AlekseyKorshuk/rewriter-qwen3-8b-grpo-v11
8B • Updated • 93 • 1
Aleksey Korshuk
AlekseyKorshuk
AI & ML interests
MultiModal, LLM, ChatBots, RLHF, AI Alignment
Recent Activity
upvoted a paper about 2 months ago
Evaluation of a Robust Control System in Real-World Cable-Driven Parallel Robots authored a paper about 2 months ago
Evaluation of a Robust Control System in Real-World Cable-Driven Parallel Robots authored a paper 3 months ago
Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using ConcordiaOrganizations
AlekseyKorshuk/rewriter-qwen3-8b-grpo-v4
8B • Updated • 3
AlekseyKorshuk/rewriter-qwen3-8b-grpo-v3
8B • Updated • 3
AlekseyKorshuk/rewriter-qwen3-8b-grpo-v2
Text Generation • 8B • Updated • 1
AlekseyKorshuk/rewriter-qwen3-8b-grpo-v1
Text Generation • 8B • Updated • 4
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-7
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-6-v3-alignment-all
Text Generation • 308k • Updated • 1
AlekseyKorshuk/mindgames-in2ai-submission
Text Generation • 8B • Updated • 17 • 1
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-6-v3-alignment-400
Text Generation • 308k • Updated • 7
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-6-v3-alignment
Text Generation • 308k • Updated • 2
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-6-v3
8B • Updated • 1
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-5-v3
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-4-v3-step-220
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-4-v3-step-200
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-4-v3
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-3-v3
8B • Updated • 4
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-3-v3-step-80
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-3-v3-step-70
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-2-v3
8B • Updated • 2
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-1-v3-step-60
8B • Updated • 1
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-1-v3
8B • Updated • 1
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-1-v2
8B • Updated
AlekseyKorshuk/Qwen3-8B-envrl-rloo-stage-1
8B • Updated
AlekseyKorshuk/Qwen3-4B-Thinking-2507-envrl-rloo-stage-1-medium-codenames-v5
Updated
AlekseyKorshuk/MogFace
Updated
AlekseyKorshuk/talknet-asd
Updated
AlekseyKorshuk/yolov11-face
Updated
AlekseyKorshuk/twscrape-prepared-regression-qwen-3b-full-1epochs
Text Classification • 0.1B • Updated • 2
AlekseyKorshuk/twscrape-prepared-regression-e5-base-4k-3epochs
Text Classification • 0.1B • Updated • 2
AlekseyKorshuk/twscrape-prepared-regression-NeoBERT-3epochs
Text Classification • 0.2B • Updated • 2