29 citations · 38 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Fast and Effective On-policy Distillation from Reasoning Prefixes
Dongxu Zhang, Zhichao Yang, Sepehr Janghorbani +6
On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal…
cs.LG2019★ 29 cited
SCALOR: Generative World Models with Scalable Object Representations
Jindong Jiang, Sepehr Janghorbani, Gerard de Melo +1
Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been s…