Cite
Notes
Only stored in your browser.
Attribution
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
arXiv 2026
Robust Multi-Objective Controlled Decoding of Large Language Models
arXiv 2025
This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
from 3 papers
Ilija Bogunovic
Shyam Sundhar Ramesh
Aurelien Lucchi
Haitham Bou-Ammar
Lorenz Wolf
Matthieu Zimmer
Seongho Son
William Bankes
Xiaohang Tang
Xiaotong Ji