Suchergebnisse - Colbert, Ian

Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization von Zhang, Shihao, Zhang, Haoyu, Colbert, Ian, Saab, Rayan

Volltext

Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach von Campa, Daniel, Saeedi, Mehdi, Colbert, Ian, Das, Srinjoy

Volltext

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos von Zhang, Haoyu, Zhang, Shihao, Colbert, Ian, Saab, Rayan

Volltext

Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola von Liu, Tian, Cann, Alex, Colbert, Ian, Saeedi, Mehdi

Volltext

A2Q+: Improving Accumulator-Aware Weight Quantization von Colbert, Ian, Pappalardo, Alessandro, Petri-Koenig, Jakoba, Umuroglu, Yaman

Volltext

Accumulator-Aware Post-Training Quantization for Large Language Models von Colbert, Ian, Franco, Giuseppe, Grob, Fabian, Zhang, Jinjie, Saab, Rayan

Volltext

Improving Quantization with Post-Training Model Expansion von Franco, Giuseppe, Monteagudo-Lago, Pablo, Colbert, Ian, Fraser, Nicholas, Blott, Michaela

Volltext

Pushing the Limits of Block Rotations in Post-Training Quantization von Sanjeet, Sai, Colbert, Ian, Monteagudo-Lago, Pablo, Franco, Giuseppe, Umuroglu, Yaman, Fraser, Nicholas J.

Volltext

Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs von Ferguson, Aidan, Gibson, Perry, D'Agata, Lara, McLeod, Parker, Yaman, Ferhat, Das, Amitabh, Colbert, Ian, Cano, José

Volltext

SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators von Umuroglu, Yaman, Berganski, Christoph, Jentzsch, Felix, Danilowicz, Michal, Kryjak, Tomasz, Bezaitis, Charalampos, Sjalander, Magnus, Colbert, Ian, Preusser, Thomas, Petri-Koenig, Jakoba, Blott, Michaela

Volltext

GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs von D'Agata, Lara, Agulló-Domingo, Carlos, Vera-López, Óscar, Shivdikar, Kaustubh, Yudha, Ardhi W. B., Yaman, Ferhat, Kaeli, David, Abellán, José L., Colbert, Ian, Cano, José

Volltext