Feeds to Scour
SubscribedAll
Scoured 181771 posts in 12.8 ms
ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization  💻Local LLMs
arxiv.org·5d
From $200 to $30: Five Layers of LLM Cost Optimization  🔍BitFunnel
blog.dwornikowski.com·1d·Hacker News
Are LLM agents good at join order optimization?  🧠Query Planners
databricks.com·3d
Carnegie Mellon at ICLR 2026  💻Programming languages
blog.ml.cmu.edu·5d
New comment by GuB-42 in "Laws of Software Engineering"  📏Code Metrics
news.ycombinator.com·4d·Hacker News
A short-term power forecasting method for wind farm clusters considering feature enhancement and real-time optimization of dynamic graphs  🌊Spectral Clustering
sciencedirect.com·5d
The Real Bottleneck in Optimization Isn’t Computation. It’s Modeling  🎯Performance Proofs
medium.com·6d
Reveal Principles of Codon Optimization via Machine Learning  🔨Compilers
biorxiv.org·4d
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving  ⚡Z3 Optimization
arxiv.org·2d
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training  📊Quantization
arxiv.org·2d·Hacker News
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems  🧮Kolmogorov Complexity
arxiv.org·2d
HARBOR: Automated Harness Optimization  🔗Topological Sorting
arxiv.org·2d
Qubit-efficient and gate-efficient encodings of graph partitioning problems for quantum optimization  ⚛️Quantum Circuits
arxiv.org·2d
Language as a Latent Variable for Reasoning Optimization  💻Local LLMs
arxiv.org·2d
Novelty-Based Generation of Continuous Landscapes with Diverse Local Optima Networks  🔲Cellular Automata
arxiv.org·2d
Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions  🌀Riemannian Computing
arxiv.org·2d
Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization  💻Local LLMs
arxiv.org·2d
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning  ⚔️Lean Tactics
arxiv.org·2d
RECURSUM: Automated Code Generation for Recurrence Relations Exceeds Expert Optimization via LayeredCodegen  🎯Performance Proofs
arxiv.org·4d
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization  🧠Machine Learning
arxiv.org·2d

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