Xin Chen

Li Zhang, Youhe Jiang, Guoliang He et al.

Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. However, existing systems struggle to (i) automatically generalize across diverse hardware architectures and precision formats, often requiring fragmented, hand-tuned kernels, and (ii) fully exploit available memory and compute resources, often causing performance bottlenecks. To address these problems, we propose TurboMind, a generalizable and efficient mixed-precision LLM inference engine of LMDeploy. TurboMind is built around two hardware-aware mixed-precision pipelines: A General Matrix Multiply (GEMM) pipeline that optimizes matrix operations through offline weight packing and online acceleration, and an attention pipeline that enables efficient attention computation with different Query, Key, and Value precision combinations. These pipelines are enabled by four key techniques: (i) Hardware-aware weight packing and (ii) adaptive head alignment for generalizability, and (iii) instruction-level parallelism and (iv) a KV memory loading pipeline for efficiency. We conduct comprehensive evaluations of LMDeploy powered by TurboMind across sixteen popular LLMs and four representative GPU architectures. Results demonstrate that LMDeploy achieves up to 61% lower serving latency (30% on average) and up to 156% higher throughput (58% on average) in mixed-precision workloads compared to existing mixed-precision frameworks, establishing consistent performance improvements across all tested configurations and hardware types. This work is open-sourced and publicly available at https://github.com/InternLM/lmdeploy.

Jieneng Chen, Yingda Xia, Jiawen Yao et al.

Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice, while most medical AI systems are built to focus on single organs with a narrow list of a few diseases. This might severely limit AI's clinical adoption. A certain number of AI models need to be assembled non-trivially to match the diagnostic process of a human reading a CT scan. In this paper, we construct a Unified Tumor Transformer (CancerUniT) model to jointly detect tumor existence & location and diagnose tumor characteristics for eight major cancers in CT scans. CancerUniT is a query-based Mask Transformer model with the output of multi-tumor prediction. We decouple the object queries into organ queries, tumor detection queries and tumor diagnosis queries, and further establish hierarchical relationships among the three groups. This clinically-inspired architecture effectively assists inter- and intra-organ representation learning of tumors and facilitates the resolution of these complex, anatomically related multi-organ cancer image reading tasks. CancerUniT is trained end-to-end using a curated large-scale CT images of 10,042 patients including eight major types of cancers and occurring non-cancer tumors (all are pathology-confirmed with 3D tumor masks annotated by radiologists). On the test set of 631 patients, CancerUniT has demonstrated strong performance under a set of clinically relevant evaluation metrics, substantially outperforming both multi-disease methods and an assembly of eight single-organ expert models in tumor detection, segmentation, and diagnosis. This moves one step closer towards a universal high performance cancer screening tool.

Yucheng Han, Chi Zhang, Xin Chen et al.

Multi-modal large language models have demonstrated impressive performances on most vision-language tasks. However, the model generally lacks the understanding capabilities for specific domain data, particularly when it comes to interpreting chart figures. This is mainly due to the lack of relevant multi-modal instruction tuning datasets. In this article, we create a high-quality instruction-tuning dataset leveraging GPT-4. We develop a multi-step data generation process in which different steps are responsible for generating tabular data, creating chart figures, and designing instruction tuning data separately. Our method's flexibility enables us to generate diverse, high-quality instruction-tuning data consistently and efficiently while maintaining a low resource expenditure. Additionally, it allows us to incorporate a wider variety of chart and task types not yet featured in existing datasets. Next, we introduce ChartLlama, a multi-modal large language model that we've trained using our created dataset. ChartLlama outperforms all prior methods in ChartQA, Chart-to-text, and Chart-extraction evaluation benchmarks. Additionally, ChartLlama significantly improves upon the baseline in our specially compiled chart dataset, which includes new chart and task types. The results of ChartLlama confirm the value and huge potential of our proposed data generation method in enhancing chart comprehension.

Mingze Yuan, Yingda Xia, Xin Chen et al.

