As AI accelerator architectures become increasingly diverse, integrating different architectures into a unified system is emerging as a new heterogeneous computing paradigm. GPUs and WSEs differ substantially in compute, memory, and communication organization, creating both architectural complementarity and additional...
Zi-Yu Hu, Zhi-Jing Ye, Jia-Min Wang et al.· 0 citations
Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations during denoising. Existing caching methods mainly exploit temporal redundancy at the feature or token level, leaving the underlying mathematical stru...
Zhen-Dong Mi, Pu Zhao, Zi-Yu Hu et al.· 0 citations
Vision language models (VLMs) incur substantial inference cost because every visual token is processed by the attention and MLP projections of every decoder layer, even when token-specific visual computation is unnecessary at many depths. We introduce Patch-to-Prune (P2P), inspired by Mechanistic Interpretability, a tr...
Rahul Chowdhury, Timothy A. Rupprecht, Xuan Shen et al.· 0 citations
Decision-Flow Sampling (DF-Sample), a training-free, data-free inference-time framework that constructs a hierarchical reasoning tree, scores terminal nodes for quality, and back-propagates utilities to inform each intermediate branching decision, indicating substantial latent reasoning potential in pretrained base mod...
Zhen-Dong Mi, Shao-Yi Huang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.