Author name cluster

Jiang Wu

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

EAAI Journal 2026 Journal Article

Transformer-based explicit model predictive control with variable prediction horizon

Sichao Wu
Jiang Wu
Xingyu Cao
Fawang Zhang
Guangyuan Yu
Junjie Zhao
Yue Qu
Fei Ma

Traditional online Model Predictive Control (MPC) methods often suffer from excessive computational complexity, limiting their practical deployment. Explicit MPC mitigates online computational load by pre-computing control policies offline, however, existing explicit MPC methods typically rely on simplified system dynamics and cost functions, restricting their accuracy for complex systems. This paper proposes a novel Transformer-based explicit MPC algorithm (TransMPC) capable of generating highly accurate control sequences in real-time for complex dynamic systems. The Transformer is a deep learning architecture utilizing self-attention mechanisms to process sequential data. Specifically, we formulate the MPC policy as an encoder-only Transformer leveraging bidirectional self-attention, enabling simultaneous inference of entire control sequences in a single forward pass. This design inherently accommodates variable prediction horizons while ensuring low inference latency. Furthermore, we introduce a direct policy optimization framework that alternates between sampling and learning phases. Unlike imitation-based approaches dependent on precomputed optimal trajectories, TransMPC directly optimizes the true finite-horizon cost via automatic differentiation. Random horizon sampling combined with a replay buffer provides independent and identically distributed (i. i. d.) training samples, ensuring robust generalization across varying states and horizon lengths. Extensive simulations and real-world multi-platform experiments demonstrate that TransMPC achieves up to 81. 97%–516. 74% faster inference than recurrent-based methods, while maintaining high accuracy in both tracking and manipulation tasks. Specifically, in the mobile robot trajectory tracking task, TransMPC achieves lateral tracking errors as low as 0. 008 m, along with millimeter-level positioning and sub-degree orientation accuracy on a 7-degrees of freedom drill arm.

Details DOI

EAAI Journal 2025 Journal Article

Multi-step citywide traffic flow forecasting based on multiscale spatio-temporal transformer

Shenkai Zhang
Taiyong Li
Yingqi Chen
Jiang Wu
Xiao Yan

Accurate citywide traffic flow forecasting is an essential task in intelligent transportation systems. Unlike single-step forecasting, multi-step traffic flow forecasting offers extended insights that support proactive traffic management and resource allocation over longer time horizons. This paper proposes a Multi-Step Multiscale Spatial–Temporal Transformer (MS-MSTformer) for citywide traffic flow forecasting, which leverages a multiscale patch mechanism to capture both local and global spatial dependencies while integrating temporal patterns of closeness, period, and trend. Two novel cross-attention modules, namely Patch-Temporal Cross-Attention (PTCA) and Region-Temporal Cross-Attention (RTCA) are presented. These modules utilize temporal information as the query, with PTCA and RTCA focusing on patches and regions, respectively, to effectively fuse diverse spatio-temporal features. Extensive experiments on the widely used New York City Taxi (NYCTaxi) and New York City Bike (NYCBike) datasets demonstrate the MS-MSTformer’s capability to provide accurate multi-step citywide traffic flow forecasting. Specifically, the proposed model outperforms the baseline models in 11 out of 12 evaluation scenarios. On average, MS-MSTformer improves Root Mean Square Error (RMSE) by 31. 13% and Mean Absolute Error (MAE) by 29. 22% over the deep learning baselines. In addition, the ablation study demonstrates the contributions of both PTCA and RTCA to the proposed MS-MSTformer.

Details DOI

NeurIPS Conference 2025 Conference Paper

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

Siwei Wen
Junyan Ye
Peilin Feng
Hengrui Kang
Zichen Wen
Yize Chen
Jiang Wu
Wenjun Wu

With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100, 000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https: //github. com/opendatalab/FakeVLM.

PDF Details

AAAI Conference 2025 Conference Paper

Utilize the Flow Before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning

Runchuan Zhu
Zhipeng Ma
Jiang Wu
Junyuan Gao
Jiaqi Wang
Dahua Lin
Conghui He

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as ''I don't know", RAIT enhances the reliability of LLMs and reduces their hallucination. Generally, RAIT modifies training samples based on the correctness of the initial LLM's response. However, this crude approach can cause LLMs to excessively refuse answering questions they could have correctly answered, the problem we call over-refusal. In this paper, we explore two primary causes of over-refusal: Static conflict occurs when similar samples within the LLM’s feature space receive differing supervision signals (original vs. modified ''I don't know"). Dynamic conflict arises as the LLM's evolving knowledge during SFT enables it to answer previously unanswerable questions, but the now-answerable training samples still retain the original ''I don't know" supervision signals from the initial LLM state, leading to inconsistencies. These conflicts cause the trained LLM to misclassify known questions as unknown, resulting in over-refusal. To address this issue, we introduce Certainty Represented Knowledge Flow for Refusal-Aware Instructions Tuning (CRaFT). CRaFT centers on two main contributions: First, we additionally incorporate response certainty to selectively filter and modify data, reducing static conflicts. Second, we implement preliminary rehearsal training to characterize changes in the LLM's knowledge state, which helps mitigate dynamic conflicts during the fine-tuning process. We conducted extensive experiments on open-ended question answering and multiple-choice question task. Experiment results show that CRaFT can improve LLM's overall performance during the RAIT process.

