Seeing the Arrow of Time in Large Multimodal Models

Zihui Xue, Mi Luo, Kristen Grauman

Keywords: arrow of time, large multimodal models, video understanding, videoQA

TL;DR: Finding that today's LMMs poorly grasp the arrow of time in video, we propose ArrowRL to enhance their temporal perception and AoTBench for rigorous evaluation.

Abstract: The Arrow of Time (AoT)—time's irreversible flow shaping physical events—is fundamental to video comprehension, yet remains a significant challenge for modern large multimodal models (LMMs). Current LMMs struggle to perceive and utilize temporal directionality in video when responding to language queries, obstructing deeper temporal understanding. We tackle this deficiency by first providing a critical analysis of existing benchmarks and models. We then introduce ArrowRL, a reinforcement learning (RL)-based training strategy with an innovative reverse reward that instills AoT awareness by encouraging divergent video interpretations between forward and reversed visual frames. For rigorous evaluation, we additionally develop AoTBench, a new multi-faceted benchmark probing temporally challenging questions. Experiments show ArrowRL greatly advances temporal perception: it not only achieves substantial improvements on our challenging AoTBench but also demonstrably boosts performance on standard video question answering (VQA) benchmarks (with peak accuracy gains reaching over 20% and 10% respectively). This validates ArrowRL's effectiveness and highlights the critical need for dedicated AoT understanding in LMMs.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 4645