arxiv:2603.08754
Xiao-Wen Yang
yangxw
AI & ML interests
LLM reasoning, Neuro-Symoblic Learning
Recent Activity
upvoted a paper 5 days ago
Vela: User Behavior as Supervision Sparks LLM Intelligence updated a model 20 days ago
AllSpark-Research/CompoWorldOrganizations
models 6
yangxw/Qwen3-8B-Dynamic-New
8B • Updated • 5
yangxw/Qwen3-8B-Dynamic-Syn
8B • Updated • 9
yangxw/Qwen3-8B-SRbench-Syn
8B • Updated • 8
yangxw/Qwen3-8B-Dynamic
8B • Updated • 4
yangxw/Llama-3.2-1B-countdown-backtrack
Text Generation • 1B • Updated • 35 • 1
yangxw/CARTS_vf
Text Generation • 1B • Updated • 18 • 1