What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study
Avyay Sadhu, Patrick Cooper
原文摘要
Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make the recipe directly applicable to causal-temporal video question answering. We present a controlled study of what RLVR actually teaches video-language models about temporal structure. We fine-tune four open models with group relative policy optimization (GRPO) under three data recipes using annotated synthetic questions, self-supervised real-video pretext tasks, and a one-to-one mixture, plus a targeted real-video augmentation arm. We evaluate the model-recipe grid on 105 CLEVRER questions with one correct option and on two real-video transfer sets. The 8B ordered gain is 4.8 points (95% video-bootstrap CI [-5.6, 15.1]), while blind accuracy increases 10.5 points ([0.9, 20.6]). The 4B model gains an accuracy advantage for ordered over shuffled frames. On the real-video sets, the 8B synthetic-only checkpoint loses 26.7 and 25.2 points, with smaller regressions under mixed and augmented recipes. In a separate scene-disjoint, single-gold Qwen3-VL-8B experiment, supervised fine-tuning (SFT) and GRPO each complete 1,200 updates at three fixed seeds. GRPO minus SFT is -3.89 points in ordered accuracy (nominal 97.5% video-bootstrap CI [-7.36, -0.45]) and -2.78 points in ordered-minus-shuffled accuracy ([-6.60, 0.87]). Transfer differences are sensitive to parseability. Intervals quantify test-video uncertainty conditional on the fitted runs. The results show why benchmark accuracy, transfer, and presented-order sensitivity need to be evaluated separately.
cs.CV