1 minute read

1 minute read

[VLM] Visual Preference Optimization with Rubric Rewards (rDPO): instance-specific rubric로 on-policy 선호쌍을 만드는 DPO 파이프라인

7 minute read

[VLM] Visual Preference Optimization with Rubric Rewards

[Agent] Why Act Without Asking?: 모호한 지시 아래 모바일 GUI 에이전트는 묻지 않고 행동한다

9 minute read

[Agent] Why Act Without Asking? Evaluating Mobile GUI Agents under Ambiguous Instructions

[LLM] RULER: Instance-aware Rubric Rewards for SVG Generation

8 minute read

[LLM] RULER: Instance-aware Rubric Rewards for SVG Generation