Yijun Tian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yijun Tian has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Nitesh V. Chawla
University of Notre Dame, Notre Dame, Indiana, USA
7 shared publications - Chunhui Zhang
Dartmouth College, Hanover, NH, USA
4 shared publications - Chuxu Zhang
University of Connecticut, Storrs, CT, USA
4 shared publications - Xiangliang Zhang
University of Notre Dame
3 shared publications - Zheyuan Liu
University of Notre Dame
3 shared publications - Yanfang Ye
Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8125-8134
Can Visual Input Be Compressed? A Visual Input Token Compression Benchmark for Large Multimodal Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8125-8134
Open AccessCan Visual Input Be Compressed? A Visual Input Token Compression Benchmark for Large Multimodal Models
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3839-3849
The Role of User-Item Connectivity in CTR Prediction
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3839-3849
Open AccessThe Role of User-Item Connectivity in CTR Prediction
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4298-4304
LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4298-4304
Open AccessLACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2599-2609
Towards Few-shot Chemical Reaction Outcome Prediction
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2599-2609
Open AccessTowards Few-shot Chemical Reaction Outcome Prediction
- Top Cited PapersOpen Access
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (8) , 1-16
Class-Imbalanced Learning on Graphs: A Survey
Rapid advancement in machine learning is increasing the demand for effective graph data analysis. However, real-world graph data often exhibits class imbalance, leading to poor performance of standard machine learning models on underrepresented classes. To address this, C lass- I mbalanced L earning on G raphs (CILG) has emerged as a promising solution that combines graph representation learning and class-imbalanced learning. This survey provides a comprehensive understanding of CILG’s current state-of-the-art, establishing the first systematic taxonomy of existing work and its connections to traditional imbalanced learning. We critically analyze recent advances and discuss key open problems. A continuously updated reading list of relevant articles and code implementations is available at https://github.com/yihongma/CILG-Papers .
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (8) , 1-16
Top Cited PapersOpen AccessClass-Imbalanced Learning on Graphs: A Survey
Rapid advancement in machine learning is increasing the demand for effective graph data analysis. However, real-world graph data often exhibits class imbalance, leading to poor performance of standard machine learning models on underrepresented classes. To address this, C lass- I mbalanced L earning on G raphs (CILG) has emerged as a promising solution that combines graph representation learning and class-imbalanced learning. This survey provides a comprehensive understanding of CILG’s current state-of-the-art, establishing the first systematic taxonomy of existing work and its connections to traditional imbalanced learning. We critically analyze recent advances and discuss key open problems. A continuously updated reading list of relevant articles and code implementations is available at https://github.com/yihongma/CILG-Papers .
- Top Cited PapersOpen Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 251-260
Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation stands out due to its outstanding efficiency and generalization. However, existing methods suffer from several drawbacks, including limited knowledge diversity and the lack of rich contextual information. To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small student LLM from multiple large teacher LLMs. In particular, we encourage the student LLM to not only generate the correct answers but also understand the rationales behind these answers. Given that different LLMs possess diverse reasoning skills, we guide the student model to assimilate knowledge from various teacher LLMs. We further introduce an in-context example generator and a teacher-forcing Chain-of-Thought strategy to ensure that the rationales are accurate and grounded in contextually appropriate scenarios. Extensive experiments on six datasets across two reasoning tasks demonstrate the superiority of our method. Results show that TinyLLM can outperform large teacher LLMs significantly, despite a considerably smaller model size. The source code is available at: https://github.com/YikunHan42/TinyLLM.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 251-260
Top Cited PapersOpen AccessBeyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation stands out due to its outstanding efficiency and generalization. However, existing methods suffer from several drawbacks, including limited knowledge diversity and the lack of rich contextual information. To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small student LLM from multiple large teacher LLMs. In particular, we encourage the student LLM to not only generate the correct answers but also understand the rationales behind these answers. Given that different LLMs possess diverse reasoning skills, we guide the student model to assimilate knowledge from various teacher LLMs. We further introduce an in-context example generator and a teacher-forcing Chain-of-Thought strategy to ensure that the rationales are accurate and grounded in contextually appropriate scenarios. Extensive experiments on six datasets across two reasoning tasks demonstrate the superiority of our method. Results show that TinyLLM can outperform large teacher LLMs significantly, despite a considerably smaller model size. The source code is available at: https://github.com/YikunHan42/TinyLLM.