Gastric cancer is the third leading cause of cancer-related mortality worldwide, but no guideline-recommended screening test exists. Existing methods can be invasive, expensive, and lack sensitivity to identify early-stage gastric cancer. In this study, we explore the feasibility of using a deep learning approach on non-contrast CT scans for gastric cancer detection. We propose a novel cluster-induced Mask Transformer that jointly segments the tumor and classifies abnormality in a multi-task manner. Our model incorporates learnable clusters that encode the texture and shape prototypes of gastric cancer, utilizing self- and cross-attention to interact with convolutional features. In our experiments, the proposed method achieves a sensitivity of 85.0% and specificity of 92.6% for detecting gastric tumors on a hold-out test set consisting of 100 patients with cancer and 148 normal. In comparison, two radiologists have an average sensitivity of 73.5% and specificity of 84.3%. We also obtain a specificity of 97.7% on an external test set with 903 normal cases. Our approach performs comparably to established state-of-the-art gastric cancer screening tools like blood testing and endoscopy, while also being more sensitive in detecting early-stage cancer. This demonstrates the potential of our approach as a novel, non-invasive, low-cost, and accurate method for opportunistic gastric cancer screening.

Ruizhe Li, Xin Chen

Cardiac Magnetic Resonance Imaging (MRI) plays an important role in the analysis of cardiac function. However, the acquisition is often accompanied by motion artefacts because of the difficulty of breath-hold, especially for acute symptoms patients. Therefore, it is essential to assess the quality of cardiac MRI for further analysis. Time-consuming manual-based classification is not conducive to the construction of an end-to-end computer aided diagnostic system. To overcome this problem, an automatic cardiac MRI quality estimation framework using ensemble and transfer learning is proposed in this work. Multiple pre-trained models were initialised and fine-tuned on 2-dimensional image patches sampled from the training data. In the model inference process, decisions from these models are aggregated to make a final prediction. The framework has been evaluated on CMRxMotion grand challenge (MICCAI 2022) dataset which is small, multi-class, and imbalanced. It achieved a classification accuracy of 78.8% and 70.0% on the training set (5-fold cross-validation) and a validation set, respectively. The final trained model was also evaluated on an independent test set by the CMRxMotion organisers, which achieved the classification accuracy of 72.5% and Cohen's Kappa of 0.6309 (ranked top 1 in this grand challenge). Our code is available on Github: https://github.com/ruizhe-l/CMRxMotion.

Jiaxu Zhang, Shaoli Huang, Zhigang Tu et al.

Previous motion generation methods are limited to the pre-rigged 3D human model, hindering their applications in the animation of various non-rigged characters. In this work, we present TapMo, a Text-driven Animation Pipeline for synthesizing Motion in a broad spectrum of skeleton-free 3D characters. The pivotal innovation in TapMo is its use of shape deformation-aware features as a condition to guide the diffusion model, thereby enabling the generation of mesh-specific motions for various characters. Specifically, TapMo comprises two main components - Mesh Handle Predictor and Shape-aware Diffusion Module. Mesh Handle Predictor predicts the skinning weights and clusters mesh vertices into adaptive handles for deformation control, which eliminates the need for traditional skeletal rigging. Shape-aware Motion Diffusion synthesizes motion with mesh-specific adaptations. This module employs text-guided motions and mesh features extracted during the first stage, preserving the geometric integrity of the animations by accounting for the character's shape and deformation. Trained in a weakly-supervised manner, TapMo can accommodate a multitude of non-human meshes, both with and without associated text motions. We demonstrate the effectiveness and generalizability of TapMo through rigorous qualitative and quantitative experiments. Our results reveal that TapMo consistently outperforms existing auto-animation methods, delivering superior-quality animations for both seen or unseen heterogeneous 3D characters.

Xin Chen, Ben Kang, Wanting Geng et al.

In this paper, we propose a simple yet unified single object tracking (SOT) framework, dubbed SUTrack. It consolidates five SOT tasks (RGB-based, RGB-Depth, RGB-Thermal, RGB-Event, RGB-Language Tracking) into a unified model trained in a single session. Due to the distinct nature of the data, current methods typically design individual architectures and train separate models for each task. This fragmentation results in redundant training processes, repetitive technological innovations, and limited cross-modal knowledge sharing. In contrast, SUTrack demonstrates that a single model with a unified input representation can effectively handle various common SOT tasks, eliminating the need for task-specific designs and separate training sessions. Additionally, we introduce a task-recognition auxiliary training strategy and a soft token type embedding to further enhance SUTrack's performance with minimal overhead. Experiments show that SUTrack outperforms previous task-specific counterparts across 11 datasets spanning five SOT tasks. Moreover, we provide a range of models catering edge devices as well as high-performance GPUs, striking a good trade-off between speed and accuracy. We hope SUTrack could serve as a strong foundation for further compelling research into unified tracking models. Code and models are available at github.com/chenxin-dlut/SUTrack.

