Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence
Read the original on arXiv Computation and Language →The paper introduces PACE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by using pairwise token contrast and adaptive trajectory confidence. Pairwise token contrast evaluates each token under four teacher views—combining correct/incorrect hints with image presence or absence—to isolate image-dependent support, while adaptive trajectory confidence normalizes teacher predictions to guide credit redistribution. Experiments demonstrate that PACE outperforms existing approaches on multiple multimodal reasoning benchmarks, achieving top accuracy across three backbones and the Qwen3‑VL‑8B‑Instruct model.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.