preference optimization
A post-training method that adjusts model behavior using comparisons or self-generated preferences to improve alignment.
- Papers
- 6
- Released code
- 0
- First seen
- June 2026
- Latest
- Sept 2026
5 papers in the last two months, against 1 in the two before.
The papers
Most central to this idea first, not most recent.
- Industrycs.CL
Post-training choices reshape refusal circuits but leave safety trade-offs
Macquarie University · Sept 2026
- Chinese Techcs.CV
Video-grounded prompt planning improves long-form text-to-video generation quality
Nanjing University, Wan Team, Alibaba Group · Sept 2026
- Top Universitycs.AI
Physiological grounding makes clinical language-model recommendations safer in controlled tests
University of Kurdistan Hewlêr, Nanyang Technological University · Aug 2026
- Top Universitycs.AI
Temperature-controlled preference updates reduce manifold drift in flow models
Zhejiang University, Kuaishou Technology · Aug 2026
- Big Techcs.AI
Self-supervised method improves agent harnesses using past trajectories
City University of Hong Kong, Microsoft Research Asia · June 2026
- Top Universitycs.LG
A framework predicts RL post-training outcomes without running reinforcement learning
MIT CSAIL · Sept 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.