Publications
We not only work independently but also collaborate closely with individuals from academia to advance our research.
*Participant name in bold works at KRAFTON
Filter
AsyncOPD: How Stale Can On-Policy Distillation Be?
AsyncOPD: How Stale Can On-Policy Distillation Be?
Aligning Embodied Companion Agent Evaluation with User Experience
Aligning Embodied Companion Agent Evaluation with User Experience
When Agent Responses Become Interaction State: Safety in a Deployed AI Teammate
When Agent Responses Become Interaction State: Safety in a Deployed AI Teammate
ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
Looped Diffusion Language Models
Looped Diffusion Language Models
Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?
Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?
Pruning and Distilling Mixture-of-Experts into Dense Language Models
Pruning and Distilling Mixture-of-Experts into Dense Language Models
SitCom: Scaling Egocentric Multi-Party Spoken Dialogue for Situated Communication Assistance
SitCom: Scaling Egocentric Multi-Party Spoken Dialogue for Situated Communication Assistance
Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization
Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization
AMUSE: Anytime Muon with Stable Gradient Evaluation