Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
• 40
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
pavlichenkoÂ
published 2
models 5 days ago
pavlichenkoÂ
updated a
collection 5 days ago
ivan-bondyrevÂ
updated a
model 6 days ago
BsalimzianovÂ
updated a
model 6 days ago
THIS IS AMAZIN! THANKS!
1
#3 opened 8 days ago
by 
ssbbss
ivan-bondyrevÂ
authored a
paper 4 months ago
kseniialysaniukÂ
authored a
paper 4 months ago
petybÂ
authored a
paper 4 months ago
pavlichenkoÂ
authored a
paper 4 months ago
kseniialysaniukÂ
authored a
paper 4 months ago
Ar4lÂ
authored a
paper 4 months ago
Ar4lÂ
submitted a
paper to Daily Papers 4 months ago
Kirili4ikÂ
authored a
paper 5 months ago
jenyagÂ
authored 3
papers 12 months ago
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Paper • 2510.23393 • Published • 21
On Pretraining for Project-Level Code Completion
Paper • 2510.13697 • Published • 8
Diff-XYZ: A Benchmark for Evaluating Diff Understanding
Paper • 2510.12487 • Published • 10
pavlichenkoÂ
authored 2
papers over 1 year ago