Paper Notes
Search
搜索
暗色模式
亮色模式
探索
标签: multimodal-alignment
此标签下有3条笔记。
2026年5月
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
2026年5月
RewardHarness: Self-Evolving Agentic Post-Training
2026年3月
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models