Data Party THU
Jul 12, 2026 · Artificial Intelligence
How Counterfactual Policy Optimization Boosts Visual Fidelity in Multimodal Reasoning (ICML 2026)
The paper introduces Counterfactual Policy Optimization (CFPO), a training‑time framework that inserts causal consistency constraints into multimodal reinforcement learning, forcing vision‑language models to rely on essential visual evidence and achieving consistent accuracy gains across real‑world and math‑centric benchmarks.
ICML2026Reinforcement Learningcausal consistency
0 likes · 19 min read