Ming Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ming Tang has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Jinqiao Wang
Chinese Academy of Sciences
43 shared publications - Yingying Chen
Institute of Automation, Chinese Academy of Sciences, Beijing, China
14 shared publications - Haiyun Guo
Institute of Automation Chinese Academy of Sciences
11 shared publications - Chaoyang Zhao
Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
8 shared publications - Xu Zhao
School of Artificial Intelligence University of Chinese Academy of Sciences
8 shared publications - Bingke Zhu
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China
7 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13077-13086
TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13077-13086
Open AccessTraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1157-1165
HB-Mamba: Hierarchical Bi-directional State Space Modeling for LiDAR Semantic Segmentation in Autonomous Driving
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1157-1165
Open AccessHB-Mamba: Hierarchical Bi-directional State Space Modeling for LiDAR Semantic Segmentation in Autonomous Driving
- Top Cited Papers
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 2699-2713
Continual Instruction Tuning for Large Multimodal Models
Instruction tuning has become a widely adopted approach for aligning large multimodal models (LMMs) with human intent. It enables multi-task joint training through unified data formats. However, as new vision-language tasks constantly emerge, exhaustive joint training of all tasks becomes impractical. Continual learning offers a more flexible and resource-efficient alternative, enabling incremental training of LMMs on emerging tasks. This study investigates two fundamental questions when applying continual learning to instruction tuning of LMMs: 1) Do LMMs suffer from catastrophic forgetting during continual instruction tuning? 2) Can existing continual learning methods be effectively applied to continual instruction tuning of LMMs? A comprehensive study was conducted to answer these questions. First, we establish the first benchmark for continual instruction tuning of LMMs and reveal the phenomenon of catastrophic forgetting in this setup. Second, we integrate and adapt traditional continual learning approaches to this setting, demonstrating the effectiveness of these strategies to varying degrees in different scenarios. Third, we explore task-similarity dynamics between pairs of vision-language tasks and propose task-similarity-informed regularization and model expansion methods. Experimental results show that our approach can consistently boost the model’s performance.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 2699-2713
Top Cited PapersContinual Instruction Tuning for Large Multimodal Models
Instruction tuning has become a widely adopted approach for aligning large multimodal models (LMMs) with human intent. It enables multi-task joint training through unified data formats. However, as new vision-language tasks constantly emerge, exhaustive joint training of all tasks becomes impractical. Continual learning offers a more flexible and resource-efficient alternative, enabling incremental training of LMMs on emerging tasks. This study investigates two fundamental questions when applying continual learning to instruction tuning of LMMs: 1) Do LMMs suffer from catastrophic forgetting during continual instruction tuning? 2) Can existing continual learning methods be effectively applied to continual instruction tuning of LMMs? A comprehensive study was conducted to answer these questions. First, we establish the first benchmark for continual instruction tuning of LMMs and reveal the phenomenon of catastrophic forgetting in this setup. Second, we integrate and adapt traditional continual learning approaches to this setting, demonstrating the effectiveness of these strategies to varying degrees in different scenarios. Third, we explore task-similarity dynamics between pairs of vision-language tasks and propose task-similarity-informed regularization and model expansion methods. Experimental results show that our approach can consistently boost the model’s performance.
