arxiv:2603.03790
Wang
Qinsi1
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement submitted a paper about 14 hours ago
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement updated a model 8 days ago
SpyRL/SpyRL-Qwen3-4B-SummarizationOrganizations
models 26
Qinsi1/Vision-Zero-InternVL3-14B-Clevr
15B • Updated • 5
Qinsi1/Vision-Zero-InternVL3-8B-Clevr
8B • Updated • 6
Qinsi1/Vision-Zero-Qwen-2.5-VL-7B-RealWorld
8B • Updated • 7 • 1
Qinsi1/Vision-Zero-Qwen-2.5-VL-7B-Chart
8B • Updated • 7 • 1
Qinsi1/Vision-Zero-Qwen-2.5-VL-7B-Clevr
8B • Updated • 6 • 1
Qinsi1/GAINRL-Qwen2.5-Coder-3B-Instruct
3B • Updated • 4 • 1
Qinsi1/angle_data
Updated
Qinsi1/GAINRL-LLaMA-3.2-3B-Instruct
3B • Updated • 4
Qinsi1/GAINRL-Qwen2.5-7B-Instruct
8B • Updated • 3
Qinsi1/GAINRL-Qwen2.5-Math-1.5B-Instruct
2B • Updated • 2