Author name cluster

Tian Bai

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

1 author row

AAAI Conference 2026 Conference Paper

Aware Distillation for Robust Vision-Language Tracking Under Linguistic Sparsity

Guangtong Zhang
Bineng Zhong
Shirui Yang
Yang Wang
Tian Bai

Vision-language object tracking overcomes the limitations of relying solely on visual features by leveraging language descriptions of objects to provide cross-modal semantic information, thereby enhancing model robustness in complex scenarios. However, most existing high-performance vision-language trackers are trained jointly on pure visual data and vision-language multimodal data. Due to the relative sparsity of language annotations in the data, the trackers tend to prioritize the localization role of visual features, diminishing the model's attention to language information. To mitigate this issue, we propose a novel vision-language tracker: Aware Distillation for Robust Vision-Language Tracking under Linguistic Sparsity (ADTrack). We introduce a knowledge distillation framework employing a knowledge-rich teacher model and a lightweight student model to establish modality correlations between vision and language, enabling efficient modeling between visual information and language descriptions. Specifically, our lightweight student module simultaneously distills language encoding capabilities from large language models through teacher-guided learning on input language, while performing target-aware perception on template images using language descriptions to generate more effective template features for subsequent visual extraction. Furthermore, to ensure perceptual robustness in linguistically sparse scenarios, we simulate language-deficient conditions during training and employ contrastive learning to enhance model adaptability. Extensive experiments demonstrate that ADTrack reduces parameters by over 50% while achieving state-of-the-art (SOTA) performance and speed on vision-language tracking benchmarks, including LaSOT, LaSOText, TNL2K, OTB-Lang and MGIT.

PDF Details DOI

JBHI Journal 2026 Journal Article

Consensus and Complementary Feature Guided Multi-modal Knowledge Distillation Network for Breast Cancer Diagnosis

Shuyu Guo
Lan Huang
Ke Tao
Ruihong Zhao
Tian Bai

The integration of Hematoxylin and Eosin (H&E) and Immunohistochemistry (IHC) staining offers complementary information for accurate assessment of HER2 status in breast cancer. While multi-modal approaches enhance diagnostic precision, the high cost and acquisition constraints of IHC limit their routine clinical application. To address this, we propose a two-stage diagnostic framework that enables effective HER2 grading using only H&E images. In the first stage, a Consensus and Complementary Feature Co-Embedding Network (CoCoFNet) extracts modality-specific and cross-modal features to fully exploit multi-modal representations. In the second stage, a Hierarchical Multi-modal Knowledge Distillation (HM-KD) strategy transfers discriminative knowledge from the multi-modal teacher to a unimodal student network. Experiments on two public datasets demonstrate that the proposed method achieves comparable performance with state-of-the-art distillation methods using only H&E for HER2 grading. Furthermore, CoCoFNet demonstrates superior fusion capability, leading to more effective supervision and improved generalization in the unimodal student network. The codes can be publicly available from https://github.com/syguo95/HMKD.

Details DOI

JBHI Journal 2026 Journal Article

DAMON: Difference-Aware Medical Visual Question Answering via Multimodal Large Language Model

Zefan Zhang
Yanhui Li
Ruihong Zhao
Tian Bai

Difference-aware Medical Visual Question Answering (MVQA) aims to answer questions regarding disease-related content and the visual differences between the paired medical images, which is crucial for assessing disease progression and guiding further treatment planning. Although current medical Multimodal Large Language Models (MLLMs) have shown promising results in MVQA, they still exhibit poor generalization performance in difference-aware MVQA due to two key challenges. Firstly, existing difference-aware MVQA datasets are biased toward temporal variations of individual diseases, limiting their ability to model multi-disease coexistence and overlapping symptoms in real-world clinical scenarios. Secondly, disease-level semantic alignment becomes more challenging with multi-image inputs, as they introduce more redundant and interfering visual features. To address the first challenge, we introduce DAMON-QA, a large-scale difference-aware MVQA dataset designed to support visual difference analysis across multiple diseases. Leveraging this dataset, we train MLLMs and propose a D ifference- A ware M edical visual questi ON answering (DAMON) model. To tackle the second challenge, we further propose a Disease-driven Prompt Module (DPM) to identify the relevant diseases and guide the disease difference analysis process. Experiments on MIMIC-Diff-VQA show that our DAMON model achieves state-of-the-art (SOTA) performance. The dataset and code can be found at https://github.com/zefanZhang-cn/DAMON.

