Jing Huang
Research Subjects
Jing Huang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Changtao Miao
University of Science and Technology of China, Hefei, China
2 shared publications - Jianshu Li
Ant Group
2 shared publications - Joey Tianyi Zhou
Singapore Management University, Singapore, Singapore and Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
2 shared publications - Tianyi Zhang
Huawei Singapore Research Center, Singapore, Singapore
2 shared publications - Wei Shi
Huawei Singapore Research Center, Singapore, Singapore
2 shared publications - Zhiya Tan
Nanyang technological university, Singapore, Singapore
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9432-9441
Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detection
Conventional image forgery detection methods produce only binary scores or pixel-level masks without interpretable evidence, while recent multimodal large language model (MLLM)-based approaches generate textual explanations that are merely post-hoc verbalizations of pre-determined classification results rather than products of genuine reasoning. Inspired by the forensic workflow of human judicial experts---''experimental analysis -- logical reasoning -- scientific evidence''---we propose an Agentic Tool-Augmented Reasoning (ATAR) framework for explainable image forgery detection, integrating 22 specialized forensic tools spanning seven complementary domains to autonomously detect, localize, and explain image forgeries through multi-turn reasoning. Concretely, we propose a Dual-Stream Forensic Reasoning paradigm to emulate the experimental analysis process of forensic experts: (1) a high-level semantic anomaly path, which magnifies suspicious regions for fine-grained inspection; and (2) a low-level forgery artifact path, which invokes forensic tools to extract objective artifactual evidence. To this end, we further propose a Forensics Curriculum Learning training strategy. First, during the General Experience SFT stage, an automated teacher--student mentoring pipeline is designed to synthesize multi-turn tool-usage reasoning trajectories. Subsequently, during the Forensic Scene RL stage, a Tool Prior Curriculum is introduced to guide early tool exploration and progressively transfer control to the agent, while a Structured Evidence Reward provides fine-grained process-level supervision. Experiments across IMDL, Deepfake detection, DMDL, and AIGC detection show that ATAR achieves 78.5% average image-level F1 on six zero-shot IMDL benchmarks, surpassing the strongest MLLM baseline by 11.8 percentage points, and remains competitive with specialized detectors on other tasks, while producing substantially more faithful and grounded explanations.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9432-9441
Open AccessAgentic Tool-Augmented Reasoning for Explainable Image Forgery Detection
Conventional image forgery detection methods produce only binary scores or pixel-level masks without interpretable evidence, while recent multimodal large language model (MLLM)-based approaches generate textual explanations that are merely post-hoc verbalizations of pre-determined classification results rather than products of genuine reasoning. Inspired by the forensic workflow of human judicial experts---''experimental analysis -- logical reasoning -- scientific evidence''---we propose an Agentic Tool-Augmented Reasoning (ATAR) framework for explainable image forgery detection, integrating 22 specialized forensic tools spanning seven complementary domains to autonomously detect, localize, and explain image forgeries through multi-turn reasoning. Concretely, we propose a Dual-Stream Forensic Reasoning paradigm to emulate the experimental analysis process of forensic experts: (1) a high-level semantic anomaly path, which magnifies suspicious regions for fine-grained inspection; and (2) a low-level forgery artifact path, which invokes forensic tools to extract objective artifactual evidence. To this end, we further propose a Forensics Curriculum Learning training strategy. First, during the General Experience SFT stage, an automated teacher--student mentoring pipeline is designed to synthesize multi-turn tool-usage reasoning trajectories. Subsequently, during the Forensic Scene RL stage, a Tool Prior Curriculum is introduced to guide early tool exploration and progressively transfer control to the agent, while a Structured Evidence Reward provides fine-grained process-level supervision. Experiments across IMDL, Deepfake detection, DMDL, and AIGC detection show that ATAR achieves 78.5% average image-level F1 on six zero-shot IMDL benchmarks, surpassing the strongest MLLM baseline by 11.8 percentage points, and remains competitive with specialized detectors on other tasks, while producing substantially more faithful and grounded explanations.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8262-8273
LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8262-8273
Open AccessLaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 15-22
SAT: Self-Attention Control for Diffusion Models Training
