TSR Desk · science · 10 November 2026, 01:00 UTC
V-STORM: A Structure-Aware Grounded Chain of Thought Dataset for Faithful and Fine-Grained
- What
- V-STORM: A Structure-Aware Grounded Chain of Thought Dataset for Faithful and Fine-Grained Spatio-Temporal Video Reasoning
- Who
- arxiv.org
- When
- 9 November 2026, 05:00 UTC
- Category
- Science
- Primary source
- https://arxiv.org/abs/2611.09511
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
Moreover, fine-tuning with V-STORM substantially improves both answer accuracy and grounding faithfulness, validating its effectiveness as supervision for faithful and evidence-grounded video reasoning. It comes from a paper posted to arXiv on 9 November 2026. While MLLMs can often identify what happens in a video, they still struggle with fine-grained spatio-temporal reasoning, which requires precise grounding when and where the supporting evidence appears and composing such evidence into a coherent reasoning chain. This challenge is exacerbated by the lack of scalable data construction and evaluation pipelines that provide granular, verifiable supervision linking reasoning steps to explicit spatio-temporal evidence.To address this gap, we present V-STORM, a structure-aware framework that transforms videos into Spatio-Temporal Scene Graphs (STSGs) and derives Grounded Chain of Thought (GCoT) from validated evidence paths, making each reasoning step traceable to structured and verifiable spatio-temporal evidence.Under this framework, we construct a 260K-sample training set and a 3K-sample human-verified benchmark, both featuring GCoT annotations that link reasoning to explicit spatio-temporal evidence.Experiments reveal a clear separation between evidence localization and evidence composition: current MLLMs can often identify relevant spatio-temporal cues, yet still fail to integrate them into correct multi-step reasoning, exposing a bottleneck that answer-only evaluation largely obscures. Our dataset, benchmark, and source code will be publicly released.
Why it counts
Moreover, fine-tuning with V-STORM substantially improves both answer accuracy and grounding faithfulness, validating its effectiveness as supervision for faithful and evidence-grounded video reasoning.
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.