Author name cluster

Jiahao 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

TIST Journal 2026 Journal Article

Improving Knowledge Tracing through Multi-Source Scaling with Decoder-Only Transformers

Teng Guo
Bojun Zhan
Shuyan Huang
Jiahao Chen
Xiangyu Zhao
Mingliang Hou
Zitao Liu

Knowledge tracing (KT) is a problem of modeling students’ knowledge states to predict their future performance by observing their historical learning interactions. The collection of educational data presents significant challenges, as students’ limited learning engagement restricts the generation of large-scale interaction data, while stringent privacy regulations further limit the availability of student learning sequences from online platforms. Hence, it is crucial to enhance the capabilities of deep learning-based KT (DLKT) models by constructing large-scale datasets through the integration of student interaction data across multiple subjects and sources. The success of ChatGPT demonstrates that the decoder-only Transformer architecture is highly effective in capturing complex information from large-scale sequential data. Against this background, we propose a novel decoder-only Transformer architecture-based model, named Unified DLKT ( UniKT ), to learn coherent and unified representations across a wide range of data sources. Specifically, we combine student learning sequences from six educational scenarios and utilize a multi-source encoding to learn unified representations of interactions from mixed data. UniKT is a stack of Transformer decoder layers for handling long-term dependencies among students’ historical interactions and future performance. We evaluate UniKT on six publicly available real-world educational datasets, and experimental results demonstrate that our method outperforms the majority of existing DLKT models in terms of AUC and accuracy. Furthermore, the empirical analysis shows the strong transferability and adaptability of UniKT in learning from multiple sources. To encourage reproducible research, we make our data and code publicly available at https://pykt.org/.

Details DOI

JBHI Journal 2026 Journal Article

SwitchNet: Adaptive Distribution Switching in UNet for Brain Lesion Segmentation

Jiahao Chen
Jingwen Guan
Bowen Xin
Yichao Hao
Guanzhong Gong
Rolf Bjerkvig
Jian Wang
Xiuying Wang

Automatic brain lesion segmentation enhances diagnostic efficiency by enabling detailed texture analysis and precise delineation of tumor subregions. Multimodal MRI has improved segmentation accuracy by combining complementary information from different modalities. Conventional methods either fuse all modalities uniformly, obscuring how individual modalities contribute to specific segmentation subtasks, or predefine modality-to-subregion mappings based on prior medical knowledge. The former limits interpretability on modality contribution during training, while the latter relies on parameter-heavy architectures like cascaded subnetworks, making models struggle to adapt to varying modalities. To address these challenges, this paper proposes SwitchNet, a novel model that integrates interpretability into the training process and optimizes parameter efficiency without relying on predefined modality selection. First, we propose Adaptive Encoder and Decoder Blocks employing dynamic switching mechanisms to efficiently allocate feature space and prioritize critical subtasks. These blocks enable the model to automatically identify and utilize the most informative modalities. By strategically allocating parameters to modalities, our model optimizes overall parameter complexity while maintaining strong performance. Second, we propose a Guide-Contribution Mechanism to provide interpretability during training by quantitatively revealing the contributions of individual modalities to the segmentation process. This mechanism offers valuable insights into how the model delineates tumor subregions. SwitchNet was validated on three benchmark datasets, including BraTS 2023, ISLES 2022, and UCSF-PDGM, achieving competitive segmentation performance while significantly enhancing interpretability and maintaining parameter efficiency without extra cost. These results highlight its potential for efficient tumor segmentation and clinical explainability.

Details DOI

ICML Conference 2025 Conference Paper

Are High-Quality AI-Generated Images More Difficult for Models to Detect?

Yao Xiao
Binbin Yang
Weiyan Chen
Jiahao Chen
Zijie Cao
ZiYi Dong
Xiangyang Ji
Liang Lin

The remarkable evolution of generative models has enabled the generation of high-quality, visually attractive images, often perceptually indistinguishable from real photographs to human eyes. This has spurred significant attention on AI-generated image (AIGI) detection. Intuitively, higher image quality should increase detection difficulty. However, our systematic study on cutting-edge text-to-image generators reveals a counterintuitive finding: AIGIs with higher quality scores, as assessed by human preference models, tend to be more easily detected by existing models. To investigate this, we examine how the text prompts for generation and image characteristics influence both quality scores and detector accuracy. We observe that images from short prompts tend to achieve higher preference scores while being easier to detect. Furthermore, through clustering and regression analyses, we verify that image characteristics like saturation, contrast, and texture richness collectively impact both image quality and detector accuracy. Finally, we demonstrate that the performance of off-the-shelf detectors can be enhanced across diverse generators and datasets by selecting input patches based on the predicted scores of our regression models, thus substantiating the broader applicability of our findings. Code and data are available at https: //github. com/Coxy7/AIGI-Detection-Quality-Paradox.

