Qian Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Qian Liu has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Erik Cambria
Nanyang technological university, Singapore, Singapore
6 shared publications - Bobo Li
National University of Singapore, Singapore, Singapore
3 shared publications - Hao Fei
National University of Singapore, Singapore, Singapore
3 shared publications - Meng Luo
National University of Singapore, Singapore, Singapore
3 shared publications - Mong Li Lee
National University of Singapore, Singapore, Singapore
3 shared publications Erik Cambria
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11182-11190
SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11182-11190
Open AccessSDO: Subspace Deconflicting Operator for Multi-Adapter Composition
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 867-879
Towards Fully Automated Medical Imaging Code Generation via Validation-Based Context Engineering
Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; however, they remain limited when applied to complex, domain-specific tasks such as medical image processing. General-purpose models lack explicit domain knowledge and robust validation mechanisms to ensure correctness, often requiring substantial human intervention to produce reliable processing pipelines. To address these limitations, we propose AutoMedImg, a multi-agent framework for fully automated medical image processing code generation. AutoMedImg orchestrates specialised agents across two phases: a Planning Phase that performs dataset analysis and architecture design with semantic and formal verification, and a Coding Phase that generates modules in parallel with static checking, execution testing, and assembly validation. This multi-stage validation mitigates error propagation throughout generation, while comprehensive auto-context engineering combining domain-specific knowledge bases, shared memory, and validation feedback automates context construction without manual prompting. A cross-project adaptive pipeline synthesis mechanism further accumulates validated pipelines and retrieves proven components for new tasks based on project similarity, enhancing generation efficiency through cross-project learning. Extensive evaluation across six diverse and well-established medical imaging datasets with five backbone LLMs demonstrates that AutoMedImg achieves zero human intervention, with Dice scores of up to 0.90 for segmentation tasks and 99% accuracy for classification.
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 867-879
Open AccessTowards Fully Automated Medical Imaging Code Generation via Validation-Based Context Engineering
Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; however, they remain limited when applied to complex, domain-specific tasks such as medical image processing. General-purpose models lack explicit domain knowledge and robust validation mechanisms to ensure correctness, often requiring substantial human intervention to produce reliable processing pipelines. To address these limitations, we propose AutoMedImg, a multi-agent framework for fully automated medical image processing code generation. AutoMedImg orchestrates specialised agents across two phases: a Planning Phase that performs dataset analysis and architecture design with semantic and formal verification, and a Coding Phase that generates modules in parallel with static checking, execution testing, and assembly validation. This multi-stage validation mitigates error propagation throughout generation, while comprehensive auto-context engineering combining domain-specific knowledge bases, shared memory, and validation feedback automates context construction without manual prompting. A cross-project adaptive pipeline synthesis mechanism further accumulates validated pipelines and retrieves proven components for new tasks based on project similarity, enhancing generation efficiency through cross-project learning. Extensive evaluation across six diverse and well-established medical imaging datasets with five backbone LLMs demonstrates that AutoMedImg achieves zero human intervention, with Dice scores of up to 0.90 for segmentation tasks and 99% accuracy for classification.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7178-7188
TrueLens: Video Fake News Detection with Dual Level Evidence Gathering and Consolidation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7178-7188
Open AccessTrueLens: Video Fake News Detection with Dual Level Evidence Gathering and Consolidation
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
CharCom: Composable Identity Control for Multi-Character Story Illustration
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessCharCom: Composable Identity Control for Multi-Character Story Illustration
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6549-6553
HUSK: A Hierarchically Structured Urban Knowledge Graph Dataset for Multi-Level Spatial Tasks
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6549-6553
Open AccessHUSK: A Hierarchically Structured Urban Knowledge Graph Dataset for Multi-Level Spatial Tasks
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14323-14325
CogMAEC'25: The 1st Workshop on Cognition-oriented Multimodal Affective and Empathetic Computing
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14323-14325
Open AccessCogMAEC'25: The 1st Workshop on Cognition-oriented Multimodal Affective and Empathetic Computing
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14101-14106
The ACM Multimedia 2025 Grand Challenge of Multimodal Conversational Aspect-based Sentiment Analysis
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14101-14106
Open AccessThe ACM Multimedia 2025 Grand Challenge of Multimodal Conversational Aspect-based Sentiment Analysis
- Open Access
- 15 July 2025
- Published by Elsevier in Information Fusion
- Vol. 125
Legal knowledge infusion for large language models: A survey
- 15 July 2025
- Published by Elsevier in Information Fusion
- Vol. 125
Open AccessLegal knowledge infusion for large language models: A survey
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7667-7676
PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly integrating multimodality, conversation context, fine-granularity, and also covering the changing sentiment dynamics as well as cognitive causal rationales. This paper bridges the gaps by introducing a multimodal conversational ABSA, where two novel subtasks are proposed: 1) Panoptic Sentiment Sextuple Extraction, panoramically recognizing holder, target, aspect, opinion, sentiment, rationale from multi-turn multi-party multimodal dialogue. 2) Sentiment Flipping Analysis, detecting the dynamic sentiment transformation throughout the conversation with the causal reasons. To benchmark the tasks, we construct PanoSent, a dataset annotated both manually and automatically, featuring high quality, large scale, multimodality, multilingualism, multi-scenarios, and covering both implicit&explicit sentiment elements. To effectively address the tasks, we devise a novel Chain-of-Sentiment reasoning framework, together with a novel multimodal large language model (namely Sentica) and a paraphrase-based verification mechanism. Extensive evaluations demonstrate the superiority of our methods over strong baselines, validating the efficacy of all our proposed methods. The work is expected to open up a new era for the ABSA community, and thus all our codes and data are open at https://PanoSent.github.io/.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7667-7676
Open AccessPanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly integrating multimodality, conversation context, fine-granularity, and also covering the changing sentiment dynamics as well as cognitive causal rationales. This paper bridges the gaps by introducing a multimodal conversational ABSA, where two novel subtasks are proposed: 1) Panoptic Sentiment Sextuple Extraction, panoramically recognizing holder, target, aspect, opinion, sentiment, rationale from multi-turn multi-party multimodal dialogue. 2) Sentiment Flipping Analysis, detecting the dynamic sentiment transformation throughout the conversation with the causal reasons. To benchmark the tasks, we construct PanoSent, a dataset annotated both manually and automatically, featuring high quality, large scale, multimodality, multilingualism, multi-scenarios, and covering both implicit&explicit sentiment elements. To effectively address the tasks, we devise a novel Chain-of-Sentiment reasoning framework, together with a novel multimodal large language model (namely Sentica) and a paraphrase-based verification mechanism. Extensive evaluations demonstrate the superiority of our methods over strong baselines, validating the efficacy of all our proposed methods. The work is expected to open up a new era for the ABSA community, and thus all our codes and data are open at https://PanoSent.github.io/.
- Open Access
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (1) , 1-24
Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning
Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR , using S eparate Relation R epresentation and L ogical R easoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct relational reasoning. Extensive experiments on two publicly available benchmark datasets demonstrate the effectiveness of our proposed SRLR as compared to 19 baseline models. Further ablation study also verifies the effects of the key components.
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (1) , 1-24
Open AccessDocument-level Relation Extraction via Separate Relation Representation and Logical Reasoning
Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR , using S eparate Relation R epresentation and L ogical R easoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct relational reasoning. Extensive experiments on two publicly available benchmark datasets demonstrate the effectiveness of our proposed SRLR as compared to 19 baseline models. Further ablation study also verifies the effects of the key components.