关注
Skanda Koppula
Skanda Koppula
Google DeepMind
在 mit.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Perceiver io: A general architecture for structured inputs & outputs
A Jaegle, S Borgeaud, JB Alayrac, C Doersch, C Ionescu, D Ding, ...
arXiv preprint arXiv:2107.14795, 2021
4112021
Efficient visual pretraining with contrastive detection
OJ Hénaff, S Koppula, JB Alayrac, A Van den Oord, O Vinyals, J Carreira
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
1382021
EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM
S Koppula, L Orosa, AG Yağlıkçı, R Azizi, T Shahroodi, K Kanellopoulos, ...
Proceedings of the 52nd Annual IEEE/ACM International Symposium on …, 2019
1172019
SMASH: Co-designing software compression and hardware-accelerated indexing for efficient sparse matrix operations
K Kanellopoulos, N Vijaykumar, C Giannoula, R Azizi, S Koppula, ...
Proceedings of the 52nd Annual IEEE/ACM International Symposium on …, 2019
902019
Object discovery and representation networks
OJ Hénaff, S Koppula, E Shelhamer, D Zoran, A Jaegle, A Zisserman, ...
European Conference on Computer Vision, 123-143, 2022
582022
Accurate, low-latency visual perception for autonomous racing: Challenges, mechanisms, and practical solutions
K Strobel, S Zhu, R Chang, S Koppula
2020 IEEE/RSJ international conference on intelligent robots and systems …, 2020
222020
HiP: Hierarchical Perceiver
J Carreira, S Koppula, D Zoran, A Recasens, C Ionescu, O Henaff, ...
arXiv preprint arXiv:2202.10890, 2022
172022
Power-based Side-Channel Attack for AES Key Extraction on the ATmega328 Microcontroller
U Banerjee, L Ho, S Koppula
Computer Systems Security, 2015
17*2015
Lossless adaptation of pretrained vision models for robotic manipulation
M Sharma, C Fantacci, Y Zhou, S Koppula, N Heess, J Scholz, Y Aytar
arXiv preprint arXiv:2304.06600, 2023
142023
Perceiver IO: a general architecture for structured inputs & outputs. arXiv 2021
A Jaegle, S Borgeaud, JB Alayrac, C Doersch, C Ionescu, D Ding, ...
URL: https://arxiv. org/abs/2107.14795, 0
11
Applying the Residue Number System to Neural Network Inference
M Abdelhamid, S Koppula
arXiv preprint arXiv:1712.04614, 2017
92017
Perception test: A diagnostic benchmark for multimodal video models
V Patraucean, L Smaira, A Gupta, A Recasens, L Markeeva, D Banarse, ...
Advances in Neural Information Processing Systems 36, 2024
82024
Learning a CNN-based End-to-end Controller for a Formula SAE Racecar
S Koppula
arXiv preprint arXiv:1708.02215, 2017
72017
Perceiver io: a general architecture for structured inputs & outputs. 2021
A Jaegle, S Borgeaud, JB Alayrac, C Doersch, C Ionescu, D Ding, ...
URL https://arxiv. org/abs/2107.14795, 0
7
Where should i spend my flops? efficiency evaluations of visual pre-training methods
S Koppula, Y Li, E Shelhamer, A Jaegle, N Parthasarathy, R Arandjelovic, ...
arXiv preprint arXiv:2209.15589, 2022
52022
Energy-efficient speaker identification with low-precision networks
S Koppula, J Glass, AP Chandrakasan
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
42018
EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators
L Orosa, S Koppula, Y Umuroglu, K Kanellopoulos, J Gomez-Luna, ...
arXiv preprint arXiv:2202.02310, 2022
32022
A Deep Learning Approach for Characterizing Major Galaxy Mergers
S Koppula, V Bapst, M Huertas-Company, S Blackwell, ...
arXiv preprint arXiv:2102.05182, 2021
32021
Understanding Recurrent Neural State using Memory Signatures
S Koppula, KC Sim, K Chin
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
32018
A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
P Papalampidi, S Koppula, S Pathak, J Chiu, J Heyward, V Patraucean, ...
arXiv preprint arXiv:2312.07395, 2023
12023
系统目前无法执行此操作,请稍后再试。
文章 1–20