works on
convergence analysis 1convex optimization 1federated learning 1heterogeneous data 1local sgd 1second-order heterogeneity 1

From the 1 of 24 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer +5

RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across…