Details DOI

AAAI Conference 2026 Conference Paper

Plug-and-Play Optimization for 3D Gaussian Splatting Compression: Distribution Regularization, Probabilistic Pruning and Detail Compensation

Tian Bai
Zheng Qiu
Haojie Chen
Ziyang Dai

Recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated remarkable rendering quality, However, their substantial computational demands hinder practical deployment on resource-constrained devices. We propose a novel plug-and-play structured compression framework that significantly reduces computational overhead while maintaining rendering fidelity. We first discover that the statistical distribution of anchor vectors is decoupled from rendering quality. Based on this finding, we propose a distribution regularization method that enforces alignment to standard Gaussian distribution through KL divergence while optimizing Gaussian radius, significantly improving entropy coding efficiency. Second, we innovatively introduce an opacity-based probabilistic pruning mechanism that transforms pruning into an opacity optimization problem, achieving intelligent scene sparsification while allowing flexible adjustment according to hardware resources. Finally, we design a lightweight high-frequency compensation network that regards the high-frequency loss caused by over-compression as a residual and effectively recovers the high-frequency details lost during the compression process through residual learning. All modules are plug-and-play and can be seamlessly integrated into mainstream structured 3DGS frameworks. Extensive experiments on Synthetic-NeRF, Tanks&Temples, Mip-NeRF360 and DeepBlending datasets demonstrate that our method significantly reduces size by over 80x compared to vanilla 3DGS while simultaneously improving fidelity. Furthermore, it achieves a better size reduction and a 20% improvement in entropy encoding efficiency when compared to HAC, while meeting the requirements for real-time rendering.

PDF Details DOI

I&C Journal 2026 Journal Article

Solving Subset Feedback Vertex Set in Chordal Graphs Faster than 2k

Tian Bai
Mingyu Xiao

The Subset Feedback Vertex Set problem (SFVS) is to delete k vertices from a given graph such that in the remaining graph, any vertex in a subset T of vertices (called a terminal set) is not in a cycle. The famous Feedback Vertex Set problem is the special case of SFVS with T being the whole set of vertices. In this paper, we study exact algorithms for SFVS in Split Graphs (SFVS-S) and SFVS in Chordal Graphs (SFVS-C). SFVS-S generalizes the minimum vertex cover problem and the prize-collecting version of the maximum independent set problem on hypergraphs (PCMIS), and SFVS-C further generalizes SFVS-S. Both SFVS-S and SFVS-C are implicit 3-Hitting Set problems. However, it is not easy to solve them faster than 3-Hitting Set. In 2019, Philip, Rajan, Saurabh, and Tale proved that SFVS-C can be solved in O * ( 2 k ) time, slightly improving the best result O * ( 2. 0755 k ) for 3-Hitting Set. In this paper, we break the “2 k -barrier” for SFVS-S and SFVS-C by introducing an O * ( 1. 8192 k ) -time algorithm. This achievement also indicates that PCMIS can be solved in O * ( 1. 8192 n ) time, marking the first exact algorithm for PCMIS that outperforms the trivial O * ( 2 n ) threshold. Our algorithm uses reduction and branching rules based on the Dulmage-Mendelsohn decomposition and a divide-and-conquer method.

