Yuping Lin

CS PhD student @ DSE Lab, MSU

[Yuping Lin @yuplin2333]

Super excited to share that two of our papers have been accepted to the Main Conference at #ACL2026! 🎉 Huge thanks to my amazing co-authors and collaborators.

Check out the thread below for a quick TL;DR on our work covering Mechanistic Interpretability and LLM Agents. 👇🧵

[Yuping Lin @yuplin2333]

📄 2/ How Memory Management Impacts LLM Agents

We explored how memory addition/deletion impacts long-term behavior of LLM Agents. And we offer guidance for robust memory design!

🔗 https://t.co/ABAlNlDdLo

[Yuping Lin @yuplin2333]

Super excited to share that two of our papers have been accepted to the Main Conference at #ACL2026! 🎉 Huge thanks to my amazing co-authors and collaborators.

Check out the thread below for a quick TL;DR on our work covering Mechanistic Interpretability and LLM Agents. 👇🧵

[Yuping Lin @yuplin2333]

📄 1/ Retrieval Heads are Dynamic

We demonstrate that retrieval heads in LLMs vary dynamically across timesteps. Furthermore, the model's hidden state actually encodes a predictive signal for future retrieval patterns.

🔗 https://t.co/VTvfYkzDUx

[Jie Ren @rjthuer]

Our paper for LLM watermark is accepeted by NAACL findings! We proposed a new method to strengthen the robustness of watermark agains paraphrase using the semantics. This is very meaningful factor for the practical application! Please find the paper at https://t.co/P8y3duN5Lk

[Wenzhuo Tang @WenzhuoTang]

🙋‍♂️What is the wildest dream for graph foundation models?
🎯Graph across domains → a single model → all the downstream
🙋‍♀️Can we achieve that?
✅Yes! UniAug: Cross-Domain Graph Data Scaling with Diffusion Models
📃https://t.co/ofHT6Dus4C

[Shenglai Zeng@NeurIPS-2025 @snowzeng2]

🚀 Excited to share our latest research on enhancing privacy in RAG systems! https://t.co/MSy5aj4IPE
Our paper introduces SAGE, a novel approach using synthetic data to protect sensitive information while maintaining high utility.
#AI #Privacy #MachineLearning #RAG #DataSecurity

[Yuping Lin @yuplin2333]

Code available at: https://t.co/X6qhJsSkQ2

[Yuping Lin @yuplin2333]

✨ Excited to share our new preprint "Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis"! https://t.co/Qg7cfS7Dda
🔍 We delve into why some jailbreak attacks succeed by exploring harmful and harmless prompts in the LLM's representation space.

[Yuping Lin @yuplin2333]

🤔 Understanding why some jailbreak methods succeed helps us build more resilient LLMs. This is crucial for safe AI deployment in real-world applications. #Research #AI #LLM #Jailbreak