Details

AAAI Conference 2025 Conference Paper

CAMH: Advancing Model Hijacking Attack in Machine Learning

Xing He
Jiahao Chen
Yuwen Pu
Qingming Li
Chunyi Zhou
Yingcai Wu
Jinbao Li
Shouling Ji

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner’s knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task’s performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task.

PDF Details DOI

ICML Conference 2025 Conference Paper

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism

Ziming Zhu
Yu Zhu 0005
Jiahao Chen
Xiaofeng Ling
Huanlei Chen
Lihua Sun

Recently, image-based 3D semantic occupancy prediction has become a hot topic in 3D scene understanding for autonomous driving. Compared with the bounding box form of 3D object detection, the ability to describe the fine-grained contours of any obstacles in the scene is the key insight of voxel occupancy representation, which facilitates subsequent tasks of autonomous driving. In this work, we propose CSV-Occ to address the following two challenges: (1) Existing methods fuse temporal information based on the attention mechanism, but are limited by high complexity. We extend the state space model to support multi-input sequence interaction and conduct temporal modeling in a cascaded architecture, thereby reducing the computational complexity from quadratic to linear. (2) Existing methods are limited by semantic ambiguity, resulting in the centers of foreground objects often being predicted as empty voxels. We enable the model to explicitly vote for the instance center to which the voxels belong and spontaneously learn to utilize the other voxel features of the same instance to update the semantics of the internal vacancies of the objects from coarse to fine. Experiments on the Occ3D-nuScenes dataset show that our method achieves state-of-the-art in camera-based 3D semantic occupancy prediction and also performs well on lidar point cloud semantic segmentation on the nuScenes dataset. Therefore, we believe that CSV-Occ is beneficial to the community and industry of autonomous vehicles.

Details

ICLR Conference 2025 Conference Paper

DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training

Yurou Liu
Jiahao Chen
Rui Jiao
Jiangmeng Li
Wenbing Huang 0001
Bing Su 0001

Denoising learning of 3D molecules learns molecular representations by imposing noises into the equilibrium conformation and predicting the added noises to recover the equilibrium conformation, which essentially captures the information of molecular force fields. Due to the specificity of Potential Energy Surfaces, the probabilities of physically reasonable noises for each atom in different molecules are different. However, existing methods apply the shared heuristic hand-crafted noise sampling strategy to all molecules, resulting in inaccurate force field learning. In this paper, we propose a novel 3D molecular pre-training method, namely DenoiseVAE, which employs a Noise Generator to acquire atom-specific noise distributions for different molecules. It utilizes the stochastic reparameterization technique to sample noisy conformations from the generated distributions, which are inputted into a Denoising Module for denoising. The Noise Generator and the Denoising Module are jointly learned in a manner conforming with the paradigm of Variational Auto Encoder. Consequently, the sampled noisy conformations can be more diverse, adaptive, and informative, and thus DenoiseVAE can learn representations that better reveal the molecular force fields. Extensive experiments show that DenoiseVAE outperforms the current state-of-the-art methods on various molecular property prediction tasks, demonstrating the effectiveness of it.

Details

AAAI Conference 2025 Conference Paper

Enhancing Adversarial Transferability with Adversarial Weight Tuning

Jiahao Chen
Zhou Feng
Rui Zeng
Yuwen Pu
Chunyi Zhou
Yi Jiang
Yuyou Gan
Jinbao Li

Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that mislead the model while appearing benign to human observers. A critical concern is the transferability of AEs, which enables black-box attacks without direct access to the target model. However, many previous attacks have failed to explain the intrinsic mechanism of adversarial transferability, lacking a unified and representative metric for transferability as well. In this paper, we rethink the property of transferable AEs and develop a novel metric to measure transferability from the perspective of generalization. Building on insights from this metric, we analyze the generalization of AEs across models with different architectures and prove that we can find a local perturbation to mitigate the gap between surrogate and target models. We further establish the inner connections between model smoothness and flat local maxima, both of which contribute to the transferability of AEs. Further, we propose a new adversarial attack algorithm, Adversarial Weight Tuning (AWT), which adaptively adjusts the parameters of the surrogate model using generated AEs to optimize the flat local maxima and model smoothness simultaneously, without the need for extra data. AWT is a data-free tuning method that combines gradient-based and model-related attack methods to enhance the transferability of AEs. Extensive experiments on a variety of models with different architectures on ImageNet demonstrate that AWT yields superior performance over other attacks, with an average increase of nearly 5% and 10% attack success rates on CNN-based and Transformer-based models, respectively, compared to state-of-the-art attacks.