Details DOI

AAAI Conference 2025 Conference Paper

MP: Endowing Large Language Models with Lateral Thinking

Tian Bai
Yongwang Cao
Yan Ge
Haitao Yu

The recent studies show that Large Language Models (LLMs) often fall short in tasks demanding creative, lateral thinking due to lacking a clear awareness of their own reasoning processes. To cope with this issue, we propose a novel metacognitive prompting method (titled as MP) by mimicking human metacognition. Through integrating metacognitive principles, MP endows LLMs with lateral thinking ability, thereby enhancing their abilities to strategize, monitor, and reflect on their responses when dealing with creative tasks. The experimental results with five base LLMs across three lateral thinking datasets demonstrate that: All LLMs armed with MP consistently outperform the representative baseline methods. For example, MP demonstrates superior performance over CoT prompting across Sentence Puzzle (+5.00%), Word Puzzle (+10.07%), BiRdQA (+6.48%), and RiddleSense (+2.65%) with GPT-3.5-turbo model. In particular, the deployment of MP with GPT-4 achieves significant performance improvements that even surpass human performance on BRAINTEASER benchmark, demonstrating the transformative potential of MP in enhancing the creative problem-solving abilities of LLMs.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Prototype-Guided Multimodal Relation Extraction based on Entity Attributes

Zefan Zhang
Weiqi Zhang
Yanhui Li
Tian Bai

Multimodal Relation Extraction (MRE) aims to predict relations between head and tail entities based on the context of sentence-image pairs. Most existing MRE methods progressively incorporate textual and visual inputs to dominate the learning process, assuming both contribute significantly to the task. However, the diverse visual appearances and text with ambiguous semantics contain less-informative contexts for the corresponding relation. To tackle these challenges, we highlight the importance of semantically invariant entity attributes that encompass fine-grained categories. Towards this, we propose a novel Prototype-Guided Multimodal Relation Extraction (PG-MRE) framework based on Entity Attributes. Specifically, we first generate detailed entity explanations using Large Language Models (LLMs) to supplement the attribute semantics. Then, the Attribute Prototype Module (APM) refines attribute categories and condenses scattered entity attribute features into cluster-level prototypes. Furthermore, prototype-aligned attribute features guide diverse visual appearance features to produce compact and distinctive multimodal representations in the Relation Prototype Module (RPM). Extensive experiments demonstrate that our method gains superior relation classification capability (especially in scenarios involving various unseen entities), achieving new state-of-the-art performances on MNRE dataset.

PDF Details DOI

JBHI Journal 2025 Journal Article

SSGraphDTI: A Drug-Target Interaction Prediction Method Integrated Structural and Dynamic Systemic Biology Attributes

Haotian Guan
Tian Bai
Jingtong Zhao
Wenhao Li
Han Wang

Drug-Target Interaction (DTI) is a crucial aspect of pharmaceutical development. However, biochemical experiments are prohibitively expensive to identify these interactions on a large scale, while the computational approach is still on the way to making a highly reliable prediction. For the purpose of promoting prediction accuracy, drug-related molecular networks are gradually introduced to this task to furnish valuable information. We hypothesized that integrating structural and systemic biological attributes could effectively enhance the performance of DTI prediction and proposed a novel DTI prediction model, SSGraphDTI, which integrated two aforementioned attributes. Specifically, the structural attributes of drugs and targets are extracted using independent convolutional neural network based models from the Simplified Molecular Input Line Entry System of drugs and the amino acid sequences of targets, respectively. Meanwhile, the systemic biological attributes of drug-target pairs are obtained through graph representation learning on the dynamically constructed heterogeneous drug-target interaction network. SSGraphDTI was meticulously trained and rigorously tested on the benchmark Dataset_DrugBank, achieving an improvement of approximately 1. 0% across five metrics compared to recent comparable methods. These results underscore the potential of combining both structural and systemic information for accurate DTI prediction. Benefiting from the fact that the input consists solely of structural data without requiring interaction information, the model effectively addresses the “cold-start problem” in drug discovery. Furthermore, by extracting systemic attributes directly from the dynamically constructed DTI networks, the model maintains strong predictive performance even when data is limited. The source code is available at https://github.com/NENUBioCompute/SSGraphDTI.

