논문 Daily Digest 2026년 03월 31일 (3편)
Mar 31, 2026
·
1 min read
목차
| # | 분야 | 제목 |
|---|---|---|
| 1 | 💬 Dialogue Summarization | Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks? |
| 2 | 🔄 Long-horizon | FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants |
| 3 | 🧠 Lifelong & Long-range Memory | Analysing Calls to Order in German Parliamentary Debates |
💬 Dialogue Summarization
1. Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
저자: Yuhang Ma, Jie Wang, Zheng Yan| 날짜: 2026-03-27 | 원문 | PDF
리뷰 생성 실패
🔄 Long-horizon
2. FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
저자: Mahesh Bhosale, Abdul Wasi, Shantam Srivastava| 날짜: 2026-03-27 | 원문 | PDF
리뷰 생성 실패
🧠 Lifelong & Long-range Memory
3. Analysing Calls to Order in German Parliamentary Debates
저자: Nina Smirnova, Daniel Dan, Philipp Mayr| 날짜: 2026-03-27 | 원문 | PDF
리뷰 생성 실패
본 리포트의 논문 리뷰는 Anthropic의 Haiku 모델을 사용하여 자동 생성되었습니다.
Authors
Hyangsuk Min
(she/her)
PhD Student
Hyangsuk Min is a PhD student at KAIST, advised by Prof. Hwanjun Song. Her research asks how AI agents stay trustworthy when the information they receive is incomplete, noisy, evolving, or spread across contexts — through data-centric evaluations of how models perceive, structure, remember, and use information, and through memory-enabled agents that reuse past interactions without losing faithfulness. She also studies AI co-scientist systems, testing whether LLMs show researcher-level understanding when reading, comparing, and synthesizing scientific literature.