rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
Manning, Stefano Ermon, and Chelsea Finn
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks.
citing papers explorer
-
Visual Preference Optimization with Rubric Rewards
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
-
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks.
- Hint Tuning: Less Data Makes Better Reasoners