Qinya Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qinya Li has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Fan Wu
Shanghai Jiao Tong University, Shanghai, China
12 shared publications - Guihai Chen
Shanghai Jiao Tong University
8 shared publications - Zhenzhe Zheng
Shanghai Jiao Tong University, Shanghai, China
6 shared publications - Chaoyue Niu
Shanghai Jiao Tong University, Shanghai, China
3 shared publications - Bin Gao
National University of Singapore
2 shared publications Bowen Sheng
Shanghai Jiao Tong University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12232-12241
PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12232-12241
Open AccessPixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 21106-21118
StarCollab: An Adaptive Co-Optimization Framework for Efficient Space-Ground Collaboration
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 21106-21118
StarCollab: An Adaptive Co-Optimization Framework for Efficient Space-Ground Collaboration
- 1 March 2026
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 41 (2) , 761-773
Grouping Algorithms for Optimal Configuration of Virtual Links in Avionics Full-Duplex Switched Ethernet
- 1 March 2026
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 41 (2) , 761-773
Grouping Algorithms for Optimal Configuration of Virtual Links in Avionics Full-Duplex Switched Ethernet
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11890-11898
Device-Cloud Collaborative Learning Framework for Efficient Unknown Object Detection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11890-11898
Open AccessDevice-Cloud Collaborative Learning Framework for Efficient Unknown Object Detection
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 6092-6101
Scale-Shift Attention in Polarization Domain for Fine-Grained Classification of Satellite ISAR Images
Traditional fine-grained classification focuses on visible light domains, such as animals and cars. However, these methods often perform poorly when applied to radar images and images of satellites because of challenges such as distinguishing between noise and objects and the significant scale differences among object components. To address these unique scenarios, we propose the scale-shift attention in polarization domain (SAPD) method for fine-grained classification in satellite ISAR images. Specifically, radar emits different types of waves, each with distinct imaging effects. We utilize multipolarization inputs and introduce a polarization domain query module to integrate complementary features from various radar wave types captured from the same viewpoint. This multipolarization learning helps distinguish noise and leverages complementary features from different inputs. Moreover, to handle the substantial scale differences between centimeter-level payloads and the overall meter-level structure of satellites, we propose a scale-shift attention mechanism based on shift kernels. This mechanism extends attention in the direction specified by the shift kernel by incorporating adjacent pixels, allowing for the diffusion of attention. This is beneficial for capturing features of satellite components with varying scales and shapes. Extensive experiments on a novel satellite ISAR image dataset validate the effectiveness and superiority of the SAPD.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 6092-6101
Scale-Shift Attention in Polarization Domain for Fine-Grained Classification of Satellite ISAR Images
Traditional fine-grained classification focuses on visible light domains, such as animals and cars. However, these methods often perform poorly when applied to radar images and images of satellites because of challenges such as distinguishing between noise and objects and the significant scale differences among object components. To address these unique scenarios, we propose the scale-shift attention in polarization domain (SAPD) method for fine-grained classification in satellite ISAR images. Specifically, radar emits different types of waves, each with distinct imaging effects. We utilize multipolarization inputs and introduce a polarization domain query module to integrate complementary features from various radar wave types captured from the same viewpoint. This multipolarization learning helps distinguish noise and leverages complementary features from different inputs. Moreover, to handle the substantial scale differences between centimeter-level payloads and the overall meter-level structure of satellites, we propose a scale-shift attention mechanism based on shift kernels. This mechanism extends attention in the direction specified by the shift kernel by incorporating adjacent pixels, allowing for the diffusion of attention. This is beneficial for capturing features of satellite components with varying scales and shapes. Extensive experiments on a novel satellite ISAR image dataset validate the effectiveness and superiority of the SAPD.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 24050-24058
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes AdaSkip, an adaptive sublayer skipping method specifically designed for long-context inference. AdaSkip adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of AdaSkip is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 24050-24058
Open AccessAdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes AdaSkip, an adaptive sublayer skipping method specifically designed for long-context inference. AdaSkip adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of AdaSkip is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21761-21769
Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation
In an era overwhelmed by vast amounts of data, the effective curation of web-crawl datasets is essential for optimizing model performance. This paper tackles the challenges associated with the unstructured and heterogeneous nature of such datasets. Traditional heuristic curation methods often inadequately capture complex features, resulting in biases and the exclusion of relevant data. We introduce an advanced, learning-driven approach, Ensemble Curation Of DAta ThroUgh Multimodal Operators, called EcoDatum, which employs a novel quality-guided deduplication method to balance feature distribution. EcoDatum strategically integrates various unimodal and multimodal data curation operators within a weak supervision ensemble framework, utilizing automated optimization to effectively score each data point. EcoDatum, which significantly improves the data curation quality and efficiency, outperforms existing state-of-the-art (SOTA) techniques, ranking 1st on the DataComp leaderboard with an average performance score of 0.182 across 38 diverse evaluation datasets. This represents a 28% improvement over the DataComp baseline method, demonstrating its effectiveness in improving dataset curation and model training efficiency.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21761-21769
Open AccessQuality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation
In an era overwhelmed by vast amounts of data, the effective curation of web-crawl datasets is essential for optimizing model performance. This paper tackles the challenges associated with the unstructured and heterogeneous nature of such datasets. Traditional heuristic curation methods often inadequately capture complex features, resulting in biases and the exclusion of relevant data. We introduce an advanced, learning-driven approach, Ensemble Curation Of DAta ThroUgh Multimodal Operators, called EcoDatum, which employs a novel quality-guided deduplication method to balance feature distribution. EcoDatum strategically integrates various unimodal and multimodal data curation operators within a weak supervision ensemble framework, utilizing automated optimization to effectively score each data point. EcoDatum, which significantly improves the data curation quality and efficiency, outperforms existing state-of-the-art (SOTA) techniques, ranking 1st on the DataComp leaderboard with an average performance score of 0.182 across 38 diverse evaluation datasets. This represents a 28% improvement over the DataComp baseline method, demonstrating its effectiveness in improving dataset curation and model training efficiency.
