{"ID":2862152,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01009","arxiv_id":"2510.01009","title":"POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency","abstract":"Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense temporal coverage under a fixed token budget. We then train Qwen2.5-VL-7B with supervised fine-tuning (SFT) on rationale+answer targets, and optionally apply Direct Preference Optimization (DPO) for preference alignment. We introduce ReasonVQA as a pilot diagnostic dataset with 12 movies and 239 human-annotated QA+rationale triplets for controlled analysis of long-context multimodal reasoning under compression. On ReasonVQA, SFT improves the best pooled-only baseline from 0.212 to 0.550 F1, showing that pooled evidence plus rationale supervision provides the main performance gains in this setting. In zero-shot transfer, POVQA also reaches 64.7\\% on TVQA after SFT+DPO. These results are preliminary: ReasonVQA is small, pooling can lose fine-grained temporal order, and DPO effects are not uniformly positive across settings. Code, dataset, and additional qualitative evaluations are available at \\href{https://povqa.github.io}{https://povqa.github.io}.","short_abstract":"Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense t...","url_abs":"https://arxiv.org/abs/2510.01009","url_pdf":"https://arxiv.org/pdf/2510.01009v3","authors":"[\"Ashim Dahal\",\"Ankit Ghimire\",\"Saydul Akbar Murad\",\"Nick Rahimi\"]","published":"2025-10-01T15:15:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.MM\"]","methods":"[\"Language Model\"]","has_code":false}