Yejin Yoon

Ph.D Candidate at Hanyang University.

Paper of the Day

Weekly paper notes and takeaways. Informal notes written quickly based on what I was exploring at the time of writing. Some personal notes may assume context from ongoing research projects.

language-modeling rag dialogue-system reasoning self-improvement reinforcement-learning memory prompting benchmark agent long-context evaluation
+ more
icl petl optimization interpretability function-calling domain-adaptation alignment-learning representation-learning peft odqa llm-as-a-judge knowledge-conflicts hallucination factuality ensemble code transformers safety multi-modality multi-linguality industry multi-agent long-horizon knowledge-editing dpo ai-detection activation weight-merging sae rl prompt-compression planning personalization lrm attention adaptor unlearning translate time-sensitive test-time-scaling tableqa synthetic-data sft self-learning scaling-laws projector preference ppo post-training persona pbrl multi-turn moe mllm mid mia lvlm knowledge-graph hypernetwork hci gan fusion dst diffusion decoding data-selection classification
2026 9 posts 2025 52 posts 2024 93 posts 2023 16 posts
View posts list →