DPO
Topics referred to by the same term
π Rating
2 news mentions Β· π 0 likes Β· π 0 dislikes
π Topics
- Model Optimization (2)
- AI Training (1)
- Multimodal AI (1)
π·οΈ Keywords
DPO (2) Β· SFT (1) Β· small language models (1) Β· parameterization (1) Β· empirical study (1) Β· training interaction (1) Β· model alignment (1) Β· multimodal models (1) Β· understanding (1) Β· generation (1) Β· alignment (1) Β· trade-offs (1) Β· diagnostic study (1)
π Key Information
π° Related News (2)
-
πΊπΈ An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models
arXiv:2603.20100v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align lan...
-
πΊπΈ Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
arXiv:2603.17044v1 Announce Type: cross Abstract: Unified multimodal models share a language model backbone for both understanding and generating ima...
π Entity Intersection Graph
People and organizations frequently mentioned alongside DPO:
-
π
SFT Β· 1 shared articles