Mixture of Memory Embeddings (MoME), a context-aware memory mechanism that replaces each token's single memory row with a mixture of M slots and uses a learned gate over the hidden state to choose which slots to read at each position, shows more promising memory-size scaling trend at sub-billion scale and remains effic...
Mu-Chen Li, Leonid Sigal, Ren-Jie Liao· 0 citations
This work introduces ZimaBlue, a scalable framework for learning generalizable World Action Models (WAMs) from large-scale video, and adopts an asynchronous Slow-Fast dual-system architecture to make generative WAMs practical for real-time control.
Xiong-Hao Wu, Yi-Jun Yang, Shi-Long Zhou et al.· 5 citations
IDEEA (Input-Dependent stEEring via Activation cluster matching via Activation cluster matching), a training-free framework for input-dependent steering that aligns the model toward the target concept while preserving the input's original representation.
Zheng Wang, Mu-Chen Li, Ren-Jie Liao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.