Author name cluster

Jiaqi Chen

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.

17 papers

2 author rows

TAAS Journal 2026 Journal Article

A Novel Physics-Informed Federated Learning Framework for Robust Bearing Fault Diagnosis

Jiaqi Chen
Jie Wang
Yongquan Jiang
ZhengHong Wang
Fan Zhang
Yan Yang

Rolling bearing failures are a primary cause of catastrophic machinery breakdowns, posing significant economic and safety risks. Effective fault diagnosis is frequently hindered by challenges inherent to modern industrial settings, including data privacy constraints, statistical heterogeneity across Non-Independent and Identically Distributed (Non-IID) datasets, and the prevalence of few-shot learning scenarios. To address these challenges, this paper introduces CARR-MgNet, a novel physics-informed federated learning framework. The framework utilizes a M ulti- g ranularity fusion Net work (MgNet) backbone, which enhances feature robustness by embedding physical fault characteristics directly into its convolutional kernels. To ensure stable federated training across heterogeneous clients, we then introduce a C lass- A verage R epresentation R egularization (CARR) mechanism to effectively mitigate client drift. Extensive experiments on four public industrial datasets validate the state-of-the-art performance of our proposed framework. Under challenging non-IID conditions, CARR-MgNet surpasses established baselines, including FedProx and MOON, by up to 8.2% in accuracy. Furthermore, it reduces the number of communication rounds required to reach 95% accuracy by 40% compared to FedAvg and reduces total communication overhead by 35%. These results demonstrate that our physics-informed federated approach provides a robust, communication-efficient, and privacy-preserving solution for real-world industrial fault diagnosis.

Details DOI

AAAI Conference 2025 Conference Paper

Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation

Jiaqi Chen
Bingqian Lin
Xinmin Liu
Lin Ma
Xiaodan Liang
Kwan-Yee K. Wong

LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined navigation graphs for movements, overlooking low-level control in navigation scenarios. To bridge this gap, we propose AO-Planner, a novel Affordances-Oriented Planner for continuous VLN task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making, both performed in a zero-shot setting. Specifically, we employ a Visual Affordances Prompting (VAP) approach, where the visible ground is segmented by SAM to provide navigational affordances, based on which the LLM selects potential candidate waypoints and plans low-level paths towards selected waypoints. We further propose a high-level PathAgent which marks planned paths into the image input and reasons the most probable path by comprehending all environmental information. Finally, we convert the selected path into 3D coordinates using camera intrinsic parameters and depth information, avoiding challenging 3D predictions for LLMs. Experiments on the challenging R2R-CE and RxR-CE datasets show that AO-Planner achieves state-of-the-art zero-shot performance (8.8% improvement on SPL). Our method can also serve as a data annotator to obtain pseudo-labels, distilling its waypoint prediction ability into a learning-based predictor. This new predictor does not require any waypoint data from the simulator and achieves 47% SR competing with supervised methods. We establish an effective connection between LLM and 3D world, presenting novel prospects for employing foundation models in low-level motion control.

PDF Details DOI

ICLR Conference 2025 Conference Paper

AFlow: Automating Agentic Workflow Generation

Jiayi Zhang 0017
Jinyu Xiang
Zhaoyang Yu 0004
Fengwei Teng
Xionghui Chen
Jiaqi Chen
Mingchen Zhuge
Xin Cheng

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFLOW, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFLOW's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFLOW enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/FoundationAgents/AFlow.

Details

AAAI Conference 2025 Conference Paper

Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

Jiaqi Chen
Xiaoye Zhu
Tianyang Liu
Ying Chen
Chen Xinhui
Yiwen Yuan
Chak Tou Leong
Zuchao Li

Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Although past methods have achieved good performance on detecting pure machine-generated text, those detectors have poor performance on distinguishing machine-revised text (rewriting, expansion, and polishing), which can have only minor changes from its original human prompt. As the content of text may originate from human prompts, detecting machine-revised text often involves identifying distinctive machine styles, e.g., worded favored by LLMs. However, existing methods struggle to detect machine-style phrasing hidden within the content contributed by humans. We propose the “Imitate Before Detect” (ImBD) approach, which first imitates the machine-style token distribution, and then compares the distribution of the text to be tested with the machine-style distribution to determine whether the text has been machine-revised. To this end, we introduce Style Preference Optimization (SPO), which aligns a scoring LLM model to the preference of text styles generated by machines. The aligned scoring model is then used to calculate the style-conditional probability curvature (Style-CPC), quantifying the log probability difference between the original and conditionally sampled texts for effective detection. We conduct extensive comparisons across various scenarios, encompassing text revisions by six LLMs, four distinct text domains, and three machine revision types. Compared to existing state-of-the-art methods, our method yields a 13% increase in AUC for detecting text revised by open-source LLMs, and improves performance by 5% and 19% for detecting GPT-3.5 and GPT-4o revised text, respectively. Notably, our method surpasses the commercially trained GPT-Zero with just 1,000 samples and five minutes of SPO, demonstrating its efficiency and effectiveness.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Learning Spatial-Aware Manipulation Ordering

