Papers
arxiv:2604.24893

Interactive Episodic Memory with User Feedback

Published on Apr 27
Authors:
,
,

Abstract

Episodic memory with natural language queries is enhanced through a feedback-based interactive approach that improves accuracy and real-world applicability.

In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., "Where did I place the mug?") that requires searching a long egocentric video, captured from the user's perspective, to find the moment that answers it. However, queries can be ambiguous or incomplete, leading to incorrect responses. Current methods ignore this key aspect and address EM-NLQ in a one-shot setup, limiting their applicability in real-world scenarios. In this work, we address this gap and introduce the Episodic Memory with Questions and Feedback task (EM-QnF). Here, the user can provide feedback on the model's initial prediction or add more information (e.g., "Before this. I'm looking for the big blue mug not the white one"), helping the model refine its predictions interactively. To this end, we collect datasets for feedback-based interaction and propose a lightweight training scheme that avoids expensive sequential optimization. We also introduce a plug-and-play Feedback ALignment Module (FALM) that enables existing EM-NLQ models to incorporate user feedback effectively. Our approach significantly improves over the state of the art on three challenging benchmarks and is better than or competitive with commercial large vision-language models while remaining efficient. Evaluation with human-generated feedback shows that it generalizes well to real-world scenarios.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.24893
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2604.24893 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.24893 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.