How JPEG Works: The Subtle Beauty and Art of Imperfection
techspot.comยท3d
๐Ÿ–ผ๏ธJPEG XL
ChatGPT is becoming an everything app
theverge.comยท4h
๐ŸบZIP Archaeology
ResumeCraft: A Free AI Tool
news.ycombinator.comยท9hยท
Discuss: Hacker News
โš–๏ธFeed Ranking
Cold Calculation
kae3g.codeberg.pageยท22hยท
Discuss: Hacker News
โšกIncremental Computation
Quantifying Data Contamination in Psychometric Evaluations of LLMs
arxiv.orgยท3d
๐Ÿง Intelligence Compression
Bayesian Decision Making around Experts
arxiv.orgยท2d
๐ŸงฎKolmogorov Bounds
StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance
arxiv.orgยท3d
๐Ÿง Machine Learning
How Google Translate & ChatGPT Work: The Transformer, Unboxed
dev.toยท3dยท
Discuss: DEV
๐Ÿง Learned Codecs
IKNet: Interpretable Stock Price Prediction via Keyword-Guided Integration of News and Technical Indicators
arxiv.orgยท2d
๐Ÿง Learned Indexing
Hyper-Accurate Time Series: Bridging the Prediction Gap with Glocal Learning by Arvind Sundararajan
dev.toยท4dยท
Discuss: DEV
๐Ÿ“ˆTime Series
Scalable Hyperbolic Embedding Optimization for Geometric Deep Learning on Modular Surfaces
dev.toยท6dยท
Discuss: DEV
๐ŸŒ€Hyperbolic Geometry
Seeing the Big Picture: Evaluating Multimodal LLMs' Ability to Interpret and Grade Handwritten Student Work
arxiv.orgยท4d
๐Ÿค–Advanced OCR
Comparing human and language models sentence processing difficulties on complex structures
arxiv.orgยท3d
๐Ÿ”—Parser Combinators
EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preference
arxiv.orgยท3d
๐Ÿ‘๏ธPerceptual Coding
LATTA: Langevin-Anchored Test-Time Adaptation for Enhanced Robustness and Stability
arxiv.orgยท4d
๐Ÿ“ŠQuantization
Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
arxiv.orgยท6d
๐Ÿ—‚๏ธVector Search
Toward a Holistic Evaluation of Robustness in CLIP Models
arxiv.orgยท6d
๐Ÿ“ŠRate-Distortion Theory