Yuxiang Yan
Zhiyuan Zhou
Xin Gao
Guanghao Li
Shenglin Li
Jiaqi Chen
Qunyan Pu
Jian Pu

Manipulation in cluttered environments is challenging due to spatial dependencies among objects, where an improper manipulation order can cause collisions or blocked access. Existing approaches often overlook these spatial relationships, limiting their flexibility and scalability. To address these limitations, we propose OrderMind, a unified spatial-aware manipulation ordering framework that directly learns object manipulation priorities based on spatial context. Our architecture integrates a spatial context encoder with a temporal priority structuring module. We construct a spatial graph using k-Nearest Neighbors to aggregate geometric information from the local layout and encode both object-object and object-manipulator interactions to support accurate manipulation ordering in real-time. To generate physically and semantically plausible supervision signals, we introduce a spatial prior labeling method that guides a vision-language model to produce reasonable manipulation orders for distillation. We evaluate OrderMind on our Manipulation Ordering Benchmark, comprising 163, 222 samples of varying difficulty. Extensive experiments in both simulation and real-world environments demonstrate that our method significantly outperforms prior approaches in effectiveness and efficiency, enabling robust manipulation in cluttered scenes.

PDF Details

RLJ Journal 2025 Journal Article

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

Jiaqi Chen
Ji Shi
Cansu Sancaktar
Jonas Frey
Georg Martius

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradigms in model-based settings, conducting experiments on 31 different environments. First, we showcase that online agents outperform their offline counterparts. We identify a key challenge behind performance degradation of offline agents: encountering Out-Of-Distribution states at test time. This issue arises because, without the self-correction mechanism in online agents, offline datasets with limited state space coverage induce a mismatch between the agent's imagination and real rollouts, compromising policy training. We demonstrate that this issue can be mitigated by allowing for additional online interactions in a fixed or adaptive schedule, restoring the performance of online training with limited interaction data. We also showcase that incorporating exploration data helps mitigate the performance degradation of offline agents. Based on our insights, we recommend adding exploration data when collecting large datasets, as current efforts predominantly focus on expert data alone.

PDF Details

RLC Conference 2025 Conference Paper

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

Jiaqi Chen
Ji Shi
Cansu Sancaktar
Jonas Frey
Georg Martius

PDF Details

EAAI Journal 2025 Journal Article

Real-time asphalt pavement ice detection and annotation with a Transformer-based model framework

Jiaqi Chen
Huaqiang Wang
Yueyan Li
Shujun Yu

Road icing is a common weather-related traffic hazard in cold winters, which increases the risk of traffic accidents. Traditional road ice detectors often damage road structures and are prone to interference. This paper develops a non-destructive ice detection model framework implemented based on the Transformer. The framework uses transfer learning to train high-accuracy transformer-based model. The framework sequentially integrates image classification and segmentation models to analyze the severity of asphalt pavement icing. The classification model (Swin Transformer) first classifies road conditions into dry, wet, or icy categories. Then, Masked-attention Mask Transformer (Mask2Former) segmentation model only annotates icy regions in the images, improving operational efficiency. The models were trained and validated on 4200 field images. The impact of training data volume on model performance, as well as the interference of road signs and cracks on model detection, was analyzed. Results show that the detection model demonstrated an accuracy of 98. 5% in identifying icy roads. The annotation model achieved an Intersection over Union (IoU) score of 94. 8% for icy regions, with a processing speed of 3. 48 frames per second (FPS). To achieve the optimal performance, at least 1800 field images should be used for training the road icing detection model and annotation model. Road signs lead to a 6. 77% decrease in the overall accuracy of the ice detection framework, while the impact of road cracks on the model is relatively minor. The framework presented in this paper is useful for transportation agencies in winter de-icing operations.

