Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Paper
•
2503.18929
•
Published
•
3
•
3
Johan Samir Obando Ceron
johanobandoc
AI & ML interests
Reinforcement Learning, Deep Learning, LLMs/LVMs.
Recent Activity
commented on
a paper
13 days ago
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning
for Fast, Scalable LLM Post-Training
authored
a paper
26 days ago
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning
for Fast, Scalable LLM Post-Training
Organizations
johanobandoc's activity
commented
a
paper
13 days ago