Roberto L. Castro

14 papers A 2B 2Journal 9

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Adapt-S: Effective DNN Pruning via Unified Accuracy and Performance Tuning. IPDPS Roberto L. Castro, Diego Andrade, Basilio B. Fraguela
2025	J	`jnl`	Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization. CoRR Vage Egiazarian, Roberto L. Castro, Denis Kuznedelev, Andrei Panferov, Eldar Kurtic, Shubhra Pandit, Alexandre Noll Marques, Mark Kurtz, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh
2025	J	`jnl`	HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs. CoRR Saleh Ashkboos, Mahdi Nikdan, Soroush Tabesh, Roberto L. Castro, Torsten Hoefler, Dan Alistarh
2025	B	`conf`	MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models. PPoPP Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler, Dan Alistarh
2025	J	`jnl`	QuEST: Stable Training of LLMs with 1-Bit Weights and Activations. CoRR Andrei Panferov, Jiale Chen, Soroush Tabesh, Roberto L. Castro, Mahdi Nikdan, Dan Alistarh
2025	J	`jnl`	Quartet: Native FP4 Training Can Be Optimal for Large Language Models. CoRR Roberto L. Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling, Jiale Chen, Mahdi Nikdan, Saleh Ashkboos, Dan Alistarh
2024	—	`—`	Development of Techniques to Optimize Automated Machine Learning Processes in High Performance Computing Systems. Roberto L. Castro
2024	J	`jnl`	MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models. CoRR Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler, Dan Alistarh
2024	J	`jnl`	STuning-DL: Model-Driven Autotuning of Sparse GPU Kernels for Deep Learning. IEEE Access Roberto L. Castro, Diego Andrade, Basilio B. Fraguela
2023	A	`conf`	VENOM: A Vectorized N: M Format for Unleashing the Power of Sparse Tensor Cores. SC Roberto L. Castro, Andrei Ivanov, Diego Andrade, Tal Ben-Nun, Basilio B. Fraguela, Torsten Hoefler
2023	J	`jnl`	VENOM: A Vectorized N: M Format for Unleashing the Power of Sparse Tensor Cores. CoRR Roberto L. Castro, Andrei Ivanov, Diego Andrade, Tal Ben-Nun, Basilio B. Fraguela, Torsten Hoefler
2022	B	`conf`	Probing the Efficacy of Hardware-Aware Weight Pruning to Optimize the SpMM Routine on Ampere GPUs. PACT Roberto L. Castro, Diego Andrade, Basilio B. Fraguela
2020	J	`jnl`	A Hybrid Approach for Tracking Individual Players in Broadcast Match Videos. CoRR Roberto L. Castro, Diego Andrade, Basilio B. Fraguela
2020	J	`jnl`	Reusing Trained Layers of Convolutional Neural Networks to Shorten Hyperparameters Tuning Time. CoRR Roberto L. Castro, Diego Andrade, Basilio B. Fraguela