OPD-V: Optimizing Visual Reasoning via Modality Balance as Privileged Info

Aniri · hf · 2026-08-06

Visual reasoning in MLLMs often suffers from 'Modality Imbalance,' where textual information dominates and visual features are ignored. This paper introduces OPD-V, a new visual On-Policy Self-Distillation (OPSD) paradigm.

Original post →

More from Models

Models channel →