Junjie (Jorji) Chen

I am currently a second-year master’s student at Anhui Polytechnic University, under the supervision of Subin Huang.

My research centers on Efficient AI, Multimodal AI, and Generative AI.

🌱 I am fully dedicated to advancing my research in these areas, working tirelessly toward my passion 🏃‍♂️.

Now, I am honored to serve as a remote research assistant for Linfeng Zhang, where I primarily contribute to projects on Efficient AI.

Collaborative opportunities are always welcome—please feel free to reach out.

Selected Previous Experiences:

I completed a remote research internship with Lichao Sun, whose guidance has been immensely helpful, and I am deeply grateful for his support.
I completed a high-definition map (HDMap) engineering internship at Megvii Research’s Transformer Group for over 900 days, where I honed my collaboration and engineering skills.
I once served as the captain of the PaddlePaddle Leading Group at Anhui Polytechnic University and was awarded the title of Gold Medal Captain by the Baidu PaddlePaddle Leading Group .

news

Mar 24, 2025	🥳 I joined TeleAI as a research intern to study two-stage text-to-video technology.
Feb 28, 2025	🥳 Our paper “DE-ESD: Dual Encoder-based Entity Synonym Discovery using Pre-trained Contextual Embeddings” has been accepted for publication in Expert Systems With Applications!
Apr 17, 2024	🌱 I have fully committed myself to academic research and have resigned from my internship at Megvii, which I started in my sophomore year.
Nov 21, 2023	🥳 I led the team `ahpu_new_peasants` to win the second prize in the OpenDigger Open Source Software Ecosystem Data Analysis Mining Platform Challenge. News link

selected publications

DE-ESD

DE-ESD: Dual encoder-based entity synonym discovery using pre-trained contextual embeddings

Subin Huang, Junjie Chen, Chengzhen Yu, Daoyu Li, Qing Zhou, and Sanmin Liu

Expert Systems with Applications, 2025

Bib PDF Code

@article{chen2025deesd,
  title = {DE-ESD: Dual encoder-based entity synonym discovery using pre-trained contextual embeddings},
  journal = {Expert Systems with Applications},
  volume = {276},
  pages = {127102},
  year = {2025},
  issn = {0957-4174},
  doi = {https://doi.org/10.1016/j.eswa.2025.127102},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417425007249},
  author = {Huang, Subin and Chen, Junjie and Yu, Chengzhen and Li, Daoyu and Zhou, Qing and Liu, Sanmin},
  keywords = {Entity synonym set, Entity synonym discovery, Dual encoder, Pre-trained language model, Contextual embedding},
}

InterCLIP-MEP

InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection

Junjie Chen, Hang Yu, Subin Huang, Sanmin Liu, and Linfeng Zhang

arXiv preprint arXiv:2406.16464, 2024

arXiv Bib PDF Code

@article{chen2024interclipmep,
  title = {InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection},
  author = {Chen, Junjie and Yu, Hang and Huang, Subin and Liu, Sanmin and Zhang, Linfeng},
  year = {2024},
  journal = {arXiv preprint arXiv:2406.16464},
  url = {https://arxiv.org/abs/2406.16464},
}

TaylorSeer

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Jiacheng Liu, Chang Zou, Yuanhuiyi Lyu, Junjie Chen, and Linfeng Zhang

arXiv preprint arXiv:2503.06923, 2025

arXiv Bib PDF Code

@article{TaylorSeer2025,
  title = {From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers},
  author = {Liu, Jiacheng and Zou, Chang and Lyu, Yuanhuiyi and Chen, Junjie and Zhang, Linfeng},
  journal = {arXiv preprint arXiv:2503.06923},
  year = {2025},
  url = {https://arxiv.org/abs/2503.06923},
}

SarcasmAnalysis

Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models

Junjie Chen, Xuyang Liu, Subin Huang, Linfeng Zhang, and Hang Yu

arXiv preprint arXiv:2503.12149, 2025

arXiv Bib PDF Code

@article{chen2025seeingsarcasmdifferenteyes,
  title = {Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models},
  author = {Chen, Junjie and Liu, Xuyang and Huang, Subin and Zhang, Linfeng and Yu, Hang},
  year = {2025},
  journal = {arXiv preprint arXiv:2503.12149},
  url = {https://arxiv.org/abs/2503.12149},
}