Showing 2026Show all
2 papers · 1 filter
cs.LG2026
PHASE: Multi-Regime Modeling of Incompressible Magnetohydrodynamics
Radhika Achikanath Chirakkara, Rajdeep Haldar, Zezheng Song +1
Magnetohydrodynamics (MHD) is central to plasma modeling in astrophysics, space science, fusion, and engineering, but resolving multiscale MHD dynamics is computationally expensive…
cs.LG2026
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
Rajdeep Haldar, Lantao Mei, Guang Lin +2
Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding…