🧠 Learned Indexing

ML-assisted Data Structures, Neural B-trees, Database Optimization, Adaptive Structures

A brief introduction to MCP server performance optimization
catchmetrics.io·1d·
Discuss: Hacker News
👁️Observatory Systems
Undertrained Tokens in DeepSeek R1
tokencontributions.substack.com·2d·
Discuss: Substack
✅Format Verification
ChatGPT wants to replace Google but I’m not convinced it’s a competition
techradar.com·7h
🔃Feed Algorithms
How Code Feedback MCP Enhances AI-Generated Code Quality
blog.niradler.com·1d
⚡Proof Automation
Inside the vLLM Inference Server: From Prompt to Response
thenewstack.io·2d
💻Local LLMs
Open-Set Graph Anomaly Detection via Normal Structure Regularisation
arxiv.org·6d
🧠Machine Learning
🧠 Solving LeetCode Until I Become Top 1% — Day `30`
dev.to·4d·
Discuss: DEV
📐Error Bounds
Aligning Spoken Dialogue Models from User Interactions
arxiv.org·2d
🎙️Whisper
An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasets
arxiv.org·5d
📊Count-Min Sketch
Timed Prediction Problem for Sandpile Models
arxiv.org·2d
🔲Cellular Automata
The Illusion of Thinking
dev.to·2d·
Discuss: DEV
🔲Cellular Automata
Dual-Hierarchy Labelling: Scaling Up Distance Queries on Dynamic Road Networks
arxiv.org·5d
📏Range Queries
A Multi-Pass Large Language Model Framework for Precise and Efficient Radiology Report Error Detection
arxiv.org·3d
✅Format Verification
Just launched a free 9-chapter course on Agentic AI Systems
dev.to·2d·
Discuss: DEV
⚔️Lean Tactics
Edge Association Strategies for Synthetic Data Empowered Hierarchical Federated Learning with Non-IID Data
arxiv.org·5d
🧠Machine Learning
Gradient Descent on Token Input Embeddings: A ModernBERT experiment
dev.to·6d·
Discuss: DEV
📊Learned Metrics
Developing AI-Powered Applications with LLMs on Google Cloud
dev.to·2d·
Discuss: DEV
🎙️Whisper
Online high-precision prediction method for injection molding product weight by integrating time series/non-time series mixed features and feature attention mec...
arxiv.org·4d
🧠Machine Learning
Choice of Scoring Rules for Indirect Elicitation of Properties with Parametric Assumptions
arxiv.org·5d
👑Coq Tactics
Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
arxiv.org·3d
💻Local LLMs