The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Paper • 2510.23393 • Published • 21
AI & ML interests
Reliable and context-aware coding assistance
Papers
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding
egor-bogomolovÂ
authored 3
papers 5 months ago
DanCipÂ
authored a
paper 6 months ago
egor-bogomolovÂ
authored 4
papers 6 months ago
Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code
Paper • 2412.02764 • Published
EnvBench: A Benchmark for Automated Environment Setup
Paper • 2503.14443 • Published • 1
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs
Paper • 2508.02455 • Published • 3
PIPer: On-Device Environment Setup via Online Reinforcement Learning
Paper • 2509.25455 • Published • 38
walekoÂ
authored a
paper 6 months ago
DanCipÂ
authored a
paper 8 months ago
pavlichenkoÂ
authored 6
papers 12 months ago
Toloka Visual Question Answering Benchmark
Paper • 2309.16511 • Published
CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcription
Paper • 2107.01091 • Published
Best Prompts for Text-to-Image Models and How to Find Them
Paper • 2209.11711 • Published • 3
Spherical convolutions on molecular graphs for protein model quality assessment
Paper • 2011.07980 • Published
Learning from Crowds with Crowd-Kit
Paper • 2109.08584 • Published • 1
IMDB-WIKI-SbS: An Evaluation Dataset for Crowdsourced Pairwise Comparisons
Paper • 2110.14990 • Published
walekoÂ
authored a
paper about 1 year ago
bzz2Â
authored a
paper over 1 year ago
AreydeÂ
authored a
paper over 1 year ago
galtimurÂ
authored a
paper almost 2 years ago