Author name cluster

Bo Cheng

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.

12 papers

2 author rows

JBHI Journal 2026 Journal Article

Adaptive Spectral Graph Attention Filtering Network for Alzheimer's Disease Classification Using Multimodal Data

Zhi Yang
Bo Cheng
Haitao Gan
Zhongwei Huang
Ran Zhou
Ji Wang

Early detection of Alzheimer's Disease (AD) is critical for timely intervention and management. However, existing graph-based approaches often fail to fully leverage the rich spectral-domain information inherent in brain network signals. To address this limitation, we propose an Adaptive Spectral Graph Attention Filtering Network (ASGAFN), which effectively models the spectral structures of functional and structural brain networks to enhance classification performance. Specifically, we first construct structural and functional brain network graphs from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI). Subsequently, a frequency-encoding-guided attention mechanism is designed to learn a shared spectral response function across graphs. This enables the construction of interpretable and adaptive spectral filters while mitigating semantic misalignment across different spectral domains. Furthermore, a spectral energy sensing module is incorporated to facilitate graph-specific adaptation, thereby enhancing flexibility and subject-level discriminability. Finally, the refined spectral signals are transformed back to the spatial domain and fused via a Multimodal Fusion and Enhancement Layer (MFEL). Extensive experiments demonstrate that ASGAFN significantly outperforms multiple baselines in AD-related classification tasks. It achieves accuracies of 96. 64% (AD vs. NC), 90. 48% (MCI vs. NC), and 91. 75% (AD vs. MCI). Additionally, it attains an accuracy of 87. 12% in the three-class classification task, underscoring its effectiveness in distinguishing among multiple disease stages. These findings validate the efficacy of spectral-domain modeling and multimodal fusion.

Details DOI

AAAI Conference 2026 Conference Paper

Analyze–Compose–Execute: A Dynamic Dialogue Framework for Multi-Agent Debate

Wenyuan Gu
Haowen Wang
Jiale Han
Xiang Li
Zhixuan Wu
Hongru Xiao
Bo Cheng

Multi-Agent Debate (MAD) is an emerging paradigm that leverages the reasoning abilities of Large Language Models (LLMs) by encouraging them to collaboratively solve problems through human-like discussions. However, current MAD methods typically constrain agents to follow fixed discussion pipelines, repeatedly applying the same discussion act for a predetermined number of rounds, which limits their effectiveness and adaptability in complex and diverse tasks. To address this limitation, we propose Analyze–Compose–Execute (ACE), a novel debate framework in which agents dynamically execute the discussion actions according to the dialogue context. By analyzing the current responses of agents, ACE selects appropriate acts from a predefined Atomic Discussion Acts Library (ADAL), which are composed into a discussion action to be executed in the next round, to enable truly dynamic debate. We conduct extensive experiments on the challenging benchmark Big-Bench Hard (BBH) benchmark. ACE achieves state-of-the- art results on 17 out of 23 tasks, with an average performance gain of 8.5% across all tasks, demonstrating the effectiveness and robustness of our approach.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities

Shanyuan Liu
Bo Cheng
Yuhang Ma
Liebucha Wu
Ao Ma
Xiaoyu Wu
Dawei Leng
Yuhui Yin

Text-to-Image generation (TTI) technologies are advancing rapidly, especially in the English language communities. However, apart from the user input language barrier problem, English-native TTI models inherently carry biases from their English world centric training data, which creates a dilemma for development of other language-native TTI models. One common choice is to fine-tune the English-native TTI model with translated samples. It falls short of fully addressing the model bias problem. Alternatively, training non-English language native models from scratch can effectively resolve the English world bias, but model trained this way would diverge from the English TTI communities, thus not able to utilize the strides continuously gaining in the English TTI communities any more. To build Chinese TTI model meanwhile keep compatibility with the English TTI communities, we propose a novel model structure referred as "Bridge Diffusion Model" (BDM). The proposed BDM employs a backbone-branch network structure to learn the Chinese semantics while keep the latent space compatible with the English-native TTI backbone, in an end-to-end manner. The unique advantages of the proposed BDM are that it's not only adept at generating images that precisely depict Chinese semantics, but also compatible with various English-native TTI plugins, such as different checkpoints, LoRA, ControlNet, Dreambooth, and Textual Inversion, etc. Moreover, BDM can concurrently generate content seamlessly combining both Chinese-native and English-native semantics within a single image, fostering cultural interaction.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation

