2 papers
cs.CL2024
LaDiMo: Layer-wise Distillation Inspired MoEfier
Sungyoon Kim, Youngjun Kim, Kihyo Moon +1
The advent of large language models has revolutionized natural language processing, but their increasing complexity has led to substantial training costs, resource demands, and env…
cs.AI2024
Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga +1
Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavi…