Multi-domain RLVR data mixing, guided by a quadratic surrogate fitted to 11 pilot runs, improves a Qwen2-VL-2B model's out-of-distribution accuracy by about 5 points over uniform mixing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Multi-domain RLVR data mixing, guided by a quadratic surrogate fitted to 11 pilot runs, improves a Qwen2-VL-2B model's out-of-distribution accuracy by about 5 points over uniform mixing.