arXiv (All)
open access
Metropolis-Hastings Dominates Importance Resampling for Policy Composition
Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive. Decoding-time policy composition allows these trade-offs to be adjusted by combining reward-specific policies at inference time. This composition t
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
- Metropolis-Hastings Dominates Importance Resampling for Policy Composition#1181654
- Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation#1062426
- Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models#1129887
- GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation#1035836
- Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards#1355803
Record · ID 1188158
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