Skip to content
View yulinlp's full-sized avatar
9 followers · 7 following

Block or report yulinlp

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yulinlp/README.md

Yulin Hu · 胡雨林

Master's student in the Sentiment Computing (SC) group, SCIR, at Harbin Institute of Technology, advised by Prof. Yanyan Zhao and co-advised by Prof. Weixiang Zhao. Currently a research intern at Huawei Consumer Business Group (终端 BG).

I study long-term memory for multimodal agents, personalized and empathetic dialogue, and safe language models. I am interested in how agents remember users over time and decide when and how to use that memory.

Personal website · Google Scholar · Email

Selected research & open source

Project Focus Links
CUE-Mem · AAAI 2027 submission Long-term user memory from implicit cues in multimodal conversations Paper · Code · Demo
OP-Bench · EMNLP 2026 Over-personalization in memory-augmented conversational agents Paper · Code
SaRFT · ACL 2025 Safety-aware role-play fine-tuning of language models Paper · Code

Selected Projects

  • QiaoBan (巧板) — Core developer of a personalized, empathetic conversational model for children and adolescents. Official news.
  • HIT AI Counselor (工小星) — Core project lead and developer of a campus assistant combining university knowledge retrieval and empathetic dialogue. Official news.

Background

  • 2025 – Present: Master's studies in Computer Science and Technology, Harbin Institute of Technology.
  • 2021 – 2025: Bachelor’s degree in Computer Science and Technology, Harbin Institute of Technology.
  • June 2026 – Present: Research Intern, Huawei Consumer Business Group.
  • Dec. 2024 – Mar. 2025: Research Intern, Du Xiaoman Financial Technology.

For publications, research experience, and honors, see my academic homepage.

Pinned Loading

  1. SaRFT SaRFT Public

    Public code repo for ACL 2025 paper "Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs"

    Python 8

  2. circle-hit/Lens circle-hit/Lens Public

    Code for our paper titled "Lens: Rethinking Multilingual Enhancement for Large Language Models"

    Python 12

  3. OP-Bench OP-Bench Public

    Benchmarking over-personalization in memory-augmented conversational agents: irrelevance, sycophancy, and repetition.

    Python 5

  4. CUE-MEM CUE-MEM Public

    CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations

    Python 5

  5. How-LLMs-Use-Memory How-LLMs-Use-Memory Public

    How Do Language Models Use Memory? Strategy readout from model activations and adaptive memory control with Duet.

    Python 5