Hossein Shirazi
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
Label-Free Reinforcement Learning via Cross-Model Entropy
The paper introduces Cross-Model Entropy (CME), a novel label-free reward signal that uses an independent verifier model to assess the quality of a generator's output, significantly improving LLM performance on open-ended instruction following.
Highlighted terms show continued research focus across papers