Mixture-of-Experts (MoE) models expand language model capacity on smartphones, but expert offloading remains constrained by limited DRAM capacity and costly data movement. Sequential token routing couples expert execution to fragmented flash reads and multistage NPU preparation, leaving sparse computation stalled on we...
Mao-Liang Li, H. Zou, Tao-Hong Han et al.· 0 citations
Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed frame budgets and candidate pools, while agent-based schedulers achieve adaptivity through...
Ke Li, Jia-Yu Chen, Mao-Liang Li et al.· 0 citations
EchoCache is proposed, an energy-guided cross-modal caching framework for efficient A2V generation that leverages audio time-frequency energy as a saliency anchor to guide latent-level cache updates and further introduces a dynamic timestep-latent caching mechanism with quantized cache management for joint efficiency a...
Jiayu Chen, Xiaoyu Wu, Rongshan Gao et al.· 0 citations
This work proposes Token Radius Attention (TRA), a training-free framework that maps query entropy to an analytic token budget and converts it into a temporally decayed radius without explicit key ranking and achieves 1.05x speedup with competitive generation quality.
Jia-Yu Chen, Zhi-Kun Jiang, Mao-Liang Li 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.
