arxiv:2504.08120
Daniil Larionov
Rexhaif
AI & ML interests
Active Learning, NLP, DL, Distributed Systems, Russian Language
Recent Activity
upvoted a paper 1 day ago
On-Policy Self-Distillation without Any Supervision liked a Space about 2 months ago
AlexWortega/same-data-different-losses updated a model 3 months ago
Rexhaif/anon-14B-SFT-ReasoningOrganizations
models 36
Rexhaif/anon-14B-SFT-Reasoning
15B • Updated • 4
Rexhaif/anon-8B-SFT-Reasoning
8B • Updated • 4
Rexhaif/anon-4B-SFT-Reasoning
4B • Updated • 5
Rexhaif/anon-0.6B-SFT-Reasoning
0.6B • Updated • 9
Rexhaif/anon-4b-rl-thinking
4B • Updated • 9 • 1
Rexhaif/anon-0.6B-RL-Thinking
0.6B • Updated • 11
Rexhaif/anon-8B-RL-Thinking
8B • Updated • 11
Rexhaif/anon-14B-RL-Thinking
15B • Updated • 8
Rexhaif/Qwen3-14B-Tulu-SFT-Dolci-Reasoning-100k
15B • Updated • 7
Rexhaif/Qwen3-8B-Tulu-SFT-Dolci-Reasoning-100k
8B • Updated • 7
datasets 26
Rexhaif/anon-reasoning-gpt-oss-120b
Viewer • Updated • 500k • 72
Rexhaif/anon-reasoning-gpt5.4
Viewer • Updated • 279k • 37 • 3
Rexhaif/anon-reasoning-seed
Viewer • Updated • 83.1k • 18
Rexhaif/anon-dataset-2M-pairwise
Viewer • Updated • 1M • 19
Rexhaif/mlem-dataset-rl-mt-pairwise
Viewer • Updated • 1M • 11
Rexhaif/Nemotron-SG-v3-Cleaned
Preview • Updated • 64
Rexhaif/minimal-sft-mix
Viewer • Updated • 300k • 49
Rexhaif/wmt-balanced-19-24
Viewer • Updated • 591k • 18
Rexhaif/seahorse
Viewer • Updated • 486k • 22
Rexhaif/MultiWOZ-reponse-choice-classification
Updated • 29