PDF Details DOI

AAAI Conference 2025 Conference Paper

VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis

Chao Pang
Xingxing Weng
Jiang Wu
Jiayu Li
Yi Liu
Jiaxing Sun
Weijia Li
Shuai Wang

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Diffusion Actor-Critic with Entropy Regulator

Yinuo Wang
Likun Wang
Yuxuan Jiang
Wenjun Zou
Tong Liu
Xujie Song
Wenxuan Wang
Liming Xiao

Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion model to fit multimodal distributions, thereby enhancing the representational capacity of the policy. Since the distribution of the diffusion policy lacks an analytical expression, its entropy cannot be determined analytically. To mitigate this, we propose a method to estimate the entropy of the diffusion policy utilizing Gaussian mixture model. Building on the estimated entropy, we can learn a parameter $\alpha$ that modulates the degree of exploration and exploitation. Parameter $\alpha$ will be employed to adaptively regulate the variance of the added noise, which is applied to the action output by the diffusion model. Experimental trials on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting a stronger representational capacity of the diffusion policy.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment

Jiahao Liu
Jiang Wu
Jinyu Chen
Miao Hu
Yipeng Zhou
Di Wu

Different from conventional federated learning, personalized federated learning (PFL) is able to train a customized model for each individual client according to its unique requirement. The mainstream approach is to adopt a kind of weighted aggregation method to generate personalized models, in which weights are determined by the loss value or model parameters among different clients. However, such kinds of methods require clients to download others' models. It not only sheer increases communication traffic but also potentially infringes data privacy. In this paper, we propose a new PFL algorithm called FedDWA (Federated Learning with Dynamic Weight Adjustment) to address the above problem, which leverages the parameter server (PS) to compute personalized aggregation weights based on collected models from clients. In this way, FedDWA can capture similarities between clients with much less communication overhead. More specifically, we formulate the PFL problem as an optimization problem by minimizing the distance between personalized models and guidance models, so as to customize aggregation weights for each client. Guidance models are obtained by the local one-step ahead adaptation on individual clients. Finally, we conduct extensive experiments using five real datasets and the results demonstrate that FedDWA can significantly reduce the communication traffic and achieve much higher model accuracy than the state-of-the-art approaches.

PDF Details DOI

ICLR Conference 2023 Conference Paper

SimPer: Simple Self-Supervised Learning of Periodic Targets

Yuzhe Yang 0003
Xin Liu 0034
Jiang Wu
Silviu Borac
Dina Katabi
Ming-Zher Poh
Daniel McDuff

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks with limited or no supervision is of great benefit. Yet, existing self-supervised learning (SSL) methods overlook the intrinsic periodicity in data, and fail to learn representations that capture periodic or frequency attributes. In this paper, we present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized augmentations, feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations. Extensive experiments on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains verify the superior performance of SimPer compared to state-of-the-art SSL methods, highlighting its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts.

Details

AAAI Conference 2022 Conference Paper

Hierarchical Multi-Supervision Multi-Interaction Graph Attention Network for Multi-Camera Pedestrian Trajectory Prediction

Guoliang Zhao
Yuxun Zhou
Zhanbo Xu
Yadong Zhou
Jiang Wu

Pedestrian trajectory prediction has become an essential underpinning in various human-centric applications including but not limited to autonomous vehicles, intelligent surveillance system and social robotics. Previous research endeavors mainly focus on single camera trajectory prediction (SCTP), while the problem of multi-camera trajectory prediction (MCTP) is often overly simplified into predicting presence in the next camera. This paper addresses MCTP from a more realistic yet challenging perspective, by redefining the task as a joint estimation of both future destination and possible trajectory. As such, two major efforts are devoted to facilitating related research and advancing modeling techniques. Firstly, we establish a comprehensive multi-camera Scenes Pedestrian Trajectory Dataset (mcScenes), which is collected from a real-world multi-camera space combined with thorough human interaction annotations and carefully designed evaluation metrics. Secondly, we propose a novel joint prediction framework, namely HM3 GAT, for the MCTP task by building a tailored network architecture. The core idea behind HM3 GAT is a fusion of topological and trajectory information that are mutually beneficial to the prediction of each task, achieved by deeply customized networks. The proposed framework is comprehensively evaluated on the mcScenes dataset with multiple ablation experiments. Status-of-the-art SCTP models are adopted as baselines to further validate the advantages of our method in terms of both information fusion and technical improvement. The mcScenes dataset, the HM3 GAT, and alternative models are made publicly available for interested readers.

PDF Details