- Top Cited PapersOpen Access
- 5 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (8) , 1-16
Knowledge Distillation on Graphs: A Survey
Graph Neural Networks (GNNs) have received significant attention for demonstrating their capability to handle graph data. However, they are difficult to be deployed in resource-limited devices because of model sizes and scalability constraints imposed by the multi-hop data dependency. In addition, real-world graphs usually possess complex structural information and features. Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, Knowledge Distillation on Graphs (KDG) has been introduced to build a smaller but effective model, leading to model compression and performance improvement. Recently, KDG has achieved considerable progress, with many studies proposed. In this survey, we systematically review these works. Specifically, we first introduce the challenges and bases of KDG, then categorize and summarize the existing work of KDG by answering the following three questions: (1) what to distillate, (2) who to whom, and (3) how to distillate. We offer in-depth comparisons and elucidate the strengths and weaknesses of each design. Finally, we share our thoughts on future research directions.
- 5 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (8) , 1-16
Top Cited PapersOpen AccessKnowledge Distillation on Graphs: A Survey
Graph Neural Networks (GNNs) have received significant attention for demonstrating their capability to handle graph data. However, they are difficult to be deployed in resource-limited devices because of model sizes and scalability constraints imposed by the multi-hop data dependency. In addition, real-world graphs usually possess complex structural information and features. Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, Knowledge Distillation on Graphs (KDG) has been introduced to build a smaller but effective model, leading to model compression and performance improvement. Recently, KDG has achieved considerable progress, with many studies proposed. In this survey, we systematically review these works. Specifically, we first introduce the challenges and bases of KDG, then categorize and summarize the existing work of KDG by answering the following three questions: (1) what to distillate, (2) who to whom, and (3) how to distillate. We offer in-depth comparisons and elucidate the strengths and weaknesses of each design. Finally, we share our thoughts on future research directions.
- 31 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 268
Mixture of Spatial–Temporal Graph Transformer Networks for urban congestion prediction using multimodal transportation data
- 31 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 268
Mixture of Spatial–Temporal Graph Transformer Networks for urban congestion prediction using multimodal transportation data
- 24 October 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 198
Forecaster as a simulator: Simulating multi-directional pedestrian flow with knowledge-guided Graph Neural Networks
- 24 October 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 198
Forecaster as a simulator: Simulating multi-directional pedestrian flow with knowledge-guided Graph Neural Networks
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3872-3876
ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation
Significant work has been conducted in the domain of food computing, yet these studies typically focus on single tasks such as t2t (instruction generation from food titles and ingredients), i2t (recipe generation from food images), or t2i (food image generation from recipes). None of these approaches integrate all modalities simultaneously. To address this gap, we introduce a novel food computing foundation model that achieves true multimodality, encompassing tasks such as t2t, t2i, i2t, it2t, and t2ti. By leveraging large language models (LLMs) and pre-trained image encoder and decoder models, our model can perform a diverse array of food computing-related tasks, including food understanding, food recognition, recipe generation, and food image generation. Compared to previous models, our foundation model demonstrates a significantly broader range of capabilities and exhibits superior performance, particularly in food image generation and recipe generation tasks. We open-sourced ChefFusion at https://github.com/Peiyu-Georgia-Li/ChefFusion-Multimodal-Foundation-Model-Integrating-Recipe-and-Food-Image-Generation.git.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3872-3876
Open AccessChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation
Significant work has been conducted in the domain of food computing, yet these studies typically focus on single tasks such as t2t (instruction generation from food titles and ingredients), i2t (recipe generation from food images), or t2i (food image generation from recipes). None of these approaches integrate all modalities simultaneously. To address this gap, we introduce a novel food computing foundation model that achieves true multimodality, encompassing tasks such as t2t, t2i, i2t, it2t, and t2ti. By leveraging large language models (LLMs) and pre-trained image encoder and decoder models, our model can perform a diverse array of food computing-related tasks, including food understanding, food recognition, recipe generation, and food image generation. Compared to previous models, our foundation model demonstrates a significantly broader range of capabilities and exhibits superior performance, particularly in food image generation and recipe generation tasks. We open-sourced ChefFusion at https://github.com/Peiyu-Georgia-Li/ChefFusion-Multimodal-Foundation-Model-Integrating-Recipe-and-Food-Image-Generation.git.