Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Machine Learning
馃 Machine Learning
Neural Networks, Training, Models, Deep Learning
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
78
posts in
13.4
ms
Agentic RL: Token-In, Token-Out Done Right
聽
馃幃
Reinforcement Learning
qgallouedec-tito.hf.space
路
1d
1 day ago
路
Hacker News
Actions for Agentic RL: Token-In, Token-Out Done Right
Designing
Loops
That Prompt Coding Agents: The Six I Actually Run
聽
鉁嶏笍
Prompt Engineering
cameronwestland.com
路
2d
2 days ago
路
Hacker News
Actions for Designing Loops That Prompt Coding Agents: The Six I Actually Run
KJLdefeated/RL.cu: RLVR
training
for LLM in CUDA/C++
聽
馃
AI
聽
Content type:
Code
github.com
路
3d
3 days ago
路
Hacker News
Actions for KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++
Phantom transitions in language
model
fine-tuning
聽
馃挰
LLMs
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Phantom transitions in language model fine-tuning
Optimal Rates for Generalization of
Gradient
Descent
Methods with
Deep
Neural Networks
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
3d
3 days ago
Actions for Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks
Growing Pains of Starting a Secret Society
聽
馃搻
Optimization Theory
聽
Content type:
Blog
mrmarket.bearblog.dev
路
1d
1 day ago
路
Hacker News
Actions for Growing Pains of Starting a Secret Society
See, Act, Correct: three levers for working with a code agent
聽
馃幃
Reinforcement Learning
聽
Content type:
Blog
blog.owulveryck.info
路
6d
6 days ago
路
Hacker News
,
Hacker News
Actions for See, Act, Correct: three levers for working with a code agent
Reinforcement
Learning
for Flow-Matching Policies with Density Transport
聽
馃
AI
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Reinforcement Learning for Flow-Matching Policies with Density Transport
Flatland: The Adventures of
Gradient
Descent
with Large Step Sizes
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
3d
3 days ago
Actions for Flatland: The Adventures of Gradient Descent with Large Step Sizes
Variational Proximal Policy Optimization
聽
馃幃
Reinforcement Learning
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Variational Proximal Policy Optimization
Second-Order Path Kernel Interpolation Formulas in
Machine
Learning
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
3d
3 days ago
Actions for Second-Order Path Kernel Interpolation Formulas in Machine Learning
Learning
Dynamics Reveal a Hierarchy of Weight-Induced Layerwise
Gram
Metrics
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics
Predictive Coding with Bayesian Priors via Proximal
Gradients
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Predictive Coding with Bayesian Priors via Proximal Gradients
Stein Kernelized Molecular Dynamics for Active
Learning
of Interatomic Potentials
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
1w
1 week ago
Actions for Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
Understanding Quantization-Aware
Training
:
Gradients
at Quantized Weights Bias to the
Low-Loss
Basin
聽
馃搲
Loss Landscapes
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin
princezuda/-RequiemGPT-: Fully open source and open weights built and
trained
by fable five with one prompt. An experience in how
AI
actually works
聽
馃
AI
聽
Content type:
Code
github.com
路
1d
1 day ago
路
Hacker News
Actions for princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works
Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through
Deep
Learning
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
1d
1 day ago
Actions for Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning
Pseudospectral Bounds for Transient Amplification in Coupled
Gradient
Descent
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
1w
1 week ago
Actions for Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent
Hybridizing Equilibrium Propagation with Ising
Machines
for Efficient Energy-Based
Learning
聽
馃
AI
聽
Content type:
Academic
arxiv.org
路
2d
2 days ago
Actions for Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning
An Ensembled Latent Factor
Model
via Differential Evolution and
Gradient
Descent
Optimization
聽
馃搻
Optimization Theory
聽
Content type:
Academic
arxiv.org
路
1w
1 week ago
Actions for An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization
« Page 1
路
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
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
Browse
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