Deep Learning

Feeds to Scour
SubscribedAll
Scoured 51 posts in 10.3 ms

Variational Proximal Policy Optimization

馃幃Reinforcement LearningContent type: Academic
arxiv.org

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

馃幃Reinforcement LearningContent type: Academic
arxiv.org

Pretraining Recurrent Networks without Recurrence

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Constrained Paraphrase Consistency for LLM Hallucination Detection

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Perturbative Contrastive Physical Learning

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Reinforcement Learning for Flow-Matching Policies with Density Transport

馃幃Reinforcement LearningContent type: Academic
arxiv.org

A prism hierarchy of learning regimes in large linear autoencoders

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Adaptive directional gradients for parameterised quantum circuits

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process

鈿欙笍Model TrainingContent type: Academic
arxiv.org

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

馃敟PyTorchContent type: Academic
arxiv.org

Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway

馃AI ResearchContent type: Academic
arxiv.org

The Spectral Dynamics and Noise Geometry of Muon

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Characterizing Learning Dynamics under Relative Reparameterization of Singular Models

鈿欙笍Model TrainingContent type: Academic
arxiv.org

DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum

鈿欙笍Model TrainingContent type: Academic
arxiv.org

nnAudio 2: Overcoming Dynamic Compilation Barriers and Transform Inconsistencies

馃敟PyTorchContent type: Academic
arxiv.org

PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Uncovering Extreme Event Mechanisms for Prediction and Control with Sensitivity-Balanced Projections

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Q-VGM: Q-Guided Value-Gradient Matching for Flow-Matching VLA Policies

馃幃Reinforcement LearningContent type: Academic
arxiv.org

Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders

鈿欙笍Model TrainingContent type: Academic
arxiv.org

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help