Details DOI

NeurIPS Conference 2025 Conference Paper

SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning

Kun Xiang
Heng Li
Terry Jingchen Zhang
Yinya Huang
Zirong Liu
Peixin Qu
Jixi He
Jiaqi Chen

We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fundamental domains spanning the physics discipline, incorporating 21 categories of highly heterogeneous diagrams. In contrast to prior works where visual elements mainly serve auxiliary purposes, our benchmark features a substantial proportion of vision-essential problems (75%) that mandate visual information extraction for correct solutions. Through extensive evaluation, we observe that even the most advanced visual reasoning models (e. g. , Gemini-2. 5-pro and o4-mini) achieve sub-60% accuracy on our benchmark. These results reveal fundamental challenges in current large language models' visual understanding capabilities, particularly in: (i) establishing rigorous coupling between diagram interpretation and physics reasoning, and (ii) overcoming their persistent reliance on textual cues as cognitive shortcuts. Project Page: github. com/SeePhys/seephys-projectHugging Face: huggingface. co/datasets/SeePhys/SeePhys

PDF Details

NeurIPS Conference 2025 Conference Paper

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

Jiaqi Chen
Bang Zhang
Ruotian Ma
Peisong Wang
Xiaodan Liang
Zhaopeng Tu
Xiaolong Li
Kwan-Yee K. Wong

Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce Self-Play Critic (SPC), a novel approach where a critic model evolves its ability to assess reasoning steps through adversarial self-play games, eliminating the need for manual step-level annotation. SPC involves fine-tuning two copies of a base model to play two roles, namely a "sneaky generator" that deliberately produces erroneous steps designed to be difficult to detect, and a "critic" that analyzes the correctness of reasoning steps. These two models engage in an adversarial game in which the generator aims to fool the critic, while the critic model seeks to identify the generator's errors. Using reinforcement learning based on the game outcomes, the models iteratively improve; the winner of each confrontation receives a positive reward and the loser receives a negative reward, driving continuous self-evolution. Experiments on three reasoning process benchmarks (ProcessBench, PRM800K, DeltaBench) demonstrate that our SPC progressively enhances its error detection capabilities (e. g. , accuracy increases from 70. 8% to 77. 7% on ProcessBench) and surpasses strong baselines, including distilled R1 model. Furthermore, SPC can guide the test-time search of diverse LLMs and significantly improve their mathematical reasoning performance on MATH500 and AIME2024, surpassing those guided by state-of-the-art process reward models.

PDF Details

NeurIPS Conference 2025 Conference Paper

Switchable Token-Specific Codebook Quantization For Face Image Compression

Yongbo Wang
Haonan Wang
Guodong Mu
Ruixin Zhang
Jiaqi Chen
Jingyun Zhang
Jun Wang
Yuan Xie

With the ever-increasing volume of visual data, the efficient and lossless transmission, along with its subsequent interpretation and understanding, has become a critical bottleneck in modern information systems. The emerged codebook-based solution utilize a globally shared codebook to quantize and dequantize each token, controlling the bpp by adjusting the number of tokens or the codebook size. However, for facial images—which are rich in attributes—such global codebook strategies overlook both the category-specific correlations within images and the semantic differences among tokens, resulting in suboptimal performance, especially at low bpp. Motivated by these observations, we propose a Switchable Token-Specific Codebook Quantization for face image compression, which learns distinct codebook groups for different image categories and assigns an independent codebook to each token. By recording the codebook group to which each token belongs with a small number of bits, our method can reduce the loss incurred when decreasing the size of each codebook group. This enables a larger total number of codebooks under a lower overall bpp, thereby enhancing the expressive capability and improving reconstruction performance. Owing to its generalizable design, our method can be integrated into any existing codebook-based representation learning approach and has demonstrated its effectiveness on face recognition datasets, achieving an average accuracy of 93. 51\% for reconstructed images at 0. 05 bpp.

PDF Details

ICRA Conference 2024 Conference Paper

A 3D Mixed Reality Interface for Human-Robot Teaming

Jiaqi Chen
Boyang Sun
Marc Pollefeys
Hermann Blum

This paper presents a mixed-reality human-robot teaming system. It allows human operators to see in real-time where robots are located, even if they are not in line of sight. The operator can also visualize the map that the robots create of their environment and can easily send robots to new goal positions. The system mainly consists of a mapping and a control module. The mapping module is a real-time multi-agent visual SLAM system that co-localizes all robots and mixed-reality devices to a common reference frame. Visualizations in the mixed-reality device then allow operators to see a virtual life-sized representation of the cumulative 3D map overlaid onto the real environment. As such, the operator can effectively "see through" walls into other rooms. To control robots and send them to new locations, we propose a drag-and-drop interface. An operator can grab any robot hologram in a 3D mini map and drag it to a new desired goal pose. We validate the proposed system through a user study and real-world deployments. We make the mixed-reality application publicly available at github.com/cvg/HoloLens_ros.