Xin Chen, Ke Ding

Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing medical datasets hinder training deeper and larger models because of overfitting. To this end, we propose a novel two-stream UNET architecture for automatic end-to-end medical image segmentation, in which intensity value and gradient vector flow (GVF) are two inputs for each stream, respectively. We demonstrate that two-stream CNNs with more low-level features greatly benefit semantic segmentation for imperfect medical image datasets. Our proposed two-stream networks are trained and evaluated on the popular medical image segmentation benchmarks, and the results are competitive with the state of the art. The code will be released soon.

Xiaohong Liu, Xiongkuo Min, Qiang Hu et al.

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

Ben Kang, Xin Chen, Jie Zhao et al.

Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constrained devices because of their slow processing speeds. To address this challenge, we present HiT, a novel family of efficient tracking models that achieve high performance while maintaining fast operation across various devices. The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality. Additionally, we introduce a dual-image position encoding approach to effectively encode spatial information. HiT achieves an impressive speed of 61 frames per second (fps) on the NVIDIA Jetson AGX platform, alongside a competitive AUC of 64.6% on the LaSOT benchmark, outperforming all previous efficient trackers.Building on HiT, we propose DyHiT, an efficient dynamic tracker that flexibly adapts to scene complexity by selecting routes with varying computational requirements. DyHiT uses search area features extracted by the backbone network and inputs them into an efficient dynamic router to classify tracking scenarios. Based on the classification, DyHiT applies a divide-and-conquer strategy, selecting appropriate routes to achieve a superior trade-off between accuracy and speed. The fastest version of DyHiT achieves 111 fps on NVIDIA Jetson AGX while maintaining an AUC of 62.4% on LaSOT.Furthermore, we introduce a training-free acceleration method based on the dynamic routing architecture of DyHiT. This method significantly improves the execution speed of various high-performance trackers without sacrificing accuracy. For instance, our acceleration method enables the state-of-the-art tracker SeqTrack-B256 to achieve a 2.68 times speedup on an NVIDIA GeForce RTX 2080 Ti GPU while maintaining the same AUC of 69.9% on the LaSOT.

Benchang Dong, Zhili Chen, Xin Chen et al.

Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with binary values. Nevertheless, challenges persist in terms of communication and accuracy in their application scenarios. In this work, we introduce CBNN, a three-party secure computation framework tailored for efficient BNN inference. Leveraging knowledge distillation and separable convolutions, CBNN transforms standard BNNs into MPC-friendly customized BNNs, maintaining high utility. It performs secure inference using optimized protocols for basic operations. Specifically, CBNN enhances linear operations with replicated secret sharing and MPC-friendly convolutions, while introducing a novel secure activation function to optimize non-linear operations. We demonstrate the effectiveness of CBNN by transforming and securely implementing several typical BNN models. Experimental results indicate that CBNN maintains impressive performance even after customized binarization and security measures

Changsheng Wang, Xin Chen, Sijia Liu et al.

Adapting pretrained large language models (LLMs) to code domains via supervised fine-tuning (FT) has been commonly used for code generation. However, we identify a previously underappreciated failure mode, the memorization barrier, where strong memorization of downstream code data in the base model could trap optimization and prevent the standard FT from effectively acquiring new, generalizable code knowledge. To overcome this barrier, we propose the information bottleneck (IB)-guided fine-tuning, termed IB-FT, which applies an IB penalty on hidden representations of the code data to compress spurious, memorized features while preserving task-relevant information. Extensive experiments on two code benchmarks (OriGen and Evol-CodeAlpaca-V1) show that IB-FT substantially alleviates the memorization barrier, improves top-1 performance (Pass@$1$), and yields far more stable gains under the stricter multi-sample metric Pass@$k^{(m)}$ (a problem counts as solved only if at least $m$ of $k$ samples pass unit tests) compared with conventional FT.

Longfei Li, Rui Yang, Xin Chen et al.

