MNIST Data Set (OpenCV
dev.to·1d·
Discuss: DEV
🧠Machine Learning
Play with Generative Adversarial Networks (GANs) in the Browser
poloclub.github.io·1d·
Discuss: Hacker News
🧠Learned Codecs
See Beyond a Single View: Multi-Attribution Learning Leads to Better Conversion Rate Prediction
arxiv.org·1d
🧠Machine Learning
V-JEPA 2: Scaling V-JEPA
gonzoml.substack.com·22h·
Discuss: Substack
📊Quantization
Facts, Arguments, Theses: Building AI Knowledge Retrieval on Meaning, Not Slices
nsavage.substack.com·1h·
Discuss: Substack
📄Text Chunking
Show HN: A short story on developing a long-context World-Model with no money
francesco215.github.io·19h·
Discuss: Hacker News
🧠Learned Codecs
Deep Dive: OpenAI's GPT-OSS
dev.to·10h·
Discuss: DEV
📊Quantization
Spiral-Bench shows which AI models most strongly reinforce users' delusional thinking
the-decoder.com·3h
🧠Intelligence Compression
From Facts & Metrics to Media Machine Learning: Evolving the Data Engineering Function at Netflix
netflixtechblog.com·1d·
Discuss: Hacker News
📊Feed Optimization
Compute Where It Counts: a trainable LLM sparsity enabling 4x CPU speed
crystalai.org·2d·
Discuss: Hacker News
🌊Streaming Algorithms
Locality-aware Concept Bottleneck Model
arxiv.org·2d
⧗Information Bottleneck
Help Your Model Learn the True Signal
towardsdatascience.com·3d
🔍Vector Forensics
What Hugging Face reveals about the data economy of fine-tuning
research.portexai.com·21h·
Discuss: Hacker News
🌀Brotli Internals
Quantifying Baseball Pitch Tunneling with K-Nearest Neighbors
runningonnumbers.com·3d·
Discuss: Hacker News
🌀Differential Geometry
2025-08-19: Paper Summary: Reproducibility Study on Network Deconvolution
ws-dl.blogspot.com·3d·
Discuss: ws-dl.blogspot.com
🧠Learned Codecs
D3FNet: A Differential Attention Fusion Network for Fine-Grained Road Structure Extraction in Remote Perception Systems
arxiv.org·1d
🌀Riemannian Computing
Adversarial Attacks against Neural Ranking Models via In-Context Learning
arxiv.org·1d
📊Search Ranking
An Empirical Study on How Video-LLMs Answer Video Questions
arxiv.org·1d
⧗Information Bottleneck
Beyond Bézier
beyondbezier.ch·4h·
Discuss: Hacker News
📖Nordic Typography
Understanding Data Influence with Differential Approximation
arxiv.org·2d
🧠Machine Learning