Fostering Video Reasoning via Next-Event Prediction

ICLR 2026 Conference Submission7344 Authors

Keywords: Multimodal Large Language Models, Video Instruction Fine-tuning

Abstract: Next-token prediction serves as the foundational learning task that enables reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video captioning primarily promote modality alignment, while video question answering typically relies on annotations from humans or much stronger MLLMs. To address this gap, we propose next-event prediction (NEP), a learning task that harnesses future video segments as a rich, self-supervised signal to foster temporal reasoning. We segment each video into past and future frames: the MLLM takes the past frames as input and predicts events in the future, thereby encouraging the model to reason temporally in order to complete the task. To study this learning task, we curate V1-33K, a dataset comprising 33,000 automatically extracted videos spanning diverse real-world scenarios. Using the same videos, we further explore a range of video instruction-tuning tasks data to provide controlled comparisons and isolate the effect of NEP. To evaluate progress, we introduce FutureBench to assess coherence in predicting unseen future events. Experiments validate that NEP offers a scalable and effective training task for fostering temporal reasoning in MLLMs.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 7344