# HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding

arXiv: https://arxiv.org/abs/2610.10156 · HTML: https://mlsanity.com/paper/2610.10156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 8 of 8)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [MIRAGE: The Illusion of Visual Understanding](https://mlsanity.com/paper/2603.21687/) (2026)
- [Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery](https://mlsanity.com/paper/2305.11692/) (2023)
- [SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence](https://mlsanity.com/paper/2506.02555/) (2025)
- [6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models](https://mlsanity.com/paper/2512.04238/) (2025)
- [Medical Imaging AI Competitions Lack Fairness](https://mlsanity.com/paper/2512.17581/) (2025)

## Abstract (arXiv)

Recent advances in Vision-Language Models (VLMs) have led to rapid progress in video understanding across a wide range of benchmark tasks. However, existing evaluations largely focus on short-term reasoning, failing to assess a critical capability: maintaining cumulative temporal consistency over extended time horizons. To close this evaluation gap, we introduce HeiCo-FOCUS, a clinically grounded dataset for evaluating long-context video understanding through the task of Foreign Object Contextual Understanding in Surgery. Built on a dataset of Heidelberg Colorectal surgeries, this task requires models to continuously track multiple objects as they are inserted, manipulated, occluded, and removed over procedures lasting up to hours. HeiCo-FOCUS comprises 30,000 visual question answering (VQA) pairs covering five core capabilities: object recognition, temporal grounding, aggregation, event and procedural understanding, and complex reasoning. The dataset was constructed through a rigorous multi-stage annotation pipeline involving large-scale crowd annotation and 39 surgical domain experts to ensure high quality and clinical relevance. To systematically probe model behavior, we introduce a multi-track evaluation framework that progressively increases temporal and contextual demands from single frames to full procedures. Experiments with ten frontier VLMs show that HeiCo-FOCUS tasks are far from solved: only around half of the models clearly outperform a text-only baseline. Across the video tracks, models perform best on event and procedural understanding (mean Accuracy: 56.5% across all models), while temporal grounding remains particularly challenging for all evaluated models (mean Accuracy: 19.7%). We therefore expect HeiCo-FOCUS to serve as a catalyst for the development of models capable of reliable, temporally consistent reasoning over hours-long videos.