Yang Tan
Yang Tan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Enming Zhang
Shenzhen Key Laboratory of Ubiquitous Data Enablingm Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication- Haisong Gu
Ping An (China) image/svg+xml
1 shared publication - Liang Diao
Ping An (China) image/svg+xml
1 shared publication - Shao-Lun Huang
Tsinghua University
1 shared publication - Wei Wu
Ping An (China) image/svg+xml
1 shared publication - Wenjie Wang
Ping An (China) image/svg+xml
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by TIB Open Publishing in Open Conference Proceedings
- Vol. 10
DeepVitminC at Sci-ImageMiner 2026 Tasks 3&4: Structured Context Augmentation for Scientific Figure Reasoning
Scientific figures encode critical experimental findings that are often not fully captured in textual descriptions. Despite recent advances in MLLMs, their performance on domain-specific scientific figures remains limited due to insufficient grounding in relevant context. In this work, we focus on in Task 3 (summarization) and Task 4 (visual question answering) of the Sci-ImageMiner 2026 challenge. We propose a structured context augmentation approach that improves model performance by providing relevant and well-organized contextual inputs. Our method extracts figure-centric and cross-referenced textual evidence from scientific papers and integrates them into structured prompts for model training. Experimental results show that our approach consistently improves performance across both tasks. We achieve first place in both Task 3 and Task 4, demonstrating the effectiveness of structured contextual inputs for scientific figure reasoning. Code is available at https://github.com/yuanjun0416/SciImageMiner34
- 1 September 2026
- Published by TIB Open Publishing in Open Conference Proceedings
- Vol. 10
Open AccessDeepVitminC at Sci-ImageMiner 2026 Tasks 3&4: Structured Context Augmentation for Scientific Figure Reasoning
Scientific figures encode critical experimental findings that are often not fully captured in textual descriptions. Despite recent advances in MLLMs, their performance on domain-specific scientific figures remains limited due to insufficient grounding in relevant context. In this work, we focus on in Task 3 (summarization) and Task 4 (visual question answering) of the Sci-ImageMiner 2026 challenge. We propose a structured context augmentation approach that improves model performance by providing relevant and well-organized contextual inputs. Our method extracts figure-centric and cross-referenced textual evidence from scientific papers and integrates them into structured prompts for model training. Experimental results show that our approach consistently improves performance across both tasks. We achieve first place in both Task 3 and Task 4, demonstrating the effectiveness of structured contextual inputs for scientific figure reasoning. Code is available at https://github.com/yuanjun0416/SciImageMiner34
- 5 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (2) , 2423-2436
Transferability-Guided Cross-Domain Cross-Task Transfer Learning
We propose two novel transferability metrics fast optimal transport-based conditional entropy (F-OTCE) and joint correspondence OTCE (JC-OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more generalizable representations for cross-domain cross-task transfer learning. Unlike the original OTCE metric that requires evaluating the empirical transferability on auxiliary tasks, our metrics are auxiliary-free such that they can be computed much more efficiently. Specifically, F-OTCE estimates transferability by first solving an optimal transport (OT) problem between source and target distributions and then uses the optimal coupling to compute the negative conditional entropy (NCE) between the source and target labels. It can also serve as an objective function to enhance downstream transfer learning tasks including model finetuning and domain generalization (DG). Meanwhile, JC-OTCE improves the transferability accuracy of F-OTCE by including label distances in the OT problem, though it incurs additional computation costs. Extensive experiments demonstrate that F-OTCE and JC-OTCE outperform state-of-the-art auxiliary-free metrics by $21.1\%$ and $25.8\%$ , respectively, in correlation coefficient with the ground-truth transfer accuracy. By eliminating the training cost of auxiliary tasks, the two metrics reduce the total computation time of the previous method from 43 min to 9.32 and 10.78 s, respectively, for a pair of tasks. When applied in the model finetuning and DG tasks, F-OTCE shows significant improvements in the transfer accuracy in few-shot classification experiments, with up to $4.41\%$ and $2.34\%$ accuracy gains, respectively.
- 5 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (2) , 2423-2436
Transferability-Guided Cross-Domain Cross-Task Transfer Learning
We propose two novel transferability metrics fast optimal transport-based conditional entropy (F-OTCE) and joint correspondence OTCE (JC-OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more generalizable representations for cross-domain cross-task transfer learning. Unlike the original OTCE metric that requires evaluating the empirical transferability on auxiliary tasks, our metrics are auxiliary-free such that they can be computed much more efficiently. Specifically, F-OTCE estimates transferability by first solving an optimal transport (OT) problem between source and target distributions and then uses the optimal coupling to compute the negative conditional entropy (NCE) between the source and target labels. It can also serve as an objective function to enhance downstream transfer learning tasks including model finetuning and domain generalization (DG). Meanwhile, JC-OTCE improves the transferability accuracy of F-OTCE by including label distances in the OT problem, though it incurs additional computation costs. Extensive experiments demonstrate that F-OTCE and JC-OTCE outperform state-of-the-art auxiliary-free metrics by $21.1\%$ and $25.8\%$ , respectively, in correlation coefficient with the ground-truth transfer accuracy. By eliminating the training cost of auxiliary tasks, the two metrics reduce the total computation time of the previous method from 43 min to 9.32 and 10.78 s, respectively, for a pair of tasks. When applied in the model finetuning and DG tasks, F-OTCE shows significant improvements in the transfer accuracy in few-shot classification experiments, with up to $4.41\%$ and $2.34\%$ accuracy gains, respectively.