Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

arXiv:2606.09547 · cs.CV, cs.LG · Submitted 2026-06-08 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-06-08

Updated: 2026-11-11

Comments: To appear at NeurIPS 2026 (E&D) and the project page is available at https://apratimbh.github.io/livecookv2/

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos.

Terminology

Abstract

Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios. Extensive experiments show that Ego-MC-Bench is highly challenging for state-of-the-art video LLMs. We argue that a key reason is the limited availability of training data for fine-tuning models on this task. Although there exists a wide range of cooking video datasets, existing datasets lack examples of mistakes along with appropriately timed interventions. To help address this data limitation, we also introduce Ego-CoMist, a counterfactual synthetic dataset created by transforming non-interactive cooking videos into supervised training examples showing proactive interventions. We show that fine-tuning on Ego-CoMist yields performance gains especially for smaller and more efficient video LLMs that are well suited for delivering assistance on edge devices.

Sources

Related papers