Running on CPU Upgrade Featured 2.58k The Smol Training Playbook 📚 2.58k The secrets to building world-class LLMs
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation Paper • 2510.23393 • Published Oct 27 • 20
Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues Paper • 2501.05258 • Published Jan 9
Code4MeV2: a Research-oriented Code-completion Platform Paper • 2510.03755 • Published Oct 4 • 7
SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge Paper • 2509.07968 • Published Sep 9 • 14
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs Paper • 2508.02455 • Published Aug 4 • 3
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs Paper • 2508.02455 • Published Aug 4 • 3 • 2
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs Paper • 2508.02455 • Published Aug 4 • 3