Yejin Yoon

Ph.D Candidate at Hanyang University.

Log

Experiment logs, notes, and fragments.

May 20 [log-23] 실험 마무리private
May 15 [log-22] 감정응답 LaaJ — K가 Q·M 우세 (audio)
May 11 [log-21] 감정응답 LaaJ — Kanana만 인간 수준과 동급 (text)
May 11 respond + LaaJ 운영 기록 (Kanana 본 실행 + 5/01·5/11 judge 회차)private
May 01 [log-20] 감정분류 — 4모델 최종 결과
kanana-o 40 posts
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.

2026 21 posts 2025 52 posts 2024 93 posts 2023 16 posts
Misc

Uncategorized notes and references.

Apr 29 site publish state — 5 case + listing 축 정리private
Apr 29 감정 — Qwen flash redoprivate
Apr 28 Research Proposal — Modality Gapprivate
Apr 28 감정 — log-17 분리private
Apr 28 감정 — 진행 상태private
Tags

Posts grouped by topic — across logs, paper notes, and misc.

kanana language-modeling rag reasoning multimodal dialogue-system emotion benchmark self-improvement memory agent kmmlu
+ more
reinforcement-learning prompting evaluation modality-gap long-context note respond ops icl petl optimization interpretability hallucination function-calling domain-adaptation alignment-learning representation-learning peft odqa multi-modality llm-as-a-judge knowledge-conflicts factuality ensemble code transformers safety multi-linguality multi-agent industry classify rl personalization minicpm long-horizon laaj knowledge-editing infra hcx exp_d dpo design ai-detection activation KoED weight-merging test-time-scaling setup sae qwen prompt-compression post-training planning multi-turn lrm knowledge empathy attention adaptor MMLU LaaJ workflow user-simulation user-preference unlearning tts translate transfer-learning tool-calling tmux time-series time-sensitive telegram talk tableqa synthetic-data status slides site sft self-reinforcing-error self-learning self-consistency scaling-laws research remode redesign publish-state prosody projector proj-memory proj-dialogue probing preference ppo pomdp plan persona pbrl partial-observability partial paper omni-modal omni observer multi-party multi-modal moe modality-preference mllm mid mia lvlm llm literature-review listing korean-bias korean knowledge-graph incident implicit-conflict hypernetwork human-reference hci gpu git gan fusion fullset exp_c embedding dst distributional-analysis distillation disagreement diffusion decoding debug debate data-selection contrastive-learning confidence-estimation comparison cognitive-science coding clip claude-code classification chatbot belief-state batch baseline audio analysis agent-memory activation-steering Qwen MiniCPM HCX
View posts list →