DA-DPO - a Artanic30 Collection

Artanic30 's Collections

DA-DPO

updated Jan 25

This is the collection for the TMLR 25 paper DA-DPO. Project Page: https://artanic30.github.io/project_pages/DA-DPO/

DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations

Paper • 2601.00623 • Published Jan 2
Artanic30/DA-DPO_llava_v1.5_7B

Reinforcement Learning • Updated Jan 25 • 2
Artanic30/DA-DPO_llava_v1.5_13B

Reinforcement Learning • Updated Jan 25