Author name cluster

Lin Yuan

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.

8 papers

1 author row

JBHI Journal 2026 Journal Article

MFE-Former: Disentangling Emotion-Identity Dynamics via Self-Supervised Learning for Enhancing Speech-Driven Depression Detection

Hao Wang
Jiayu Ye
Yanhong Yu
Lin Lu
Lin Yuan
Qingxiang Wang

Acoustic features are crucial behavioral indicators for depression detection. However, prior speech-based depression detection methods often overlook the variability of emotional patterns across samples, leading to interference from speaker identity and hindering the effective extraction of emotional changes. To address this limitation, we developed the Emotional Word Reading Experiment (EWRE) and introduced a method combining self-supervised and supervised learning for depression detection from speech called MFE-Former. First, we generate fine-grained emotional representations for response segments by computing cosine similarity between intra-sample and inter-sample contexts. Concurrently, orthogonality constraints decouple identity information from emotional features, while a Transformer decoder reconstructs spectral structures to improve sensitivity to depression-related emotional patterns. Next, we propose a multi-scale emotion change perception module and a Bernoulli distribution-based joint decision module integrate multi-level information for depression detection. By enhancing the distribution differences among positive, neutral, and negative emotional features, we find that patients with depression are more inclined to express negative emotions, whereas healthy individuals express more positive emotions. The experimental results on EWRE and AVEC 2014 show that MFE-Former outperforms state-of-the-art temporal methods under conditions of variability in emotional patterns across samples.

Details DOI

AAAI Conference 2026 Conference Paper

Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction

Jun Xu
Xinkai Du
Yu Ao
Peilong Zhao
Yang Li
Ling Zhong
Lin Yuan
Zhongpu Bo

Efficient retrieval of external knowledge bases and web pages is crucial for enhancing the reasoning abilities of LLMs. Previous works on training LLMs to leverage external retrievers for solving complex problems have predominantly employed end-to-end reinforcement learning. However, these approaches neglect supervision over the reasoning process, making it difficult to guarantee logical coherence and rigor. To address these limitations, we propose Thinker, a hierarchical thinking model for deep search through multi-turn interaction, making the reasoning process supervisable and verifiable. It decomposes complex problems into independently solvable sub-problems, each dually represented in both natural language and an equivalent logical function to support knowledge base and web searches. Concurrently, dependencies between sub-problems are passed as parameters via these logical functions, enhancing the logical coherence of the problem-solving process. To avoid unnecessary external searches, we perform knowledge boundary determination to check if a sub-problem is within the LLM's intrinsic knowledge, allowing it to answer directly. Experimental results indicate that with as few as several hundred training samples, the performance of Thinker is competitive with established baselines. Furthermore, when scaled to the full training set, Thinker significantly outperforms these methods across various datasets and model sizes.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

Lin Yuan
Jun Xu
Honghao Gui
Mengshu Sun
Zhiqiang Zhang
Lei Liang
Jun Zhou

High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU instructions mainly focus on information extraction (IE), neglecting tasks such as machine reading comprehension, question answering, and text classification. Furthermore, the lack of diversity in the data has led to a decreased generalization ability of trained LLMs in other NLU tasks and a noticeable decline in the fundamental model's general capabilities. To address this issue, we propose Hum, a large-scale, high-quality synthetic instruction corpus for NLU tasks, designed to enhance the NLU capabilities of LLMs. Specifically, Hum includes IE (either close IE or open IE), machine reading comprehension, text classification, and instruction generalist tasks, thereby enriching task diversity. Additionally, we introduce a human-LLMs collaborative mechanism to synthesize instructions, which enriches instruction diversity by incorporating guidelines, preference rules, and format variants. We conduct extensive experiments on 5 NLU tasks and 28 general capability evaluation datasets for LLMs. Experimental results show that Hum enhances the NLU capabilities of six LLMs by an average of 3.1%, with no significant decline observed in other general capabilities.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MLEP: Multi-granularity Local Entropy Patterns for Generalized AI-generated Image Detection

Lin Yuan
Xiaowan Li
Yan Zhang
Jiawei Zhang
Hongbo Li
Xinbo Gao

Advances in image generation technologies have raised growing concerns about their potential misuse, particularly in producing misinformation and deepfakes. This creates an urgent demand for effective methods to detect AI-generated images (AIGIs). While progress has been made, achieving reliable performance across diverse generative models and scenarios remains challenging due to the absence of source-invariant features and the limited generalization of existing approaches. In this study, we investigate the potential of using image entropy as a discriminative cue for AIGI detection and propose Multi-granularity Local Entropy Patterns (MLEP), a set of feature maps computed based on Shannon entropy from shuffled small patches at multiple image scales. MLEP effectively captures pixel dependencies across scales and dimensions while disrupting semantic content, thereby reducing potential content bias. Based on MLEP, we can easily build a robust CNN-based classifier capable of detecting AIGIs with enhanced reliability. Extensive experiments in an open-world setting, involving images synthesized by 32 distinct generative models, demonstrate that our approach achieves substantial improvements over state-of-the-art methods in both accuracy and generalization. Our code and models are available at https: //www. github. com/fkeufss/MLEP/.

