Homepage
Open in app
Sign in
Get started
AI Weekly
IPPI
AI Biweekly
More
Contribute to Synced Review
Tagged in
Model Compression
SyncedReview
We produce professional, authoritative, and thought-provoking content relating to artificial intelligence, machine intelligence, emerging technologies and industrial insights.
More information
Followers
8.5K
Elsewhere
More, on Medium
Model Compression
Synced
in
SyncedReview
Aug 29
NVIDIA’s Minitron: Compressing Llama 3.1 and Mistral NeMo for Superior Performance in 4B and 8B Models
Read more…
14
Synced
in
SyncedReview
Jun 9, 2022
Microsoft’s XTC Extreme Lightweight Compression Method for Pretrained Transformers Achieves SOTA Results and 50x…
Read more…
30
Synced
in
SyncedReview
Jun 8, 2022
Gem-Miner: Finding Lottery Tickets at Initialization and Bettering All Baselines at 19x Faster Speeds
Read more…
14
Synced
in
SyncedReview
Apr 11, 2022
Maryland U & Google Introduce LilNetX: Simultaneously Optimizing DNN Size, Cost, Structured Sparsity & Accuracy
Read more…
9
Synced
in
SyncedReview
Nov 18, 2021
Intel’s Prune Once for All Compression Method Achieves SOTA Compression-to-Accuracy Results on BERT
Read more…
11
Synced
in
SyncedReview
Jul 22, 2021
Only Train Once: SOTA One-Shot DNN Training and Pruning Framework
Read more…
56
Synced
in
SyncedReview
Jun 17, 2021
Does Knowledge Distillation Really Work? NYU & Google Study Provides Insights on Student Model Fidelity
Read more…
25
Synced
in
SyncedReview
Jun 1, 2021
Georgia Tech & Microsoft Reveal ‘Super Tickets’ in Pretrained Language Models: Improving Model Compression and…
Read more…
8