PDF Details DOI

IROS Conference 2025 Conference Paper

ExFace: Expressive Facial Control for Humanoid Robots with Diffusion Transformers and Bootstrap Training

Dong Zhang
Jingwei Peng
Yuyang Jiao
Jiayuan Gu
Jingyi Yu 0001
Jiahao Chen

This paper presents a novel Expressive Facial Control (ExFace) method based on Diffusion Transformers, which achieves precise mapping from human facial blendshapes to bionic robot motor control. By incorporating an innovative model bootstrap training strategy, our approach not only generates high-quality facial expressions but also significantly improves accuracy and smoothness. Experimental results demonstrate that the proposed method outperforms previous methods in terms of accuracy, frames per second (FPS), and response time. Furthermore, we develop the ExFace dataset driven by human facial data. ExFace shows excellent real-time performance and natural expression rendering in applications such as robot performances and human-robot interactions, offering a new solution for bionic robot interaction.

Details

ICRA Conference 2025 Conference Paper

Knowledge-Driven Visual Target Navigation: Dual Graph Navigation

Shiyao Li
Ziyang Meng
Jiansong Pei
Jiahao Chen
Bingcheng Dong
Guangsheng Li
Shenglan Liu 0001
Feilong Wang

In unknown environments, navigating a robot by a given image to a specific location or instance is critical and challenging. The existing end-to-end approaches require simultaneous implicit learning of multiple subtasks, and modular approaches depend on metric information. Both approaches face high computational demands, often leading to difficulties in real-time updates and limited generalization, making them challenging to implement on resource-constrained devices. To address these challenges, we propose Dual Graph Navigation (DGN), a knowledge-driven, lightweight image instance navigation framework. DGN builds an External Knowledge Graph (EKG) from small-scale datasets to capture prior object correlations, efficiently guiding target exploration. During exploration, DGN builds an Internal Knowledge Graph (IKG) using an instance-aware module, which records explored objects based on reachability relationships rather than precise metric information. The IKG dynamically updates the EKG, enhancing the robot's adaptability to the current environment. Together, they realize topological perception and reduce computational overhead. Furthermore, unlike approaches characterized by over-dependence between components, DGN employs a plug-and-play modular design that allows independent training and flexible replacement of functional modules, effectively enhancing generalization performance while reducing training and deployment costs. Experiments illustrate that DGN generalizes well in different simulation environments (AI2-THOR, Habitat), achieving state-of-the-art performance on the ProcTHOR-10K dataset. It is compatible with three distinct real-world robot platforms, including edge computing devices without CUDA support. It exhibits a decision-making speed of 3. 8 to 5. 5 times over baseline methods. Further details can be found on the project page: https://dogplanningloyo.github.io/DGN/.

Details

ICML Conference 2025 Conference Paper

Rethinking the Bias of Foundation Model under Long-tailed Distribution

Jiahao Chen
Bin Qin 0001
Jiangmeng Li
Hao Chen 0102
Bing Su 0001

Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as parameter imbalance and data imbalance. During fine-tuning, we observe that parameter imbalance plays a more critical role, while data imbalance can be mitigated using existing re-balancing strategies. Moreover, we find that parameter imbalance cannot be effectively addressed by current re-balancing techniques, such as adjusting the logits, during training, unlike data imbalance. To tackle both imbalances simultaneously, we build our method on causal learning and view the incomplete semantic factor as the confounder, which brings spurious correlations between input samples and labels. To resolve the negative effects of this, we propose a novel backdoor adjustment method that learns the true causal effect between input samples and labels, rather than merely fitting the correlations in the data. Notably, we achieve an average performance increase of about 1. 67% on each dataset.

Details

AAAI Conference 2024 Conference Paper

Improving Open-Domain Dialogue Response Generation with Multi-Source Multilingual Commonsense Knowledge