Bo Cheng
Yuhang Ma
Liebucha Wu
Shanyuan Liu
Ao Ma
Xiaoyu Wu
Dawei Leng
Yuhui Yin

The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing, inconsistent lighting, conflicting view angles, etc. To effectively address these issues, we propose a \textbf{Hi}erarchical \textbf{Co}ntrollable (HiCo) diffusion model for layout-to-image generation, featuring object seperable conditioning branch structure. Our key insight is to achieve spatial disentanglement through hierarchical modeling of layouts. We use a multi branch structure to represent hierarchy and aggregate them in fusion module. To evaluate the performance of multi-objective controllable layout generation in natural scenes, we introduce the HiCo-7K benchmark, derived from the GRIT-20M dataset and manually cleaned. https: //github. com/360CVGroup/HiCo_T2I.

PDF Details DOI

IROS Conference 2023 Conference Paper

An Implantable Variable Length Actuator for Modulating in Vivo Musculo-Tendon Force in a Bipedal Animal Model

Sean Thomas
Ravin Joshi
Bo Cheng
Huanyu Cheng
Michael C. Aynardi
Gregory S. Sawicki
Jonas Rubenson

Mobility, a critical factor in quality of life, is often rehabilitated using simplistic solutions, such as walkers. Exoskeletons (wearable robotics) offer a more sophisticated rehabilitation approach. However, non-adherence to externally worn mobility aids limits their efficacy. Here, we present the concept of a fully implantable assistive limb actuator that overcomes non-adherence constraints, and which can provide high-precision assistive force. In a bipedal animal model (fowl), we have developed a variable length isometric actuator (measuring ϕ9 x 30 mm) that is able to be directly implanted within the leg via a bone anchor and tendon fixation, replacing the lateral gastrocnemius muscle belly. The actuator is able to generate isometric force similar to the in vivo force of the native muscle, designed to generate assistive torque at the ankle and reduce muscular demand at no additional energy cost. The device has a stroke of 10 mm that operates up to 770 mm/s (77 stroke lengths/s), capable of acting as a clutch (disengaging when needed) and with a tunable slack length to modulate the timing and level of assistive force during gait. Surgical techniques to attach the actuator to the biological system, the Achilles tendon and tibia, have been established and validated using survival surgeries and cadaveric specimens.

Details

AAAI Conference 2023 Conference Paper

TC-DWA:Text Clustering with Dual Word-Level Augmentation

Bo Cheng
Ximing Li
Yi Chang

The pre-trained language models, e.g., ELMo and BERT, have recently achieved promising performance improvement in a wide range of NLP tasks, because they can output strong contextualized embedded features of words. Inspired by their great success, in this paper we target at fine-tuning them to effectively handle the text clustering task, i.e., a classic and fundamental challenge in machine learning. Accordingly, we propose a novel BERT-based method, namely Text Clustering with Dual Word-level Augmentation (TCDWA). To be specific, we formulate a self-training objective and enhance it with a dual word-level augmentation technique. First, we suppose that each text contains several most informative words, called anchor words, supporting the full text semantics. We use the embedded features of anchor words as augmented data, which are selected by ranking the norm-based attention weights of words. Second, we formulate an expectation form of word augmentation, which is equivalent to generating infinite augmented features, and further suggest a tractable approximation of Taylor expansion for efficient optimization. To evaluate the effectiveness of TCDWA, we conduct extensive experiments on several benchmark text datasets. The results demonstrate that TCDWA consistently outperforms the state-of-the-art baseline methods. Code available: https://github.com/BoCheng-96/TC-DWA.

PDF Details DOI

AAAI Conference 2022 Short Paper

Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)

Yi Liang
Shuai Zhao
Bo Cheng
Yuwei Yin
Hao Yang

Few-shot relation learning refers to infer facts for relations with a limited number of observed triples. Existing metriclearning methods for this problem mostly neglect entity interactions within and between triples. In this paper, we explore this kind of fine-grained semantic meanings and propose our model TransAM. Specifically, we serialize reference entities and query entities into sequence and apply transformer structure with local-global attention to capture both intra- and inter-triple entity interactions. Experiments on two public benchmark datasets NELL-One and Wiki-One with 1shot setting prove the effectiveness of TransAM.

