31 citations · 88 across the 23 of their papers we have counts for
4 papers · 1 filter
RankLane: Efficient MoE Prefill on Accelerators with Ranked Expert Capacities
Wentao Ni, Chihao Yu, Hong Cai +4
Mixture-of-experts (MoE) models expand model capacity by activating only a subset of experts for each token. On accelerators with static execution plans, expert capacities and plac…
TileWeave: Heterogeneous Tiling for Sparse Prefill on Mobile SoCs
Wentao Ni, Hong Cai, Mingu Lee +7
Smartphone applications increasingly require large language models to process long contexts, whereas high prefill latency and memory demands constrain local inference. Block-sparse…
Interactive Differentiable Simulation
Eric Heiden, David Millard, Hejia Zhang +1
Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While learning-based models of the environment dynamics have con…
Scaling simulation-to-real transfer by learning composable robot skills
Ryan Julian, Eric Heiden, Zhanpeng He +5
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simu…