Seonil Son
3 papers · Latest:
Robotics
RLDX-1 Technical Report
RLDX-1 is a new robotic policy using a Multi-Stream Action Transformer to achieve superior dexterous manipulation in complex real-world tasks.
2605.03269
Natural Language ProcessingCorrect Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
CRAFT mitigates LLM reasoning flaws by building a Reasoning Knowledge Graph from consensus traces, improving accuracy and trace quality.
2604.14121
Artificial IntelligenceHow Much LLM Does a Self-Revising Agent Actually Need?
This paper externalizes LLM agent reflection to empirically study the marginal impact of LLMs on planning and revision.
2604.07236
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.