Announcement_4
Three papers accepted at ICML 2026 
— XRPO (targeted exploration and exploitation for GRPO), DOT-MoE (differentiable optimal transport for MoEfication), and Reward Under Attack (robustness and hackability of process reward models).
Three papers accepted at ICML 2026 — XRPO (targeted exploration and exploitation for GRPO), DOT-MoE (differentiable optimal transport for MoEfication), and Reward Under Attack (robustness and hackability of process reward models).