- Top Cited Papers
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (7) , 9616-9630
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
Anomaly detection methods typically require extensive normal samples from the target class for training, limiting their applicability in scenarios that require rapid adaptation, such as cold start. Zero-shot and few-shot anomaly detection do not require labeled samples from the target class in advance, making them a promising research direction. Existing zero-shot and few-shot approaches often leverage powerful multimodal models to detect and localize anomalies by comparing image-text similarity. However, their handcrafted generic descriptions fail to capture the diverse range of anomalies that may emerge in different objects, and simple patch-level image-text matching often struggles to localize anomalous regions of varying shapes and sizes. To address these issues, this paper proposes the FiLo++ method, which consists of two key components. The first component, Fused Fine-Grained Descriptions (FusDes), utilizes large language models to generate anomaly descriptions for each object category, combines both fixed and learnable prompt templates and applies a runtime prompt filtering method, producing more accurate and task-specific textual descriptions. The second component, Deformable Localization (DefLoc), integrates the vision foundation model Grounding DINO with position-enhanced text descriptions and a Multi-scale Deformable Cross-modal Interaction (MDCI) module, enabling accurate localization of anomalies with various shapes and sizes. In addition, we design a position-enhanced patch matching approach to improve few-shot anomaly detection performance. Experiments on multiple datasets demonstrate that FiLo++ achieves significant performance improvements compared with existing methods. Code will be available at https://github.com/CASIA-IVA-Lab/FiLo.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (7) , 9616-9630
Top Cited PapersFiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
Anomaly detection methods typically require extensive normal samples from the target class for training, limiting their applicability in scenarios that require rapid adaptation, such as cold start. Zero-shot and few-shot anomaly detection do not require labeled samples from the target class in advance, making them a promising research direction. Existing zero-shot and few-shot approaches often leverage powerful multimodal models to detect and localize anomalies by comparing image-text similarity. However, their handcrafted generic descriptions fail to capture the diverse range of anomalies that may emerge in different objects, and simple patch-level image-text matching often struggles to localize anomalous regions of varying shapes and sizes. To address these issues, this paper proposes the FiLo++ method, which consists of two key components. The first component, Fused Fine-Grained Descriptions (FusDes), utilizes large language models to generate anomaly descriptions for each object category, combines both fixed and learnable prompt templates and applies a runtime prompt filtering method, producing more accurate and task-specific textual descriptions. The second component, Deformable Localization (DefLoc), integrates the vision foundation model Grounding DINO with position-enhanced text descriptions and a Multi-scale Deformable Cross-modal Interaction (MDCI) module, enabling accurate localization of anomalies with various shapes and sizes. In addition, we design a position-enhanced patch matching approach to improve few-shot anomaly detection performance. Experiments on multiple datasets demonstrate that FiLo++ achieves significant performance improvements compared with existing methods. Code will be available at https://github.com/CASIA-IVA-Lab/FiLo.
- Open Access
GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by single-target localization and limited types of practical tasks, due to the lack of unified modeling for generalized grounding tasks. Therefore, we propose GeM-VG, an MLLM capable of Generalized Multi-image Visual Grounding. To support this, we systematically categorize and organize existing multi-image grounding tasks according to their reliance of cross-image cues and reasoning, and introduce the MG-Data-240K dataset, addressing the limitations of existing datasets regarding target quantity and image relation. To tackle the challenges of robustly handling diverse multi-image grounding tasks, we further propose a hybrid reinforcement finetuning strategy that integrates chain-of-thought (CoT) reasoning and direct answering, considering their complementary strengths. This strategy adopts an R1-like algorithm guided by a carefully designed rule-based reward, effectively enhancing the model's overall perception and reasoning capabilities. Extensive experiments demonstrate the superior generalized grounding capabilities of our model. For multi-image grounding, it outperforms the previous leading MLLMs by 2.0% and 9.7% on MIG-Bench and MC-Bench, respectively. In single-image grounding, it achieves a 9.1% improvement over the base model on ODINW. Furthermore, our model retains strong capabilities in general multi-image understanding.
Open AccessGeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by single-target localization and limited types of practical tasks, due to the lack of unified modeling for generalized grounding tasks. Therefore, we propose GeM-VG, an MLLM capable of Generalized Multi-image Visual Grounding. To support this, we systematically categorize and organize existing multi-image grounding tasks according to their reliance of cross-image cues and reasoning, and introduce the MG-Data-240K dataset, addressing the limitations of existing datasets regarding target quantity and image relation. To tackle the challenges of robustly handling diverse multi-image grounding tasks, we further propose a hybrid reinforcement finetuning strategy that integrates chain-of-thought (CoT) reasoning and direct answering, considering their complementary strengths. This strategy adopts an R1-like algorithm guided by a carefully designed rule-based reward, effectively enhancing the model's overall perception and reasoning capabilities. Extensive experiments demonstrate the superior generalized grounding capabilities of our model. For multi-image grounding, it outperforms the previous leading MLLMs by 2.0% and 9.7% on MIG-Bench and MC-Bench, respectively. In single-image grounding, it achieves a 9.1% improvement over the base model on ODINW. Furthermore, our model retains strong capabilities in general multi-image understanding.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4464-4473
Referring Expression Instance Retrieval and A Strong End-to-End Baseline
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4464-4473
Open AccessReferring Expression Instance Retrieval and A Strong End-to-End Baseline
- Open Access
- 1 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58  (1) , 1-33
Deep Learning for Human Parsing: A Survey
Human parsing has recently attracted increasing attention due to its wide applications in many areas, such as surveillance analysis, human-robot interaction, and person search. Many methods now focus on developing human parsing algorithms based on deep learning. To stimulate future research, we present the comprehensive review of recent advances in this field. This survey analyzes state-of-the-art methods, covering a broad spectrum of pioneering works for human parsing. This work introduces five insightful categories: (1) structure-driven architectures that exploit the relationship of different parts and the inherent hierarchical structure of a human body, (2) graph-based networks model part-relation reasoning to achieve an effective human body analysis, (3) context-aware networks utilize multiple types of contextual information to classify pixels accurately, (4) LSTM-based methods combine short-distance and long-distance spatial dependencies to leverage local and global contexts, and (5) combined auxiliary information approaches use related tasks to improve the performance. We also discuss the advantages and disadvantages of each category and the relationships between different methods. Additionally, we present quantitative performance comparisons of the reviewed methods on benchmark datasets. Finally, we introduce some common applications and suggest new directions for future study.
