Mohammad Ghavamzadeh

Senior Director of Technology@QualComm·美国·OpenReview

研究方向

test-time scaling of GenAI models · diffusion models · post training of GenAI models · RLHF · bandit algorithms · online learning · reinforcement learning

发表论文（10 篇）

6.5

ICLR 2026Poster

5.5

Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences

合作者 (20)