Recent text-to-image diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, a persistent challenge lies in the generation of detailed images, especially human-related images, which often exhibit distorted faces and eyes. Existing approaches to address this issue either involve the utilization of more specific yet lengthy prompts or the direct application of restoration tools to the generated image. Besides, a few studies have shown that attention maps can enhance diffusion models' stability by guiding intermediate samples during the inference process. In this paper, we propose a novel training strategy (SAT) to improve the sample quality during the training process. To address this issue in a straightforward manner, we introduce blur guidance as a solution to refine intermediate samples, enabling diffusion models to produce higher-quality outputs with a moderate ratio of control. Improving upon this, SAT leverages the intermediate attention maps of diffusion models to further improve training sample quality. Specifically, SAT adversarially blurs only the regions that diffusion models attend to and guide them during the training process. We examine and compare both cross-attention mask control (CAC) and self-attention mask control (SAC) based on stable diffusion (SD) V-1.5, and our results show that our method under SAC (i.e SAT) improves the performance of stable diffusion.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 15-22
Open AccessSAT: Self-Attention Control for Diffusion Models Training
Recent text-to-image diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, a persistent challenge lies in the generation of detailed images, especially human-related images, which often exhibit distorted faces and eyes. Existing approaches to address this issue either involve the utilization of more specific yet lengthy prompts or the direct application of restoration tools to the generated image. Besides, a few studies have shown that attention maps can enhance diffusion models' stability by guiding intermediate samples during the inference process. In this paper, we propose a novel training strategy (SAT) to improve the sample quality during the training process. To address this issue in a straightforward manner, we introduce blur guidance as a solution to refine intermediate samples, enabling diffusion models to produce higher-quality outputs with a moderate ratio of control. Improving upon this, SAT leverages the intermediate attention maps of diffusion models to further improve training sample quality. Specifically, SAT adversarially blurs only the regions that diffusion models attend to and guide them during the training process. We examine and compare both cross-attention mask control (CAC) and self-attention mask control (SAC) based on stable diffusion (SD) V-1.5, and our results show that our method under SAC (i.e SAT) improves the performance of stable diffusion.
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 34-44
ImEW: A Framework for Editing Image in the Wild
The ability to edit images in a realistic and visually appealing manner is a fundamental requirement in various computer vision applications. In this paper, we present ImEW, a unified framework designed for solving image editing tasks. ImEW utilizes off-the-shelf foundation models to address four essential editing tasks: object removal, object translation, object replacement, and generative fill beyond the image frame. These tasks are accomplished by leveraging the capabilities of state-of-the-art foundation models, namely the Segment Anything Model, Grounding DINO, LaMa, and Stable Diffusion. These models have undergone extensive training on large-scale datasets and have exhibited exceptional performance in understanding image context, object manipulation, and texture synthesis. Through extensive experimentation, we demonstrate the effectiveness and versatility of ImEW in accomplishing image editing tasks across a wide range of real-world scenarios. The proposed framework opens up new possibilities for realistic and visually appealing image editing and enables diverse applications requiring sophisticated image modifications. Additionally, we discuss the limitations and outline potential directions for future research in the field of image editing using off-the-shelf foundation models, enabling continued advancements in this domain.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 34-44
Open AccessImEW: A Framework for Editing Image in the Wild
The ability to edit images in a realistic and visually appealing manner is a fundamental requirement in various computer vision applications. In this paper, we present ImEW, a unified framework designed for solving image editing tasks. ImEW utilizes off-the-shelf foundation models to address four essential editing tasks: object removal, object translation, object replacement, and generative fill beyond the image frame. These tasks are accomplished by leveraging the capabilities of state-of-the-art foundation models, namely the Segment Anything Model, Grounding DINO, LaMa, and Stable Diffusion. These models have undergone extensive training on large-scale datasets and have exhibited exceptional performance in understanding image context, object manipulation, and texture synthesis. Through extensive experimentation, we demonstrate the effectiveness and versatility of ImEW in accomplishing image editing tasks across a wide range of real-world scenarios. The proposed framework opens up new possibilities for realistic and visually appealing image editing and enables diverse applications requiring sophisticated image modifications. Additionally, we discuss the limitations and outline potential directions for future research in the field of image editing using off-the-shelf foundation models, enabling continued advancements in this domain.