arxiv:2509.25455
Konstantin Grotov
konstantgr
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 21 hours ago
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N
Sampling via max@k Optimisation
authored
a paper
28 days ago
PIPer: On-Device Environment Setup via Online Reinforcement Learning
Organizations
models
4
konstantgr/mnp-model-mistralai-Mistral-7B-Instruct-v0.2
Text Generation
•
4B
•
Updated
konstantgr/mnp-model-google-gemma-2b
Text Generation
•
2B
•
Updated
•
1
konstantgr/custom-goldfish-gpt2-experiment-roneneldan-TinyStories-100-seeded_random-0.001
Text Generation
•
0.1B
•
Updated
konstantgr/custom-goldfish-gpt2-experiment-roneneldan-TinyStories-30-hash-avalanche-0.001
Text Generation
•
0.1B
•
Updated