Prostate Imaging Reporting and Data System (PI-RADS) based on multi-parametric MRI classiêes patients into 5 categories (PI-RADS 1-5) for routine clinical diagnosis guidance. However, there is no consensus on whether PI-RADS 3 patients should go through biopsies. Mining features from these hard samples (HS) is meaningful for physicians to achieve accurate diagnoses. Currently, the mining of HS biomarkers is insuìcient, and the eéectiveness and robustness of HS biomarkers for prostate cancer diagnosis have not been explored. In this study, biomarkers from diéerent data distributions are constructed. Results show that HS biomarkers can achieve better performances in diéerent data distributions.

Daping Zhang, Xin Chen, Yujia Zhang et al.

Agriculture is the fundamental industry of the society, which is the basis of food supply and an important source of employment and GDP increase. However, the insufficient expert can not fulfill the demand of farmers. To address this problem, we design a chatbot to answer frequently asked questions in the Agriculture field. Template-based questions will be answered by AIML while LSA is used for other service-based questions. This chatbot will assist farmers by dealing with industry problems conveniently and efficiently.

Zixiao Shen, Xin Chen, Jonathan M. Garibaldi

This paper presents a novel meta learning framework for feature selection (FS) based on fuzzy similarity. The proposed method aims to recommend the best FS method from four candidate FS methods for any given dataset. This is achieved by firstly constructing a large training data repository using data synthesis. Six meta features that represent the characteristics of the training dataset are then extracted. The best FS method for each of the training datasets is used as the meta label. Both the meta features and the corresponding meta labels are subsequently used to train a classification model using a fuzzy similarity measure based framework. Finally the trained model is used to recommend the most suitable FS method for a given unseen dataset. This proposed method was evaluated based on eight public datasets of real-world applications. It successfully recommended the best method for five datasets and the second best method for one dataset, which outperformed any of the four individual FS methods. Besides, the proposed method is computationally efficient for algorithm selection, leading to negligible additional time for the feature selection process. Thus, the paper contributes a novel method for effectively recommending which feature selection method to use for any new given dataset.

Zixiao Shen, Xin Chen, Jonathan M. Garibaldi

In this paper, based on a fuzzy entropy feature selection framework, different methods have been implemented and compared to improve the key components of the framework. Those methods include the combinations of three ideal vector calculations, three maximal similarity classifiers and three fuzzy entropy functions. Different feature removal orders based on the fuzzy entropy values were also compared. The proposed method was evaluated on three publicly available biomedical datasets. From the experiments, we concluded the optimized combination of the ideal vector, similarity classifier and fuzzy entropy function for feature selection. The optimized framework was also compared with other six classical filter-based feature selection methods. The proposed method was ranked as one of the top performers together with the Correlation and ReliefF methods. More importantly, the proposed method achieved the most stable performance for all three datasets when the features being gradually removed. This indicates a better feature ranking performance than the other compared methods.

Ruizhe Li, Dorothee Auer, Christian Wagner et al.

Deep learning based image segmentation has achieved the state-of-the-art performance in many medical applications such as lesion quantification, organ detection, etc. However, most of the methods rely on supervised learning, which require a large set of high-quality labeled data. Data annotation is generally an extremely time-consuming process. To address this problem, we propose a generic semi-supervised learning framework for image segmentation based on a deep convolutional neural network (DCNN). An encoder-decoder based DCNN is initially trained using a few annotated training samples. This initially trained model is then copied into sub-models and improved iteratively using random subsets of unlabeled data with pseudo labels generated from models trained in the previous iteration. The number of sub-models is gradually decreased to one in the final iteration. We evaluate the proposed method on a public grand-challenge dataset for skin lesion segmentation. Our method is able to significantly improve beyond fully supervised model learning by incorporating unlabeled data.

Xin Chen, Emma Marriott, Yuling Yan

In recent years, high-speed videoendoscopy (HSV) has significantly aided the diagnosis of voice pathologies and furthered the understanding the voice production in recent years. As the first step of these studies, automatic segmentation of glottal images till presents a major challenge for this technique. In this paper, we propose an improved Saliency Network that automatically delineates the contour of the glottis from HSV image sequences. Our proposed additional saliency measure, Motion Saliency (MS), improves upon the original Saliency Network by using the velocities of defined edges. In our results and analysis, we demonstrate the effectiveness of our approach and discuss its potential applications for computer-aided assessment of voice pathologies and understanding voice production.