Details DOI

TCS Journal 2024 Journal Article

Exact algorithms for restricted subset feedback vertex set in chordal and split graphs

Tian Bai
Mingyu Xiao

The Restricted Subset Feedback Vertex Set problem (R-SFVS) takes a graph G = ( V, E ), a terminal set T ⊆ V, and an integer k as the input. The task is to determine whether there exists a subset S ⊆ V ∖ T of at most k vertices, after deleting which no terminal in T is contained in a cycle in the remaining graph. R-SFVS is NP -complete even when the input graph is restricted to split graphs. In this paper, we mainly show that R-SFVS in chordal and split graphs can be solved in O ( 1. 1550 | V | ) time and exponential space or in O ( 1. 1605 | V | ) time and polynomial space, significantly improving all previous results. As a by-product, we show that the Maximum Independent Set problem parameterized by the edge clique cover number is fixed-parameter tractable. Furthermore, by using a simple reduction from R-SFVS to Vertex Cover, we obtain an O ⁎ ( 1. 2738 k ) -time parameterized algorithm and a tight O ( k 2 ) -kernel for R-SFVS in chordal and split graphs.

Details DOI

TCS Journal 2023 Journal Article

A parameterized algorithm for subset feedback vertex set in tournaments

Tian Bai
Mingyu Xiao

The Subset Feedback Vertex Set problem (SFVS) takes an n-vertex graph G = ( V, E ), a terminal set T ⊆ V, and an integer k as the input. The goal is to determine whether there exists a subset S ⊆ V of at most k vertices whose removal makes no terminal in T contained in a cycle in the remaining graph. When T = V, SFVS degenerates to the classical Feedback Vertex Set problem (FVS). Both SFVS and FVS have been extensively studied in parameterized algorithms. In this paper, we study parameterized algorithms for Subset Feedback Vertex Set in Tournaments (SFVST), i. e. , SFVS with the restriction that the input graph is always a tournament. By using the iterative compression method and a novel dynamic programming, we show that SFVST can be solved in 2 k + o ( k ) n O ( 1 ) time, improving the bound obtained from 3-Hitting Set.

Details DOI

AAAI Conference 2023 Conference Paper

Facility Location Games with Entrance Fees

Mengfan Ma
Mingyu Xiao
Tian Bai
Bakh Khoussainov

The facility location game is an extensively studied problem in mechanism design. In the classical model, the cost of each agent is her distance to the nearest facility. In this paper, we consider a novel model where each facility charges an entrance fee, which is a function of the facility's location. Thus, in our model, the cost of each agent is the sum of the distance to the facility and the entrance fee of the facility. The generalized model captures more real-life scenarios. In our model, the entrance fee function can be an arbitrary function, and the corresponding preferences of agents may not be single-peaked anymore: this makes the problem complex and requires new techniques in the analysis. We systematically study the model and design strategyproof mechanisms with nice approximation ratios and also complement these with nearly-tight impossibility results. Specifically, for one-facility and two-facility games, we provide upper and lower bounds for the approximation ratios given by deterministic and randomized mechanisms, with respect to the utilitarian and egalitarian objectives. Most of our bounds are tight, and these bounds are independent of the entrance fee functions. Our results also match the results of the classical model.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Medical Concept Representation Learning from Multi-source Data

Tian Bai
Brian L. Egleston
Richard Bleicher
Slobodan Vucetic

Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. We first modify the Pointwise Mutual Information (PMI) measure of similarity between the codes. We then develop a new negative sampling method for word2vec model that implicitly factorizes the modified PMI matrix. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we evaluated cross-referencing between ICD-9 and CPT medical code ontologies. Our results indicate that vector representations of codes learned by the proposed approach provide superior cross-referencing when compared to several existing approaches.

PDF Details