arxiv:2512.02472
Wenhao Yu
wyu1
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders upvoted a paper 2 months ago
Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM ReasoningOrganizations
models 15
wyu1/Leopard-Idefics2
8B • Updated • 2 • 4
wyu1/Leopard-LLaVA
Updated • 2 • 7
wyu1/FiD-3B-TQA
Updated • 1
wyu1/FiD-3B-NQ
Updated • 1
wyu1/FiD-3B-WebQ
Updated • 1
wyu1/GenRead-3B-TQA-MergeDPR
Updated • 2
wyu1/GenRead-3B-NQ-MergeDPR
Updated • 1
wyu1/GenRead-3B-WebQ-MergeDPR
Updated • 1
wyu1/FiD-WebQ
Updated • 1
wyu1/GenRead-3B-WebQ
Updated • 1
datasets 63
wyu1/Qwen3-4B-5-10-human-solver-v9-1000
Viewer • Updated • 7.53k • 5
wyu1/Qwen3-4B-5-10-human-solver-v8-1000
Viewer • Updated • 7.54k • 12
wyu1/Qwen3-4B-5-10-human-solver-v7-1000
Viewer • Updated • 6.88k • 9
wyu1/Qwen3-4B-5-10-human-solver-v6-1000
Viewer • Updated • 6.72k • 9
wyu1/Qwen3-4B-5-10-human-solver-v5-1000
Viewer • Updated • 6.42k • 7
wyu1/Qwen3-4B-5-10-human-solver-v4-1000
Viewer • Updated • 6.86k • 9
wyu1/Qwen3-4B-5-10-human-solver-v3-1000
Viewer • Updated • 6.78k • 8
wyu1/Qwen3-4B-5-10-human-solver-v2-1000
Viewer • Updated • 5.68k • 9
wyu1/Qwen3-4B-5-10-human-solver-v1-1000
Viewer • Updated • 6.45k • 4
wyu1/Qwen3-8B-5-10-human-solver-v10-1000
Viewer • Updated • 6.9k • 9