{"ID":2840506,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.13190","arxiv_id":"2511.13190","title":"Video Spatial Reasoning with Object-Centric 3D Rollout","abstract":"Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning-the ability to comprehend object locations, orientations, and inter-object relationships in dynamic 3D scenes-remains a key unsolved challenge. Existing approaches primarily rely on spatially grounded supervised fine-tuning or reinforcement learning, yet we observe that such models often exhibit query-locked reasoning, focusing narrowly on objects explicitly mentioned in the prompt while ignoring critical contextual cues. To address this limitation, we propose Object-Centric 3D Rollout (OCR), a novel strategy that introduces structured perturbations to the 3D geometry of selected objects during training. By degrading object-specific visual cues and projecting the altered geometry into 2D space, OCR compels the model to reason holistically across the entire scene. We further design a rollout-based training pipeline that jointly leverages vanilla and region-noisy videos to optimize spatial reasoning trajectories. Experiments demonstrate state-of-the-art performance: our 3B-parameter model achieves 47.5% accuracy on VSI-Bench, outperforming several 7B baselines. Ablations confirm OCR's superiority over prior rollout strategies (e.g., T-GRPO, NoisyRollout).","short_abstract":"Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning-the ability to comprehend object locations, orientations, and inter-object relationships in dynamic 3D scenes-remains a key unsolved chal...","url_abs":"https://arxiv.org/abs/2511.13190","url_pdf":"https://arxiv.org/pdf/2511.13190v1","authors":"[\"Haoran Tang\",\"Meng Cao\",\"Ruyang Liu\",\"Xiaoxi Liang\",\"Linglong Li\",\"Ge Li\",\"Xiaodan Liang\"]","published":"2025-11-17T09:53:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}