<aside> 📌 이번 차수 계획

일시: 2025년 1~2월 매주 화요일 오후 4시 장소: 한양대학교 IT/BT관 506발표자: 김강산, 윤예진, 서동건, 이정연, 김창현, 김지수, 신영우, 서기정, 손유리, 이휘영, 김승희, 황의지 각 1회 발표 방법: 자료는 영어로 작성, 발표는 한국어/영어 자유 발표 주제: 아래 지정 논문, 김창현은 졸업논문주제 발표

</aside>

Papers to be presented

  1. Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs
  2. From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
  3. THEAGENTCOMPANY: BENCHMARKING LLM AGENTS ON CONSEQUENTIAL REAL WORLD TASKS
  4. Training Large Language Models to Reason in a Continuous Latent Space
  5. Training Language Models to Self-Correct via Reinforcement Learning
  6. Generative Agent Simulations of 1,000 People
  7. Large Concept Models: Language Modeling in a Sentence Representation Space
  8. Alignment faking in large language models
  9. LATENT ACTION PRETRAINING FROM VIDEOS
  10. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
  11. Survey of Cultural Awareness in Language Models: Text and Beyond

Schedule