Sixing Wu
Jiong Yu
Jiahao Chen
Xiaofan Deng
Wei Zhou

Knowledge-grounded Dialogue Response Generation (KRG) can facilitate informative and fidelity dialogues using external knowledge. Prior monolingual works can only use the knowledge of the corresponding native language. Thus, due to the prohibitive costs of collecting and constructing external knowledge bases, the limited scale of accessible external knowledge always constrains the ability of KRG, especially in low-resource language scenarios. To this end, we propose a new task, Multi-Source Multilingual Knowledge-Grounded Response Generation (MMKRG), which simultaneously uses multiple knowledge sources of different languages. We notice that simply combining knowledge of different languages is inefficient due to the Cross-Conflict issue and Cross-Repetition issue. Thus, we propose a novel approach MMK-BART, which uses a simple but elegant Estimate-Cluster-Penalize mechanism to overcome the mentioned issues and adopts the multilingual language model mBART as the backbone. Meanwhile, based on the recent multilingual corpus XDailyDialog, we propose an MMKRG dataset MMK-DailyDialog, which has been aligned to the large-scale multilingual commonsense knowledge base ConceptNet and supports four languages (English, Chinese, German, and Italian). Extensive experiments have verified the effectiveness of our dataset and approach in monolingual, cross-lingual, and multilingual scenarios.

PDF Details DOI

IROS Conference 2024 Conference Paper

Preliminary Result of Cury: A Backdrivable Leg Design Using Linear Actuators

Zhongtao Guan
Yiming Chen
Junlei Zhu
Yu Hu
Weibang Bai
Jiahao Chen

This paper reports the design, simulation, and experiment of a robotic leg prototype named Cury, which has the potential to achieve minimal clearance and excellent backdrivability. Inspired by human walking data, the actuator design incorporates four-bar linkages and ball screws and is further optimized to meet the torque requirement. The Webots simulation is used to obtain the closed-loop chain description of the robotic leg from fits the URDF specification, and this simulation is used to assess the actuator output requirements at a given predefined trajectory. Leveraging customized ac motors and drives, Cury demonstrates satisfactory trajectory tracking performance using a simple controller. The motor drive design files and Webots simulation files are open-sourced.

Details

TMLR Journal 2023 Journal Article

Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale with MinDiff Loss

Akshaj Kumar Veldanda
Ivan Brugere
Jiahao Chen
Sanghamitra Dutta
Alan Mishler
Siddharth Garg

Prior work has observed that the test error of state-of-the-art deep neural networks often continues to decrease with increasing over-parameterization, a phenomenon referred to as double descent. This allows deep learning engineers to instantiate large models without having to worry about over-fitting. Despite its benefits, however, prior work has shown that over-parameterization can exacerbate bias against minority subgroups. Several fairness-constrained DNN training methods have been proposed to address this concern. Here, we critically examine MinDiff, a fairness-constrained training procedure implemented within TensorFlow's Responsible AI Toolkit, that aims to achieve Equality of Opportunity. We show that although MinDiff improves fairness for under-parameterized models, it is likely to be ineffective in the over-parameterized regime. This is because an overfit model with zero training loss is trivially group-wise fair on training data, creating an “illusion of fairness,” thus turning off the MinDiff optimization (this will apply to any disparity-based measures which care about errors or accuracy; while it won’t apply to demographic parity). We find that within specified fairness constraints, under-parameterized MinDiff models can even have lower error compared to their over-parameterized counterparts (despite baseline over-parameterized models having lower error compared to their under-parameterized counterparts). We further show that MinDiff optimization is very sensitive to choice of batch size in the under-parameterized regime. Thus, fair model training using MinDiff requires time-consuming hyper-parameter searches. Finally, we suggest using previously proposed regularization techniques, viz. L2, early stopping and flooding in conjunction with MinDiff to train fair over-parameterized models. In our results, over-parameterized models trained using MinDiff+regularization with standard batch sizes are fairer than their under-parameterized counterparts, suggesting that at the very least, regularizers should be integrated into fair deep learning flows, like MinDiff.

PDF Details

AAAI Conference 2023 Conference Paper

Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations

Jiahao Chen
Zitao Liu
Shuyan Huang
Qiongqiong Liu
Weiqi Luo

Knowledge tracing (KT) is a crucial technique to predict students’ future performance by observing their historical learning processes. Due to the powerful representation ability of deep neural networks, remarkable progress has been made by using deep learning techniques to solve the KT problem. The majority of existing approaches rely on the homogeneous question assumption that questions have equivalent contributions if they share the same set of knowledge components. Unfortunately, this assumption is inaccurate in real-world educational scenarios. Furthermore, it is very challenging to interpret the prediction results from the existing deep learning based KT models. Therefore, in this paper, we present QIKT, a question-centric interpretable KT model to address the above challenges. The proposed QIKT approach explicitly models students’ knowledge state variations at a ﬁne-grained level with question-sensitive cognitive representations that are jointly learned from a question-centric knowledge acquisition module and a question-centric problem solving module. Meanwhile, the QIKT utilizes an item response theory based prediction layer to generate interpretable prediction results. The proposed QIKT model is evaluated on three public real-world educational datasets. The results demonstrate that our approach is superior on the KT prediction task, and it outperforms a wide range of deep learning based KT models in terms of prediction accuracy with better model interpretability. To encourage reproducible results, we have provided all the datasets and code at https://pykt.org/.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information