Details

JBHI Journal 2024 Journal Article

LHAR: Lightweight Human Activity Recognition on Knowledge Distillation

Shizhuo Deng
Jiaqi Chen
Da Teng
Chuangui Yang
Dongyue Chen
Tong Jia
Hao Wang

Sensor-based Human Activity Recognition (HAR) is widely used in daily life and is the basic-level bridge to virtual healthcare in the metaverse. The current challenge is the low recognition accuracy for personalized users on smart wearable devices. The limited resource cannot support large deep learning models updated locally. Besides, integrating and transmitting sensor data to the cloud would reduce the efficiency. Considering the tradeoff between performance and complexity, we propose a Lightweight Human Activity Recognition (LHAR) framework. In LHAR, we combine the cross-people HAR task with the lightweight model task. LHAR framework is designed on the teacher-student architecture and the student network consists of multiple depthwise separable convolution layers to achieve fewer parameters. The dark knowledge distilled from the complex teacher model enhances the generalization ability of LHAR. To achieve effective knowledge distillation, we propose two optimization methods. Firstly, we train the teacher model by ensemble learning to promote teacher performance. Secondly, a multi-channel data augmentation method is proposed for the diversity of the dataset, which is a plug-in operation for the ensemble teacher model. In the experiments, we compare LHAR with state-of-art models in comparison evaluation, ablation study and the hyperparameter analysis, which proves the better performance of LHAR in efficiency and effectiveness.

Details DOI

EAAI Journal 2024 Journal Article

Non-MapReduce computing for intelligent big data analysis

Xudong Sun
Lingxiang Zhao
Jiaqi Chen
Yongda Cai
Dingming Wu
Joshua Zhexue Huang

MapReduce is a popular paradigm in distributed computing, but it is not efficient when executing iterative algorithms over a distributed big dataset due to its heavy data communication overhead. Non-MapReduce computing is an alternative for improving computing efficiency and data scalability when using iterative algorithms to process big distributed datasets on clusters. In this paper, we investigate Non-MapReduce approach in distributed computing and use Spark implementations of machine learning algorithms to discuss the problems of MapReduce in executing iterative algorithms over a big distributed dataset and the advantages of Non-MapReduce for the same tasks. We present a method to build a new machine learning library made of sequential algorithms for distributed computing. We use experiment results to show comparisons of computing efficiency and data scalability of MapReduce and Non-MapReduce in executing six machine learning algorithms over big datasets.

Details DOI

NeurIPS Conference 2022 Conference Paper

DeepInteraction: 3D Object Detection via Modality Interaction

Zeyu Yang
Jiaqi Chen
Zhenwei Miao
Wei Li
Xiatian Zhu
Li Zhang

Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Experiments on the large-scale nuScenes dataset show that our proposed method surpasses all prior arts often by a large margin. Crucially, our method is ranked at the first position at the highly competitive nuScenes object detection leaderboard.

PDF Details

NeurIPS Conference 2021 Conference Paper

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

Pan Lu
Liang Qiu
Jiaqi Chen
Tanglin Xia
Yizhou Zhao
Wei Zhang
Zhou Yu
Xiaodan Liang

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107, 439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspired by real-world diagram word problems that highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning. Thus, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning. To facilitate potential IconQA models to learn semantic representations for icon images, we further release an icon dataset Icon645 which contains 645, 687 colored icons on 377 classes. We conduct extensive user studies and blind experiments and reproduce a wide range of advanced VQA methods to benchmark the IconQA task. Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset. IconQA and Icon645 are available at https: //iconqa. github. io.

PDF Details

IROS Conference 2020 Conference Paper

Robot Calligraphy using Pseudospectral Optimal Control in Conjunction with a Novel Dynamic Brush Model

Sen Wang
Jiaqi Chen
Xuanliang Deng
Seth Hutchinson 0001
Frank Dellaert

Chinese calligraphy is a unique art form with great artistic value but difficult to master. In this paper, we formulate the calligraphy writing problem as a trajectory optimization problem, and propose an improved virtual brush model for simulating the real writing process. Our approach is inspired by pseudospectral optimal control in that we parameterize the actuator trajectory for each stroke as a Chebyshev polynomial. The proposed dynamic virtual brush model plays a key role in formulating the objective function to be optimized. Our approach shows excellent performance in drawing aesthetically pleasing characters, and does so much more efficiently than previous work, opening up the possibility to achieve real-time closed-loop control.

Details