arXiv (All)
open access
GraftOOD: Grafting Out-of-Distribution Exemplars into Advantage-Weighted Rectification for Video Reward Optimization
Video reward optimization can increase proxy rewards while reducing video dynamics, a mismatch we identify as \emph{motion collapse}, including under a video-level motion-quality reward. We propose \textbf{GraftOOD}, which replaces part of the online rollouts in selected prompt groups with out-of-di
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback#436429
- Dynamic Potential-Based Reward Shaping#638158
- Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation#1106000
- Understanding Helpfulness and Harmless Tension in Reward Models#1342526
- RPS: Information Elicitation with Reinforcement Prompt Selection#14045
Record · ID 1297822
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive