Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression,
Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking, while RLHF is difficult to scale and subject to individual aesthetic differences that complicate the calibration of facial, body motion, and chromatic cues across narrative contexts. We introduce EmoReward, a new self-evolving training mechanism…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL was first seen on Hugging Face · Daily papers on Nov 5, 2026. Since then it has appeared in 18 checks on 2 different days. Its best position was #7 of 30, reached on Nov 6, 05:28 UTC. It dropped off the list after Nov 6, 17:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 6, 17:28 UTC, after 2 days of trending.
#7 on Hugging Face · Daily papers, on Nov 6, 05:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 2 days (18 checks) since.