Dongjun Kim - AI Researcher

Hi, I'm Dongjun Kim

I turn deep research insights into real-world AI systems.

I turn deep research insights into real-world AI systems. I am a master’s student at Korea University advised by Dr. Heuiseok Lim.

Evaluation Data

Collaboration with NC AI, ETRI (NC AI Consortium)

Implemented an evaluation framework (50+ benchmarks) covering reasoning, safety, and robustness with reproducible pipelines and CI triggers.
Designed a unified metric layer and Weights & Biases dashboards for time series tracking, regression checks, and cross-model slice analysis.
Conducted pre- and post-training analyses on successive checkpoints, identified failure modes, and provided recommendations used for data and recipe updates.
Introduced contamination checks (deduplication and overlap scans) and standardized runbooks to support fair, comparable evaluations across systems.

Training Data

Korea University NLP&AI Lab · KT Corporation

Co-developed an on-the-fly legal knowledge editing framework with continuous retrieval and timestamp-aware sequential updates (team of 8).
Led crawling and construction of the Korean Legislative Amendment dataset, aligning implementation periods and applying high-precision filtering.
Contributed mechanistic interpretability analyses on locality and generalization in edited knowledge.
Built expert evaluation demos and protocols for human assessment, enabling attorney review and iterative error analysis.

Training

NLP&AI Lab, Korea University

Contributed on post-training for a team of 10, including instruction tuning, training framework, and multilingual and code-switch datasets.
Curated code and math corpora, established quality gates, and ran capability evaluations for coding and math.
KULLM Reasoning: implemented reinforcement learning with custom reward functions and GRPO and applied adaptive response length.
Observed improved Korean reasoning and math accuracy versus a Qwen3 reasoning baseline while reducing unnecessary verbosity in internal evaluations.

Agents Evaluation

Auto-Generated Benchmarks From Real-Time Data

Implemented daily crawlers across multiple news categories, real-time QA generation, and automated multi-LLM evaluation on daily refreshed data.
Launched a live leaderboard with time-aware ranking and quarterly stability/volatility metrics to track consistency over time.
Maintained scheduling, monitoring, and data hygiene to support regular refreshes and clear longitudinal comparisons; operated on Hugging Face Spaces.

Hi, I'm Dongjun Kim