PDF Details

JBHI Journal 2021 Journal Article

Exploiting Shared Knowledge From Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation

Yichi Zhang
Qingcheng Liao
Lin Yuan
He Zhu
Jiezhen Xing
Jicong Zhang

The novel Coronavirus disease (COVID-19) is a highly contagious virus and has spread all over the world, posing an extremely serious threat to all countries. Automatic lung infection segmentation from computed tomography (CT) plays an important role in the quantitative analysis of COVID-19. However, the major challenge lies in the inadequacy of annotated COVID-19 datasets. Currently, there are several public non-COVID lung lesion segmentation datasets, providing the potential for generalizing useful information to the related COVID-19 segmentation task. In this paper, we propose a novel relation-driven collaborative learning model to exploit shared knowledge from non-COVID lesions for annotation-efficient COVID-19 CT lung infection segmentation. The model consists of a general encoder to capture general lung lesion features based on multiple non-COVID lesions, and a target encoder to focus on task-specific features based on COVID-19 infections. We develop a collaborative learning scheme to regularize feature-level relation consistency of given input and encourage the model to learn more general and discriminative representation of COVID-19 infections. Extensive experiments demonstrate that trained with limited COVID-19 data, exploiting shared knowledge from non-COVID lesions can further improve state-of-the-art performance with up to 3. 0% in dice similarity coefficient and 4. 2% in normalized surface dice. In addition, experimental results on large scale 2D dataset with CT slices show that our method significantly outperforms cutting-edge segmentation methods metrics. Our method promotes new insights into annotation-efficient deep learning and illustrates strong potential for real-world applications in the global fight against COVID-19 in the absence of sufficient high-quality annotations.

Details DOI

EAAI Journal 2009 Journal Article

Cloud theory-based simulated annealing algorithm and application

Pin Lv
Lin Yuan
Jinfang Zhang

Using the randomness and stable tendency of a Y condition normal cloud generator, a cloud theory-based simulated annealing algorithm (CSA) is originally proposed, whose characteristic is approximately continuous decrease in temperature and implied “Backfire & Re-Annealing”. It fits the annealing process of solid matter in nature much better, overcomes the traditional simulated annealing algorithm (SA)'s disadvantages, which are slow searching speed and being trapped by local minimum easily, then enhances the veracity of final solution and reduces the time cost of the optimization process simultaneously. Theory analysis proves that CSA is convergent and typical function optimization experiments show that CSA is superior to SA in terms of convergence speed, searching ability and robustness. The result of the application using CSA for multiple observers sitting problem (MOST) in visibility-based terrain reasoning (VBTR) also declares the new algorithm's usefulness and effectiveness adequately.

Details DOI

AAAI Conference 2004 Short Paper

Finding Redundant Constraints for FSM Minimization

Lin Yuan

Finite state machine (FSM) is a computation model that consists of a finite set of states, a start state, an input alphabet, and a transition function that defines the next state and/or outputs based on the current state and input symbols. Finding an equivalent FSMwith minimal number of states is generally referred as state minimization or state reduction (SR) problem. State minimization is an effective approach in logic synthesis to optimize sequential circuit design in terms of area and power(Kam, 1997). The SR problem of FSM is NP-complete and can be treated as a special case of the Constraint Satisfaction Problem(CSP) where the transition function defines all the constraints that need to be satisfied. Interestingly, we observe that not all the constraints are required to obtain a given SR solution. Identifying the redundancy in the FSM will be useful in the following occasions. First, it helps to understand the nature of the NP-complete SR problem and to build FSM benchmarks to test the effectiveness of SR solvers. Second, the redundancy can be utilized to hide information and thus provide security protection to the FSM. Simulation results on real life FSMs reveal the existence of extremely rich redundancy.

PDF Details

AAAI Conference 2004 Short Paper

Generating “Random” 3-SAT Instances with Specific Solution Space Structure

Pushkin R. Pari
Lin Yuan

Generating good benchmarks is important for the evaluation and improvement of any algorithm for NP-hard problems such as the Boolean satisfiability (SAT) problem. Carefully designed benchmarks are also helpful in the study of the nature of NP-completeness . Probably the most well-known and successful story is the discovery of the phase transition phenomenon (Cheeseman, Kanefsky, and Taylor 1991). More recently, (Achlioptas et al. 2000) pointed out the importance of generating satisfiable problem instances. In this abstract, we consider how to create 3-SAT formulas that look like random but with specific solution structures. In particular, we show that random 3-SAT formulas do not have their solutions distributed randomly in the solution space and we further develop generators to build random 3-SAT formulas with randomly distributed solutions or fixed number of solutions.

PDF Details