shared dataset that causes the heavy cache thrashing. Prior work tries to solve the problem by enforcing all training jobs iterating over the dataset in the same order and requesting each data in lockstep, leading to strong constraints: all jobs must have the same dataset and run simultaneously. In this paper, we propose a dependent sampling algorithm (DSA) and domain-specific cache policy to relax the constraints. Besides, a novel tree data structure is designed to efficiently implement DSA. Based on the proposed technologies, we implemented a prototype system, named Joader, which can share data prep work as long as the datasets share partially. We evaluate the proposed Joader in practical scenarios, showing a greater versatility and superiority over training speed improvement (up to 500% in ResNet18).

PDF Details

JBHI Journal 2021 Journal Article

Reinventing 2D Convolutions for 3D Images

Jiancheng Yang
Xiaoyang Huang
Yi He
Jingwei Xu
Canqian Yang
Guozheng Xu
Bingbing Ni

There have been considerable debates over 2D and 3D representation learning on 3D medical images. 2D approaches could benefit from large-scale 2D pretraining, whereas they are generally weak in capturing large 3D contexts. 3D approaches are natively strong in 3D contexts, however few publicly available 3D medical dataset is large and diverse enough for universal 3D pretraining. Even for hybrid (2D + 3D) approaches, the intrinsic disadvantages within the 2D/3D parts still exist. In this study, we bridge the gap between 2D and 3D convolutions by reinventing the 2D convolutions. We propose ACS (axial-coronal-sagittal) convolutions to perform natively 3D representation learning, while utilizing the pretrained weights on 2D datasets. In ACS convolutions, 2D convolution kernels are split by channel into three parts, and convoluted separately on the three views (axial, coronal and sagittal) of 3D representations. Theoretically, ANY 2D CNN (ResNet, DenseNet, or DeepLab) is able to be converted into a 3D ACS CNN, with pretrained weight of a same parameter size. Extensive experiments validate the consistent superiority of the pretrained ACS CNNs, over the 2D/3D CNN counterparts with/without pretraining. Even without pretraining, the ACS convolution can be used as a plug-and-play replacement of standard 3D convolution, with smaller model size and less computation.

Details DOI

AAAI Conference 2020 Conference Paper

Enumerating Maximal k -Plexes with Worst-Case Time Guarantee

Yi Zhou
Jingwei Xu
Zhenyu Guo
Mingyu Xiao
Yan Jin

The problem of enumerating all maximal cliques in a graph is a key primitive in a variety of real-world applications such as community detection and so on. However, in practice, communities are rarely formed as cliques due to data noise. Hence, k-plex, a subgraph in which any vertex is adjacent to all but at most k vertices, is introduced as a relaxation of clique. In this paper, we investigate the problem of enumerating all maximal k-plexes and present FaPlexen, an enumeration algorithm which integrates the “pivot” heuristic and new branching schemes. To our best knowledge, for the ﬁrst time, FaPlexen lists all maximal k-plexes with provably worst-case running time O(n2 γn ) in a graph with n vertices, where γ < 2. Then, we propose another algorithm CommuPlex which non-trivially extends FaPlexen to ﬁnd all maximal kplexes of prescribed size for community detection in massive real-life networks. We ﬁnally carry out experiments on both real and synthetic graphs and demonstrate that our algorithms run much faster than the state-of-the-art algorithms.

PDF Details

IJCAI Conference 2018 Conference Paper

Human Motion Generation via Cross-Space Constrained Sampling

Zhongyue Huang
Jingwei Xu
Bingbing Ni

We aim to automatically generate human motion sequence from a single input person image, with some specific action label. To this end, we propose a cross-space human motion video generation network which features two paths: a forward path that first samples/generates a sequence of low dimensional motion vectors based on Gaussian Process (GP), which is paired with the input person image to form a moving human figure sequence; and a backward path based on the predicted human images to re-extract the corresponding latent motion representations. As lack of supervision, the reconstructed latent motion representations are expected to be as close as possible to the GP sampled ones, thus yielding a cyclic objective function for cross-space (i. e. , motion and appearance) mutual constrained generation. We further propose an alternative sampling/generation algorithm with respect to constraints from both spaces. Extensive experimental results show that the proposed framework successfully generates novel human motion sequences with reasonable visual quality.

PDF Details

NeurIPS Conference 2018 Conference Paper

Video Prediction via Selective Sampling

Jingwei Xu
Bingbing Ni
Xiaokang Yang

Most adversarial learning based video prediction methods suffer from image blur, since the commonly used adversarial and regression loss pair work rather in a competitive way than collaboration, yielding compromised blur effect. In the meantime, as often relying on a single-pass architecture, the predictor is inadequate to explicitly capture the forthcoming uncertainty. Our work involves two key insights: (1) Video prediction can be approached as a stochastic process: we sample a collection of proposals conforming to possible frame distribution at following time stamp, and one can select the final prediction from it. (2) De-coupling combined loss functions into dedicatedly designed sub-networks encourages them to work in a collaborative way. Combining above two insights we propose a two-stage network called VPSS (\textbf{V}ideo \textbf{P}rediction via \textbf{S}elective \textbf{S}ampling). Specifically a \emph{Sampling} module produces a collection of high quality proposals, facilitated by a multiple choice adversarial learning scheme, yielding diverse frame proposal set. Subsequently a \emph{Selection} module selects high possibility candidates from proposals and combines them to produce final prediction. Extensive experiments on diverse challenging datasets demonstrate the effectiveness of proposed video prediction approach, i. e. , yielding more diverse proposals and accurate prediction results.

PDF Details

IJCAI Conference 2015 Conference Paper

Ice-Breaking: Mitigating Cold-Start Recommendation Problem by Rating Comparison

Jingwei Xu
Yuan Yao
Hanghang Tong
Xianping Tao
Jian Lu

Recommender system has become an indispensable component in many e-commerce sites. One major challenge that largely remains open is the coldstart problem, which can be viewed as an ice barrier that keeps the cold-start users/items from the warm ones. In this paper, we propose a novel rating comparison strategy (RAPARE) to break this ice barrier. The center-piece of our RAPARE is to provide a fine-grained calibration on the latent profiles of cold-start users/items by exploring the differences between cold-start and warm users/items. We instantiate our RAPARE strategy on the prevalent method in recommender system, i. e. , the matrix factorization based collaborative filtering. Experimental evaluations on two real data sets validate the superiority of our approach over the existing methods in cold-start scenarios.

PDF Details