Zitao Liu
Qiongqiong Liu
Teng Guo
Jiahao Chen
Shuyan Huang
Xiangyu Zhao
Jiliang Tang
Weiqi Luo

Knowledge tracing (KT) is a task that predicts students' future performance based on their historical learning interactions. With the rapid development of deep learning techniques, existing KT approaches follow a data-driven paradigm that uses massive problem-solving records to model students' learning processes. However, although the educational contexts contain various factors that may have an influence on student learning outcomes, existing public KT datasets mainly consist of anonymized ID-like features, which may hinder the research advances towards this field. Therefore, in this work, we present, \emph{XES3G5M}, a large-scale dataset with rich auxiliary information about questions and their associated knowledge components (KCs)\footnote{\label{ft: kc}A KC is a generalization of everyday terms like concept, principle, fact, or skill. }. The XES3G5M dataset is collected from a real-world online math learning platform, which contains 7, 652 questions, and 865 KCs with 5, 549, 635 interactions from 18, 066 students. To the best of our knowledge, the XES3G5M dataset not only has the largest number of KCs in math domain but contains the richest contextual information including tree structured KC relations, question types, textual contents and analysis and student response timestamps. Furthermore, we build a comprehensive benchmark on 19 state-of-the-art deep learning based knowledge tracing (DLKT) models. Extensive experiments demonstrate the effectiveness of leveraging the auxiliary information in our XES3G5M with DLKT models. We hope the proposed dataset can effectively facilitate the KT research work.

PDF Details

NeurIPS Conference 2022 Conference Paper

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

Zitao Liu
Qiongqiong Liu
Jiahao Chen
Shuyan Huang
Jiliang Tang
Weiqi Luo

Knowledge tracing (KT) is the task of using students' historical learning interaction data to model their knowledge mastery over time so as to make predictions on their future interaction performance. Recently, remarkable progress has been made of using various deep learning techniques to solve the KT problem. However, the success behind deep learning based knowledge tracing (DLKT) approaches is still left somewhat unknown and proper measurement and analysis of these DLKT approaches remain a challenge. First, data preprocessing procedures in existing works are often private and custom, which limits experimental standardization. Furthermore, existing DLKT studies often differ in terms of the evaluation protocol and are far away real-world educational contexts. To address these problems, we introduce a comprehensive python based benchmark platform, \textsc{pyKT}, to guarantee valid comparisons across DLKT methods via thorough evaluations. The \textsc{pyKT} library consists of a standardized set of integrated data preprocessing procedures on 7 popular datasets across different domains, and 10 frequently compared DLKT model implementations for transparent experiments. Results from our fine-grained and rigorous empirical KT studies yield a set of observations and suggestions for effective DLKT, e. g. , wrong evaluation setting may cause label leakage that generally leads to performance inflation; and the improvement of many DLKT approaches is minimal compared to the very first DLKT model proposed by Piech et al. \cite{piech2015deep}. We have open sourced \textsc{pyKT} and our experimental results at \url{https: //pykt. org/}. We welcome contributions from other research groups and practitioners.

PDF Details

NeurIPS Conference 2021 Conference Paper

Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training

Shangshu Qian
Viet Hung Pham
Thibaud Lutellier
Zeou Hu
Jungwon Kim
Lin Tan
Yaoliang Yu
Jiahao Chen

Deep learning (DL) systems have been gaining popularity in critical tasks such as credit evaluation and crime prediction. Such systems demand fairness. Recent work shows that DL software implementations introduce variance: identical DL training runs (i. e. , identical network, data, configuration, software, and hardware) with a fixed seed produce different models. Such variance could make DL models and networks violate fairness compliance laws, resulting in negative social impact. In this paper, we conduct the first empirical study to quantify the impact of software implementation on the fairness and its variance of DL systems. Our study of 22 mitigation techniques and five baselines reveals up to 12. 6% fairness variance across identical training runs with identical seeds. In addition, most debiasing algorithms have a negative impact on the model such as reducing model accuracy, increasing fairness variance, or increasing accuracy variance. Our literature survey shows that while fairness is gaining popularity in artificial intelligence (AI) related conferences, only 34. 4% of the papers use multiple identical training runs to evaluate their approach, raising concerns about their results’ validity. We call for better fairness evaluation and testing protocols to improve fairness and fairness variance of DL systems as well as DL research validity and reproducibility at large.

PDF Details