- Open Access
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
Open AccessAdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
- Open Access
- 21 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 8 (4) , 1-30
SemiCMT: Contrastive Cross-Modal Knowledge Transfer for IoT Sensing with Semi-Paired Multi-Modal Signals
This paper proposes a novel contrastive cross-modal knowledge transfer framework, SemiCMT, for multi-modal IoT sensing applications. It effectively transfers the feature extraction capability (also called knowledge) learned from a source modality (e.g., acoustic signals) with abundant unlabeled training data, to a target modality (e.g., seismic signals) that lacks enough training data, in a self-supervised manner with the help of only a small set of synchronized multi-modal pairs. The transferred model can be quickly finetuned to downstream target-modal tasks with only limited labels. The key design constitutes of three aspects: First, we factorize the latent embedding of each modality into shared and private components and perform knowledge transfer considering both the modality information commonality and gaps. Second, we enforce structural correlation constraints between the source modality and the target modality, to push the target modal embedding space symmetric to the source modal embedding space, with the anchoring of additional source-modal samples, which expands the existing modal-matching objective in current multi-modal contrastive frameworks. Finally, we conduct downstream task finetuning in the spherical space with a KNN classifier to better align with the structured modality embedding space. Extensive evaluations on five multimodal IoT datasets are performed to validate the effectiveness of SemiCMT in cross-modal knowledge transfer, including a new self-collected dataset using seismic and acoustic signals for office activity monitoring. SemiCMT consistently outperforms existing self-supervised and knowledge transfer approaches by up to 36.47% in the finetuned target-modal classification tasks. The code and the self-collected dataset will be released at https://github.com/SJTU-RTEAS/SemiCMT.
- 21 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 8 (4) , 1-30
Open AccessSemiCMT: Contrastive Cross-Modal Knowledge Transfer for IoT Sensing with Semi-Paired Multi-Modal Signals
This paper proposes a novel contrastive cross-modal knowledge transfer framework, SemiCMT, for multi-modal IoT sensing applications. It effectively transfers the feature extraction capability (also called knowledge) learned from a source modality (e.g., acoustic signals) with abundant unlabeled training data, to a target modality (e.g., seismic signals) that lacks enough training data, in a self-supervised manner with the help of only a small set of synchronized multi-modal pairs. The transferred model can be quickly finetuned to downstream target-modal tasks with only limited labels. The key design constitutes of three aspects: First, we factorize the latent embedding of each modality into shared and private components and perform knowledge transfer considering both the modality information commonality and gaps. Second, we enforce structural correlation constraints between the source modality and the target modality, to push the target modal embedding space symmetric to the source modal embedding space, with the anchoring of additional source-modal samples, which expands the existing modal-matching objective in current multi-modal contrastive frameworks. Finally, we conduct downstream task finetuning in the spherical space with a KNN classifier to better align with the structured modality embedding space. Extensive evaluations on five multimodal IoT datasets are performed to validate the effectiveness of SemiCMT in cross-modal knowledge transfer, including a new self-collected dataset using seismic and acoustic signals for office activity monitoring. SemiCMT consistently outperforms existing self-supervised and knowledge transfer approaches by up to 36.47% in the finetuned target-modal classification tasks. The code and the self-collected dataset will be released at https://github.com/SJTU-RTEAS/SemiCMT.
- 28 August 2024
- Published by Springer Nature
- p. 391-406
GIPUT: Maximizing Photo Coverage Efficiency for UAV Trajectory
- 28 August 2024
- Published by Springer Nature
- p. 391-406
GIPUT: Maximizing Photo Coverage Efficiency for UAV Trajectory