Here is Lin Li (李琳).

I am a postdoctoral fellow in AI Chip Center for Emerging Smart Systems (ACCESS) at the Hong Kong University of Technology and Science (HKUST), advised by Prof. Kwang-Ting (Tim) Cheng. Additionally, I collaborate with Prof. Long Chen at HKUST. Prior to this, I obtained my PhD degree in Computer Science and Technology from Zhejiang University (ZJU), under the supervision of Prof. Jun Xiao.
My research interest includes Multi-modal Large Language Models and Scene Understanding.

If you are interested in any aspect of me, I am always open to discussions and collaborations. Feel free to reach out to me at - lllidy[at]ust.hk

📝 Publications

AAAI 2026

Relation-R1: Progressively cognitive chain-of-thought guided reinforcement learning for unified relation comprehension

Lin Li*, Wei Chen*, Jiahui Li, Kwang-Ting Cheng, Long Chen

Code

• The first unified relation comprehension framework that explicitly integrates cognitive chain-of-thought (CoT)-guided supervised fine-tuning and group relative policy optimization (GRPO) within a reinforcement learning paradigm.

NeurIPS 2025

Interaction-centric knowledge infusion and transfer for open-vocabulary scene graph generation

Lin Li, Chuhan Zhang, Dong Zhang, Chong Sun, Chen Li, Long Chen

Code

• An interaction-centric end-to-end OVSGG framework that shifts the paradigm from object-level representations to interaction-driven learning.

ACM MM 2025

Compositional zero-shot learning via progressive language-based observations

Lin Li, Guikun Chen, Zhen Wang, Jun Xiao, Long Chen

• Automatically allocating the observation order in the form of primitive concepts or graduated descriptions, enabling effective prediction of unseen state-object compositions.

TPAMI 2024

Nicest: Noisy label correction and training for robust scene graph generation

Lin Li, Jun Xiao, Hanrong Shi, Hanwang Zhang, Yi Yang, Wei Liu, Long Chen

Code

• An out-of-distribution scene graph generation dataset VG-OOD and a debiased Knowledge distillation strategy.

NeurIPS 2023

Zero-shot visual relation detection via composite visual cues from large language models

Lin Li, Jun Xiao, Guikun Chen, Jian Shao, Yueting Zhuang, Long Chen

Code

• The first exploration of zero-shot visual relation detection via composite description prompts.

ICCV 2023

Compositional feature augmentation for unbiased scene graph generation

Lin Li, Guikun Chen, Jun Xiao, Yi Yang, Chunping Wang, Long Chen

Code

• Tackling unbiased scene graph generation from the perspective of increasing the diversity of triplet features.

CVPR 2022 Oral

The devil is in the labels: Noisy label correction for robust scene graph generation

Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, Jun Xiao

Code

• Reformulating scene graph generation (SGG) as a noisy label learning problem, and pointing out that the two plausible assumptions are not applicable for SGG.

(†: Corresponding author, *: Equal contribution, ♢: Student first author)

• EMNLP 2025 RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution. Jiahui Li, Lin Li, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou, Cheng Yang

• AI Magazine, 2025 Recent Advances in Finetuning Multimodal Large Language Models. Zhen Wang*, Lin Li*, Long Chen

• ACM MM 2025 Zero-shot compositional action recognition with neural logic constraints. Gefan Ye*, Lin Li*†, Kexin Li*, Jun Xiao, Long Chen

• CVPR 2025 Highlight Comm: A coherent interleaved image-text dataset for multimodal understanding and generation. Wei Chen*, Lin Li*, Yongqi Yang*, Bin Wen, Fan Yang, Tingting Gao, Yu Wu, Long Chen

• PR 2025 Knowledge integration for grounded situation recognition. Jiaming Lei, Sijing Wu, Lin Li†, Lei Chen, Jun Xiao, Yi Yang, Long Chen

• ACM MM 2024 Seeing beyond classes: Zero-shot grounded situation recognition via language explainer. Jiaming Lei, Lin Li†, Chunping Wang, Jun Xiao, Long Chen

• IJCV 2024 From easy to hard: Learning curricular shape-aware features for robust panoptic scene graph generation. Hanrong Shi*, Lin Li*†, Jun Xiao, Yueting Zhuang, Long Chen.

• TCSVT 2023 Label semantic knowledge distillation for unbiased scene graph generation. Lin Li, Jun Xiao, Hanrong Shi, Wenxiao Wang, Jian Shao, An-An Liu, Yi Yang, Long Chen.

• ICME 2023 Oral Addressing predicate overlap in scene graph generation with semantic granularity controller. Guikun Chen*, Lin Li*, Yawei Luo, Jun Xiao

• ESWA 2023 Question-guided feature pyramid network for medical visual question answering. Yonglin Yu, Haifeng Li, Hanrong Shi, Lin Li†

• ACM MM 2021 Oral Instance-wise or class-wise? a tale of neighbor shapley for concept-based explanation. Jiahui Li, Kun Kuang, Lin Li, Long Chen, Songyang Zhang, Jian Shao, Jun Xiao

• TMM 2020 Explore video clip order with self-supervised and curriculum learning for video applications.
  Jun Xiao, Lin Li♢, Dejing Xu, Chengjiang Long, Jian Shao, Shifeng Zhang, Shiliang Pu, Yueting Zhuang

🎖 Honors and Awards

• 2025 ACM HZ Chapter Doctoral Dissertation Award.
• 2025 2nd Place in the Data Curation for Vision Language Reasoning (DCVLR) Challenge. NeurIPS 2025.
• 2023.10 Academic Star Training Program for Doctoral Students in Zhejiang University.
• 2022.09 Transfar Group Scholarship at Zhejiang University.
• 2021.09 National Scholarship.
• 2019 1st Place in the ImageCLEF Visual Question Answering (VQA) Challenge 2019.
• 2017.09 National Scholarship.