3 papers
cs.LG2026
Reward-Gated On-Policy Distillation
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3
On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…
cs.AI2026
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts…
cs.LG2026
Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs
Vansh Bansal, Cho Cholyeon, Syamantak Kumar +2
In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on…