Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
• 33
AI & ML interests
Reliable and context-aware coding assistance
Recent Activity
View all activity
Papers
Mellum2 Technical Report
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Articles
kseniialysaniukÂ
authored a
paper about 1 month ago
pavlichenkoÂ
authored a
paper about 1 month ago
kseniialysaniukÂ
authored a
paper about 1 month ago
egor-bogomolovÂ
authored 3
papers 9 months ago
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Paper • 2510.23393 • Published • 21
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
Paper • 2508.21433 • Published • 9
Diff-XYZ: A Benchmark for Evaluating Diff Understanding
Paper • 2510.12487 • Published • 9
LiqsÂ
authored a
paper 9 months ago
DanCipÂ
authored a
paper 9 months ago
egor-bogomolovÂ
authored 4
papers 10 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 • 4
PIPer: On-Device Environment Setup via Online Reinforcement Learning
Paper • 2509.25455 • Published • 38
saridormiÂ
authored a
paper 10 months ago
DanCipÂ
authored a
paper 11 months ago
v3rganzÂ
authored a
paper 12 months ago
pavlichenkoÂ
authored 5
papers over 1 year 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