…From Implicit Preferences to Explicit Multimodal Generative Criteria Published on May 8 Submitted by Juanxi Tian on May 12 OpenEnvision Authors: Juanxi Tian , Fengyuan Liu , , , , , Haodong Li , , Abstract Auto-Rubric as Reward…
…This rubric reward is applied only to responses with correct final answers (positive-only strategy), distinguishing the reasoning quality among correct responses and preventing reward hacking . Experiments on three reasoning LLMs (4B…
…By cascading these adaptive efficiency metrics with a strict correctness gate, our approach effectively avoids the brevity bias associated with absolute penalties and mitigates reward hacking. Extensive experiments on long-horizon benchmarks…
…i'd love to see an ablation on gating strength across data scales to confirm it's the main driver rather than a stability hack. the arXivLens breakdown helped me parse the…
Papers arxiv:2606.06286 LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs Published on Jun 4 Submitted by Gianluca Barmina on Jun…
…overall, trb seems like a principled bridge rather than a hack, and i can see it being handy for other on-policy setups where teacher signals are noisy early on. Get this…
…View arXiv page View PDF Project page GitHub 180 Add to collection Community Introduce on-policy distillation to flow matching models. This is an automated message from the Librarian Bot . I found…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.