Why wavelets is a bad choice for image coding
codecs.multimedia.cxยท16h
๐Ÿ“ŠRate-Distortion Theory
Flag this post
Justice for Babbage
nybooks.comยท22h
๐Ÿ”ฒCellular Automata
Flag this post
Everything About Transformers
krupadave.comยท1d
๐Ÿ“Text Parsing
Flag this post
The Art and Science of Counting Pixels: The Math of Figment
fredbenenson.comยท3dยท
Discuss: Hacker News
๐Ÿ“Mathematical Art
Flag this post
Tencent/WeKnora
github.comยท8h
๐Ÿค–Archive Automation
Flag this post
<i>Nanotyrannus</i> and <i>Tyrannosaurus</i> coexisted at the close of the Cretaceous
nature.comยท14h
๐ŸฆดBinary Paleontology
Flag this post
A Minimal Route to Transformer Attention
neelsomaniblog.comยท1dยท
Discuss: Hacker News
๐ŸงฎVector Embeddings
Flag this post
**Cracking the Code of Coreference Resolution** In the real
dev.toยท9hยท
Discuss: DEV
๐ŸŒณTrie Structures
Flag this post
Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning
arxiv.orgยท2d
๐Ÿ“ŠLearned Metrics
Flag this post
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance forSelf-supervised Monocular Depth Estimation
dev.toยท1dยท
Discuss: DEV
๐Ÿ“Projective Geometry
Flag this post
Open Korean Historical Corpus: A Millennia-Scale Diachronic Collection of Public Domain Texts
arxiv.orgยท2d
๐Ÿ”คCharacter Classification
Flag this post
A Technical Deep About How To Solve AWS WAF CAPTCHA
dev.toยท1hยท
Discuss: DEV
โšกProof Automation
Flag this post
InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
dev.toยท2hยท
Discuss: DEV
๐Ÿค–Advanced OCR
Flag this post
Neural active manifolds: nonlinear dimensionality reduction for uncertainty quantification
arxiv.orgยท6h
๐ŸŒ€Riemannian Computing
Flag this post
SWAN: Self-supervised Wavelet Neural Network for Hyperspectral Image Unmixing
arxiv.orgยท3d
๐Ÿง Machine Learning
Flag this post
Cross-Platform Evaluation of Reasoning Capabilities in Foundation Models
arxiv.orgยท6h
๐Ÿ’ปProgramming languages
Flag this post
Do LLMs Signal When They're Right? Evidence from Neuron Agreement
arxiv.orgยท6h
๐Ÿ’ปLocal LLMs
Flag this post
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
arxiv.orgยท4d
๐ŸงฎVector Embeddings
Flag this post