Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Early Silicon of Raptor: The First 3D-DRAM Accelerator for Generative Inferenced-Matrix · ACM/IEEE International Symposium on Computer Architecture (ISCA)Jun 1COMET: A Framework for Modeling Compound Operation Dataflows with Explicit Collectivesd-Matrix · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)Apr 26StreamDedup : Distributed In-line Deduplication for Disaggregated Storaged-Matrix, Microsoft, NVIDIA · ACM Transactions on Reconfigurable Technology and SystemsMar 2CRoPE: Efficient Parametrization of Rotary Positional Embeddingd-Matrix · arXiv (Cornell University)Jan 6Corsair: An In-Memory Computing Chiplet Architecture for Inference-Time Compute Accelerationd-Matrix · IEEE Micro4 citationsAug 4, 2025Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMsd-Matrix · International Joint Conference on Neural Networks (IJCNN)1 citationJun 30, 2025Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programmingd-Matrix · ACM/IEEE Design Automation Conference (DAC)3 citationsJun 22, 2025MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inferenced-Matrix · neural information processing systems1 citationJan 1, 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generationd-Matrix · neural information processing systemsJan 1, 2025