firstbacksecondback
36 Results
|
Workshop
|
Sat 7:42 |
[Paper-Oral 3] Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data Yu Yang · Aaditya Singh · Mostafa Elhoushi · Anas Mahmoud · Kushal Tirumala · Fabian Gloeckle · Baptiste Roziere · Carole-Jean Wu · Ari Morcos · Newsha Ardalani |
|
|
Workshop
|
Sat 12:30 |
Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference |
|
|
Poster
|
Tue 8:45 |
Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy Dongmin Park · Seola Choi · Doyoung Kim · Hwanjun Song · Jae-Gil Lee |
|
|
Poster
|
Wed 15:00 |
ZipLM: Inference-Aware Structured Pruning of Language Models Eldar Kurtić · Elias Frantar · Dan Alistarh · Dan Alistarh |
|
|
Poster
|
Tue 8:45 |
CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models Denis Kuznedelev · Eldar Kurtić · Elias Frantar · Dan Alistarh · Dan Alistarh |
|
|
Poster
|
Wed 8:45 |
Don’t just prune by magnitude! Your mask topology is a secret weapon Duc Hoang · Souvik Kundu · Shiwei Liu · Shiwei Liu · Zhangyang "Atlas" Wang |
|
|
Poster
|
Tue 8:45 |
Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training Aleksandra Nowak · Bram Grooten · Decebal Constantin Mocanu · Jacek Tabor |
|
|
Poster
|
Thu 15:00 |
Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics Gaetano Romano · Idris A. Eckley · Paul Fearnhead · Guillem Rigaill |
|
|
Poster
|
Wed 15:00 |
Towards Higher Ranks via Adversarial Weight Pruning Yuchuan Tian · Hanting Chen · Tianyu Guo · Chao Xu · Yunhe Wang |
|
|
Poster
|
Tue 15:15 |
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning Yihua Zhang · Yimeng Zhang · Aochuan Chen · jinghan jia · Jiancheng Liu · Gaowen Liu · Mingyi Hong · Shiyu Chang · Sijia Liu |
|
|
Poster
|
Thu 15:00 |
Data Pruning via Moving-one-Sample-out Haoru Tan · Sitong Wu · Fei Du · Yukang Chen · Zhibin Wang · Fan Wang · Xiaojuan Qi |
|
|
Poster
|
Tue 15:15 |
You Only Condense Once: Two Rules for Pruning Condensed Datasets Yang He · Lingao Xiao · Joey Tianyi Zhou |