PDF Details

AAAI Conference 2021 Short Paper

Knowledge-aware Dialogue Generation with Hybrid Attention (Student Abstract)

Yaru Zhao
Bo Cheng
Yingying Zhang

Using commonsense knowledge to assist dialogue generation is a big step forward for dialogue generation task. However, how to fully utilize commonsense information is always a challenge. Furthermore, the entities generated in the response do not match the information in post most often. In this paper, we propose a dialogue generation model which uses hybrid attention to better generate rational entities. When a user post is given, the model encodes relevant knowledge graphs from a knowledge base with a graph attention mechanism. Then it will encode the user post and graphs with a co-attention mechanism, which effectively encodes complex related data. Through the above mechanism, we can get a better mutual understanding of post and knowledge. The experimental results show that our model is more effective than the current state-of-the-art model (CCM).

PDF Details

AAAI Conference 2020 Short Paper

HGMAN: Multi-Hop and Multi-Answer Question Answering Based on Heterogeneous Knowledge Graph (Student Abstract)

Xu Wang
Shuai Zhao
Bo Cheng
Jiale Han
Yingting Li
Hao Yang
Guoshun Nan

Multi-hop question answering models based on knowledge graph have been extensively studied. Most existing models predict a single answer with the highest probability by ranking candidate answers. However, they are stuck in predicting all the right answers caused by the ranking method. In this paper, we propose a novel model that converts the ranking of candidate answers into individual predictions for each candidate, named heterogeneous knowledge graph based multi-hop and multi-answer model (HGMAN). HGMAN is capable of capturing more informative representations for relations assisted by our heterogeneous graph, which consists of multiple entity nodes and relation nodes. We rely on graph convolutional network for multi-hop reasoning and then binary classiﬁcation for each node to get multiple answers. Experimental results on MetaQA dataset show the performance of our proposed model over all baselines.

PDF Details

AAAI Conference 2020 Short Paper

Hypergraph Convolutional Network for Multi-Hop Knowledge Base Question Answering (Student Abstract)

Jiale Han
Bo Cheng
Xu Wang

Graph convolutional networks (GCN) have been applied in knowledge base question answering (KBQA) task. However, the pairwise connection between nodes of GCN limits the representation capability of high-order data correlation. Furthermore, most previous work does not fully utilize the semantic relation information, which is vital to reasoning. In this paper, we propose a novel multi-hop KBQA model based on hypergraph convolutional network. By constructing a hypergraph, the form of pairwise connection between nodes and nodes is converted to the high-level connection between nodes and edges, which effectively encodes complex related data. To better exploit the semantic information of relations, we apply co-attention method to learn similarity between relation and query, and assign weights to different relations. Experimental results demonstrate the effectivity of the model.

PDF Details

AAAI Conference 2020 Short Paper

Neural Dynamics and Gamma Oscillation on a Hybrid Excitatory-Inhibitory Complex Network (Student Abstract)

Yuan Wang
Xia Shi
Bo Cheng
Junliang Chen

This paper investigates the neural dynamics and gamma oscillation on a complex network with excitatory and inhibitory neurons (E-I network), as such network is ubiquitous in the brain. The system consists of a small-world network of neurons, which are emulated by Izhikevich model. Moreover, mixed Regular Spiking (RS) and Chattering (CH) neurons are considered to imitate excitatory neurons, and Fast Spiking (FS) neurons are used to mimic inhibitory neurons. Besides, the relationship between synchronization and gamma rhythm is explored by adjusting the critical parameters of our model. Experiments visually demonstrate that the gamma oscillations are generated by synchronous behaviors of our neural network. We also discover that the Chattering(CH) excitatory neurons can make the system easier to synchronize.

PDF Details

IJCAI Conference 2020 Conference Paper

Two-Phase Hypergraph Based Reasoning with Dynamic Relations for Multi-Hop KBQA

Jiale Han
Bo Cheng
Xu Wang

Multi-hop knowledge base question answering (KBQA) aims at finding the answers to a factoid question by reasoning across multiple triples. Note that when human performs multi-hop reasoning, one tends to concentrate on specific relation at different hops and pinpoint a group of entities connected by the relation. Hypergraph convolutional networks (HGCN) can simulate this behavior by leveraging hyperedges to connect more than two nodes more than pairwise connection. However, HGCN is for undirected graphs and does not consider the direction of information transmission. We introduce the directed-HGCN (DHGCN) to adapt to the knowledge graph with directionality. Inspired by human's hop-by-hop reasoning, we propose an interpretable KBQA model based on DHGCN, namely two-phase hypergraph based reasoning with dynamic relations, which explicitly updates relation information and dynamically pays attention to different relations at different hops. Moreover, the model predicts relations hop-by-hop to generate an intermediate relation path. We conduct extensive experiments on two widely used multi-hop KBQA datasets to prove the effectiveness of our model.

PDF Details DOI