Sewon Min
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
ModSleuth reconstructs LLM dependency graphs from public artifacts
Train An Imaginative Agent
A new training framework called Agima trains an agent to imagine and reason about the consequences of its actions before executing them.
Highlighted terms show continued research focus across papers