Lune

NeurIPS2025顶会

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?

Apratim Bhattacharyya, Bicheng Xu, Sanjay Haresh, Reza Pourreza, Litian Liu, Sunny Panchal, Leonid Sigal, Roland Memisevic

2025年份
2被引次数
1顶会引用

摘要

Multi-modal Large Language Models (LLM) have advanced conversational abilities but struggle with providing live, interactive step-by-step guidance, a key capability for future AI assistants. Effective guidance requires not only delivering instructions but also detecting their successful execution, as well as identifying and alerting users to mistakes, all of which has to happen in real-time. This requires models that are not turn-based, but that can react asynchronously to a video stream, as well as video data showing users performing tasks including mistakes and their corrections. To this end, we introduce Qualcomm Interactive Cooking, a new benchmark and dataset built upon CaptainCook4D, which contains user mistakes during task execution. Our dataset and benchmark features densely annotated, timed instructions and feedback messages, specifically including mistake alerts precisely timestamped to their visual occurrence in the video. We evaluate state-ofthe-art multi-modal LLMs on the Qualcomm Interactive Cooking benchmark and introduce LIVEMAMBA, a streaming multi-modal LLM designed for interactive instructional guidance. This work provides the first dedicated benchmark and a strong baseline for developing and evaluating on live, situated coaching.

To address the challenge of live, step-by-step coaching, we introduce the Qualcomm Interactive Cooking dataset and benchmark, as currently available large-scale vision-language datasets and * Equal contribution. † Work done while employed at Qualcomm AI Research. ‡ Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc. 39th Conference on Neural Information Processing Systems (NeurIPS 2025).

1: Slice one tomato into about 1/2 inch thick slices. 2: Place the thick slices of tomatoes on a platter, ensuring they only make a single layer. 3: Season the tomato slices with salt. 4: Season the platter with 1/4 teaspoon of black pepper. 5: Sprinkle mozzarella cheese on top of the tomato throughout the platter. 6: Garnish the platter with Italian seasoning. 7: Add a drizzle of extra-virgin olive oil, about 1 tablespoon, over the entire platter.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper1

问问它们各自怎么用它

它引用的顶会 Paper29

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