Skip to main content
Scour
Discover
Docs
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Model Optimization
⚖️ Model Optimization
model compression, quantization, model size
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
35
posts in
41.8
ms
🏭
Industrial Policy
arXiv
·
18h
18 hours ago
Lightweight Transformer
Models
for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment
🤖
Unmanned Systems
arXiv
·
1d
1 day ago
Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided
Knowledge
Distillation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation
📱
Edge AI Optimization
arXiv
·
1d
1 day ago
Efficient Network Inference via Hardware-Aware Architecture Search,
Model
Pruning
&
Quantization
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
📱
Edge AI Optimization
arXiv
·
1d
1 day ago
PRIDE: Privileged Information-enhanced
Distillation
for Empathetic Dialogue Generation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation
ℹ️
Information Theory
arXiv
·
5d
5 days ago
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention
Distillation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation
📱
Edge AI Optimization
arXiv
·
5d
5 days ago
LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer
Distillation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation
📱
Edge AI Optimization
arXiv
·
5d
5 days ago
HilDA: Hierarchical
Distillation
with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin
Covered by
ai-brief.liziran.com
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin
🔓
Open Source AI
arXiv
·
1d
1 day ago
SVD-Surgeon:
Optimal
Singular-Value Surgery for Large Language
Model
Compression
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression
📱
Edge AI Optimization
arXiv
·
5d
5 days ago
Wisdom of Committee: Diverse
Distillation
from Large Foundation
Models
and Domain Experts
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts
🔗
ONNX
arXiv
·
1d
1 day ago
NeoJaundice-AI: Smartphone-Based Neonatal Jaundice Detection Using Dual-Input Deep Learning and Synthetic Augmentation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for NeoJaundice-AI: Smartphone-Based Neonatal Jaundice Detection Using Dual-Input Deep Learning and Synthetic Augmentation
ℹ️
Information Theory
arXiv
·
6d
6 days ago
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
🤖
AI
arXiv
·
6d
6 days ago
Attribution-Guided and Coverage-Maximized
Pruning
for Structural MoE
Compression
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
📱
Edge AI Optimization
arXiv
·
5d
5 days ago
A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems
🚀
Startups
Tech Funding News
·
17h
17 hours ago
Two
quantum
computing researchers just raised €3.5M to fix AI’s runaway energy bill
Covers
# The Future of AI Efficiency.
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Two quantum computing researchers just raised €3.5M to fix AI’s runaway energy bill
📱
Edge AI Optimization
tech.eu
·
15h
15 hours ago
Ora Computing raises €3.5M to build the efficiency layer of the AI stack
Covers
# The Future of AI Efficiency.
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Ora Computing raises €3.5M to build the efficiency layer of the AI stack
« Page 1
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report