paper / markchen90 / May 13 / failedDynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
paper / markchen90 / May 13 / failedDeepStack: Scalable and Accurate Design Space Exploration for Distributed 3D-Stacked AI Accelerators
paper / markchen90 / May 13 / failedAlgorithm and Hardware Co-Design for Efficient Complex-Valued Uncertainty Estimation