Abstract: Text-to-Video generation has achieved remarkable progress with the rise of diffusion models. In this work, we introduce Cached Memory-Guided Video Generation (Corgi), aiming to generate ...
Abstract: In the context of Electroencephalography (EEG) research, how is Working Memory (WM) leveraged in Human-Computer Interaction (HCI)? To address this question, this paper explores how WM is ...
Official implementation of the paper $\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation. **Abstract**: *Current video-language models ...
A lightweight framework that gives language models (LMs) a persistent, evolving memory during inference time. Dynamic Cheatsheet (DC) endows black-box language models with the ability to store and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback