X1AOX1A/WorldModel-Textworld-Qwen2.5-7B
Text Generation • 8B • Updated • 165
Yixia Li
X1AOX1A
AI & ML interests
None yet
Recent Activity
authored a paper 6 days ago
Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification upvoted a paper 10 days ago
ClawGym: A Scalable Framework for Building Effective Claw AgentsOrganizations
X1AOX1A/WorldModel-Alfworld-Qwen2.5-7B
Text Generation • 8B • Updated • 26
X1AOX1A/WorldModel-Sciworld-Qwen2.5-7B
Text Generation • 8B • Updated • 133
X1AOX1A/WorldModel-Webshop-Qwen2.5-7B
Text Generation • 8B • Updated • 387 •
X1AOX1A/WorldModel-Alfworld-Llama3.1-8B
Text Generation • 8B • Updated • 2
X1AOX1A/WorldModel-Sciworld-Llama3.1-8B
Text Generation • 8B • Updated • 25
X1AOX1A/WorldModel-Textworld-Llama3.1-8B
Text Generation • 8B • Updated • 98
X1AOX1A/WorldModel-Webshop-Llama3.1-8B
Text Generation • 8B • Updated • 187
X1AOX1A/WorldModel-Stabletoolbench-Qwen2.5-7B
Text Generation • 8B • Updated • 34 • 1
X1AOX1A/WorldModel-Stabletoolbench-Llama3.1-8B
Text Generation • 8B • Updated • 4 • 1