Author name cluster

Jin Ma

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.

7 papers

1 author row

AAAI Conference 2026 Conference Paper

TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking

Yongqi Fan
Xiaoyang Chen
Dezhi Ye
Jie Liu
Haijin Liang
Jin Ma
Ben He
Yingfei Sun

Reasoning-intensive ranking models built on Large Language Models (LLMs) have made notable progress. However, existing approaches often rely on large-scale LLMs and explicit Chain-of-Thought (CoT) reasoning, resulting in high computational cost and latency that limit real-world use. To address this, we propose TFRank, an efficient pointwise reasoning ranker based on small-scale LLMs. To improve ranking performance, TFRank effectively integrates CoT data, fine-grained score supervision, and multi-task training. Furthermore, it achieves an efficient "Think-Free" reasoning capability by employing a "think-mode switch" and pointwise format constraints. Specifically, this allows the model to leverage explicit reasoning during training while delivering precise relevance scores for complex queries at inference without generating any reasoning chains. Experiments show that TFRank achieves performance comparable to models with four times more parameters on the BRIGHT benchmark, and demonstrates strong competitiveness on the BEIR benchmark. Further analysis shows that TFRank achieves an effective balance between performance and efficiency, providing a practical solution for integrating advanced reasoning into real-world systems.

PDF Details DOI

JBHI Journal 2025 Journal Article

FlexibleSleepNet:A Model for Automatic Sleep Stage Classification Based on Multi-Channel Polysomnography

Ze Ren
Jin Ma
Ying Ding

In the task of automatic sleep stage classification, deep learning models often face the challenge of balancing temporal-spatial feature extraction with computational complexity. To address this issue, this study introduces FlexibleSleepNet, a lightweight convolutional neural network architecture designed around the Adaptive Feature Extraction (AFE) Module and Scale-Varying Compression (SVC) Module. Through multi-channel polysomnography data input and preprocessing, FlexibleSleepNet utilizes the AFE Module to capture intra-channel features and employs the SVC Module for channel feature compression and dimension expansion. The collaborative work of these modules enables the network to effectively capture temporal-spatial dependencies between channels. Additionally, the network extracts feature maps through four distinct stages, each from different receptive field scales, culminating in precise sleep stage classification via a classification module. This study conducted k-fold cross-validation on three different databases: SleepEDF-20, SleepEDF-78, and SHHS. Experimental results show that FlexibleSleepNet demonstrates superior classification performance, achieving classification accuracies of 86. 9% and 87. 6% on the SleepEDF-20 and SHHS datasets, respectively. It performs particularly well on the SleepEDF-78 dataset, where it reaches a classification accuracy of 87. 0%. Additionally, it has significantly enhanced computational efficiency while maintaining low computational complexity.

Details DOI

NeurIPS Conference 2025 Conference Paper

Model Merging in Pre-training of Large Language Models

Yunshui Li
Yiyuan Ma
Shen Yan
Chaoyi Zhang
Jing Liu
Jianqiao Lu
Ziwen Xu
Mengzhao Chen

Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model merging techniques during the pre-training process. Through extensive experiments with both dense and Mixture-of-Experts (MoE) architectures ranging from millions to over 100 billion parameters, we demonstrate that merging checkpoints trained with constant learning rates not only achieves significant performance improvements but also enables accurate prediction of annealing behavior. These improvements lead to both more efficient model development and significantly lower training costs. Our detailed ablation studies on merging strategies and hyperparameters provide new insights into the underlying mechanisms while uncovering novel applications. Through comprehensive experimental analysis, we offer the open-source community practical pre-training guidelines for effective model merging.

PDF Details

JBHI Journal 2023 Journal Article

sEMG-Based End-to-End Continues Prediction of Human Knee Joint Angles Using the Tightly Coupled Convolutional Transformer Model

Tuanjie Liang
Ning Sun
Qiong Wang
Jingyu Bu
Long Li
Yuhao Chen
Menglin Cao
Jin Ma

Wearable exoskeleton robots can promote the rehabilitation of patients with physical dysfunction. And improving human-computer interaction performance is a significant challenge for exoskeleton robots. The traditional feature extraction process based on surface Electromyography(sEMG) is complex and requires manual intervention, making real-time performance difficult to guarantee. In this study, we propose an end-to-end method to predict human knee joint angles based on sEMG signals using a tightly coupled convolutional transformer (TCCT) model. We first collected sEMG signals from 5 healthy subjects. Then, the envelope was extracted from the noise-removed sEMG signal and used as the input to the model. Finally, we developed the TCCT model to predict the knee joint angle after 100 ms. For the prediction performance, we used the Root Mean Square Error(RMSE), Pearson Correlation Coefficient(CC), and Adjustment R 2 as metrics to evaluate the error between the actual knee angle and the predicted knee angle. The results show that the model can predict the human knee angle quickly and accurately. The mean RMSE, Adjustment R 2, and (CC) values of the model are 3. 79°, 0. 96, and 0. 98, respectively, which are better than traditional deep learning models such as Informer (4. 14, 0. 95, 0. 98), CNN (5. 56, 0. 89, 0. 96) and CNN-BiLSTM (3. 97, 0. 95, 0. 98). In addition, the prediction time of our proposed model is only 11. 67 ± 0. 67 ms, which is less than 100 ms. Therefore, the real-time and accuracy of the model can meet the continuous prediction of human knee joint angle in practice.

Details DOI

AAAI Conference 2023 Conference Paper

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Yizhen Chen
Jie Wang
Lijian Lin
Zhongang Qi
Jin Ma
Ying Shan

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.

PDF Details DOI

JBHI Journal 2021 Journal Article

Left Ventricle Quantification Challenge: A Comprehensive Comparison and Evaluation of Segmentation and Regression for Mid-Ventricular Short-Axis Cardiac MR Data

Wufeng Xue
Jiahui Li
Zhiqiang Hu
Eric Kerfoot
James Clough
Ilkay Oksuz
Hao Xu
Vicente Grau

Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm $^2$ for the two areas, 2. 15 mm for the cavity dimensions, 2. 03 mm for RWTs, and a 9. 5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.

Details DOI

EAAI Journal 2015 Journal Article

An integrated feature selection and cluster analysis techniques for case-based reasoning

Guo-Niu Zhu
Jie Hu
Jin Qi
Jin Ma
Ying-Hong Peng

Feature selection and case organization are crucial steps in case-based reasoning (CBR), since the retrieval efficiency and accuracy even the success of the CBR system are heavily dependent on their quality. However, inappropriate feature selection and case selection together with ill-structured case organization may not only present a dilemma in case retrieval, but also greatly increase the case base. To obtain an efficient CBR system, selection of proper features and suitable cases with appropriate case organization are very important. This paper proposes a hybrid CBR system by introducing reduction technique in feature selection and cluster analysis in case organization. In this study, a minimal set of features is selected from the problem domain while redundant ones are reduced through neighborhood rough set algorithm. Once feature selection is finished, the growing hierarchical self-organizing map (GHSOM) is taken as a cluster tool to organize those cases so that the initial case base can be divided into some small subsets with hierarchical structure. New case is led into corresponding subset for case retrieval. Experiments on UCI datasets and a practical case in electromotor product design show the effectiveness of the proposed approach. The results indicate that the research techniques can effectively enhance the performance of the CBR system.

Details DOI