arxiv:2511.20785
Sudong Wang PRO
xiao45791
AI & ML interests
None yet
Recent Activity
updated a model about 3 hours ago
xiao45791/Qwen3-VL-8B-Instruct-1M-after500steps-stage2-720steps-DAPO published a model about 4 hours ago
xiao45791/Qwen3-VL-8B-Instruct-1M-after500steps-stage2-720steps-DAPO updated a model about 4 hours ago
xiao45791/Qwen3-VL-8B-Instruct-SFT-MMR1-TechAI-Gemini-DistillOrganizations
models 8
xiao45791/Qwen3-VL-8B-Instruct-1M-after500steps-stage2-720steps-DAPO
9B • Updated
xiao45791/Qwen3-VL-8B-Instruct-SFT-MMR1-TechAI-Gemini-Distill
9B • Updated
xiao45791/Qwen3-VL-4B-Instruct-SFT-Gemini-Distill-after500steps-step2-dapo-1144steps
5B • Updated • 28
xiao45791/Qwen3-VL-4B-Instruct-SFT-Gemini-Distill-after500steps-step2-grpo-1320steps
5B • Updated • 25
xiao45791/Qwen3-VL-4B-Instruct-SFT-Gemini-Distill-after500steps-step2-grpo-1500steps
5B • Updated • 41
xiao45791/Qwen3-VL-4B-Instruct-SFT-Gemini-Distill-after500steps-step2-DAPO-720steps
5B • Updated • 44
xiao45791/Qwen3-VL-4B-Instruct-SFT-Gemini-Distill-after500steps-step2-DAPO-960steps
5B • Updated • 48
xiao45791/Qwen3-VL-4B-Instruct-SFT-MMR1-TechAI-Gemini-Distill-DAPO-30steps
5B • Updated • 64
datasets 0
None public yet