# RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models

arXiv: https://arxiv.org/abs/2601.03369 · HTML: https://mlsanity.com/paper/2601.03369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [STAR: A Benchmark for Situated Reasoning in Real-World Videos](https://mlsanity.com/paper/2405.09711/) (2024)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos](https://mlsanity.com/paper/2406.19392/) (2024)
- [Fostering Video Reasoning via Next-Event Prediction](https://mlsanity.com/paper/2505.22457/) (2025)
- [Global Feature Aggregation for Accident Anticipation](https://mlsanity.com/paper/2006.08942/) (2020)
- [STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving](https://mlsanity.com/paper/2506.06218/) (2025)
- [RiskBench: A Scenario-based Benchmark for Risk Identification](https://mlsanity.com/paper/2312.01659/) (2023)
- [TimeLogic: A Temporal Logic Benchmark for Video QA](https://mlsanity.com/paper/2501.07214/) (2025)
- [Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO](https://mlsanity.com/paper/2511.16669/) (2025)

## Abstract (arXiv)

With the rapid growth of video centered social media, the ability to anticipate risky events from visual data is a promising direction for ensuring public safety and preventing real world accidents. Prior work has extensively studied supervised video risk assessment across domains such as driving, protests, and natural disasters. However, many existing datasets provide models with access to the full video sequence, including the accident itself, which substantially reduces the difficulty of the task. To better reflect real world conditions, we introduce a new video understanding benchmark RiskCueBench in which videos are carefully annotated to identify a risk signal clip, defined as the earliest moment that indicates a potential safety concern. Experimental results reveal a significant gap in current systems ability to interpret evolving situations and anticipate future risky events from early visual signals, highlighting important challenges for deploying video risk prediction models in practice.