논문 Daily Digest 2026년 04월 03일 (3편)
Apr 3, 2026
·
1 min read
목차
| # | 분야 | 제목 |
|---|---|---|
| 1 | 💬 Dialogue Summarization | In harmony with gpt-oss |
| 2 | 💬 Dialogue Summarization | Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning |
| 3 | 🔄 Long-horizon | Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment |
💬 Dialogue Summarization
저자: Borislav Mavrin| 날짜: 2026-04-01 | 원문 | PDF
리뷰 생성 실패
2. Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
저자: Cai Zhou, Zekai Wang, Menghua Wu| 날짜: 2026-04-01 | 원문 | PDF
리뷰 생성 실패
🔄 Long-horizon
3. Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment
저자: Kai Nelson, Tobias Kreiman, Sergey Levine| 날짜: 2026-04-01 | 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. She is passionate about building human-aligned and trustworthy long-context summarization and memory systems for large language models.