Skip to content
View kailinjiang's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.

Block or report kailinjiang

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.

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
kailinjiang/README.md

I am a PhD student in University of Science and Technology of China (USTC), supervised by Bin Li (USTC, 李斌). Currently, I am doing my internship in Tencent Yuanbao (Tencent QingYun) and working on Agentic Search, LLM for Ranking. Previously, I held research intern positions at BIGAI.

Research Interests:

  • 🧬 Continual Learning — Enabling models to continuously acquire, update, and inject knowledge without catastrophic forgetting.
  • ⚖️ LLM for Ranking — Leveraging large language models for next-generation information retrieval and ranking.
  • 🎯 MLLM Evaluation & Benchmarking — Designing rigorous evaluation protocols to assess reasoning and reliability of foundation models.

📎 Homepages

📊 GitHub Stats

Kailin Jiang's GitHub Stats

Pinned Loading

  1. bigai-ai/ICE bigai-ai/ICE Public

    【ICLR 2025 🔥】The code for Consistent In-Context Editing, an approach for tuning language models through contextual distributions, overcoming the limitations of traditional fine-tuning methods that …

    Python 56 4

  2. MMKE-Bench-ICLR/MMKE-Bench MMKE-Bench-ICLR/MMKE-Bench Public

    【ICLR 2025 🔥】MMKE-Bench, a challenging benchmark for evaluating diverse semantic editing in real-world scenarios.

    Python 23 1

  3. MLLMKCBENCH/MLLMKC MLLMKCBENCH/MLLMKC Public

    【AAAI 2026 🔥】A benchmark that evaluates multimodel knowledge conflicts for large multimodal model

    Python 25 1

  4. EVOKE-LMM/EVOKE EVOKE-LMM/EVOKE Public

    【ICLR 2026 🔥】This work introduces MMEVOKE benchmark to reveal challenges in knowledge injection and explores potential solutions.

    Python 223

  5. KORE-LMM/KORE KORE-LMM/KORE Public

    【ICML 2026 🔥】Knowledge injection method based on knowledge-oriented controls, achieving precision adaptation and powerful retention.

    Python 203 2

  6. MINED-LMM/MINED MINED-LMM/MINED Public

    【ACL 2026 🔥】Temporal Awareness Evaluation, Comprehensive Benchmarking, and Multi-Dimensional Analysis!

    Python 177