https://cognaptus.com/tags/reward-shaping/ Recent content in Reward-Shaping on Cognaptus Hugo -- 0.145.0 en-us Sun, 23 Aug 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-08-23-shape-the-signal-keep-the-objective-merlas-bet-on-reusable-rlhf-rewards/ Sun, 23 Aug 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-08-23-shape-the-signal-keep-the-objective-merlas-bet-on-reusable-rlhf-rewards/ MeRLa suggests that RLHF teams can improve post-training not only by changing reward models or optimizers, but by learning a reusable layer that makes existing rewards more informative.