Surprise-gated episodic memory using V-JEPA-2 improves robot QA by ≥12% over prior memory methods and outperforms supervised baselines on event segmentation.
Simon: a simple framework for online temporal action localization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Defines OZ-TAL task and presents a training-free VLM-based method that outperforms prior approaches for online and offline zero-shot temporal action localization on THUMOS14 and ActivityNet-1.3.
OnPoint enables point-supervised online temporal action localization by distilling pseudo-segments, class-activation sequences, and anticipatory windows from an offline teacher to an online student.
citing papers explorer
-
Worth Remembering: Surprise-Gated Robot Episodic Memory
Surprise-gated episodic memory using V-JEPA-2 improves robot QA by ≥12% over prior memory methods and outperforms supervised baselines on event segmentation.