- 1 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58  (1) , 1-33
Open AccessDeep Learning for Human Parsing: A Survey
Human parsing has recently attracted increasing attention due to its wide applications in many areas, such as surveillance analysis, human-robot interaction, and person search. Many methods now focus on developing human parsing algorithms based on deep learning. To stimulate future research, we present the comprehensive review of recent advances in this field. This survey analyzes state-of-the-art methods, covering a broad spectrum of pioneering works for human parsing. This work introduces five insightful categories: (1) structure-driven architectures that exploit the relationship of different parts and the inherent hierarchical structure of a human body, (2) graph-based networks model part-relation reasoning to achieve an effective human body analysis, (3) context-aware networks utilize multiple types of contextual information to classify pixels accurately, (4) LSTM-based methods combine short-distance and long-distance spatial dependencies to leverage local and global contexts, and (5) combined auxiliary information approaches use related tasks to improve the performance. We also discuss the advantages and disadvantages of each category and the relationships between different methods. Additionally, we present quantitative performance comparisons of the reviewed methods on benchmark datasets. Finally, we introduce some common applications and suggest new directions for future study.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 11, 9501-9509
FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records
Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this potential, no specialized models for stellar flare forecasting have been proposed to date. In this paper, we present extensive experimental evidence demonstrating that both stellar physical properties and historical flare records are valuable inputs for flare forecasting tasks. We then introduce FLARE (Forecasting Light-curve-based Astronomical Records via features Ensemble), the first-of-its-kind large model specifically designed for stellar flare forecasting. FLARE integrates stellar physical properties and historical flare records through a novel Soft Prompt Module and Residual Record Fusion Module. Experiments on the Kepler light curve dataset demonstrate that FLARE achieves superior performance compared to other methods across all evaluation metrics. Finally, we validate the forecast capability of our model through a comprehensive case study.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 11, 9501-9509
Open AccessFLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records
Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this potential, no specialized models for stellar flare forecasting have been proposed to date. In this paper, we present extensive experimental evidence demonstrating that both stellar physical properties and historical flare records are valuable inputs for flare forecasting tasks. We then introduce FLARE (Forecasting Light-curve-based Astronomical Records via features Ensemble), the first-of-its-kind large model specifically designed for stellar flare forecasting. FLARE integrates stellar physical properties and historical flare records through a novel Soft Prompt Module and Residual Record Fusion Module. Experiments on the Kepler light curve dataset demonstrate that FLARE achieves superior performance compared to other methods across all evaluation metrics. Finally, we validate the forecast capability of our model through a comprehensive case study.
- 16 August 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22  (6) , 1116-1126
Semi-supervised Learning for Detector-free Multi-person Pose Estimation
- 16 August 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22  (6) , 1116-1126
Semi-supervised Learning for Detector-free Multi-person Pose Estimation
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27  (15209210) , 7557-7569
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
Vision-language models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage the potential of VLMs in adapting to downstream tasks, context optimization methods such as prompt tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks. To address this challenge, we propose context optimization with multi-knowledge representation (CoKnow), a framework that enhances prompt learning for VLMs with rich contextual knowledge. To facilitate CoKnow during inference, we train lightweight semantic knowledge mappers, which are capable of generating multi-knowledge representations for an input image without requiring additional priors. Experimentally, we conduct extensive experiments on 11 publicly available datasets, demonstrating that CoKnow outperforms a series of previous methods.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27  (15209210) , 7557-7569
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
Vision-language models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage the potential of VLMs in adapting to downstream tasks, context optimization methods such as prompt tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks. To address this challenge, we propose context optimization with multi-knowledge representation (CoKnow), a framework that enhances prompt learning for VLMs with rich contextual knowledge. To facilitate CoKnow during inference, we train lightweight semantic knowledge mappers, which are capable of generating multi-knowledge representations for an input image without requiring additional priors. Experimentally, we conduct extensive experiments on 11 publicly available datasets, demonstrating that CoKnow outperforms a series of previous methods.