Wynne Li

wxli318's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in wxli318/GenAgent_Raw_Rollouts 7 days ago

Add best-of-8 reruns of the 1,607 low-score tasks: picks, lists with reruns, GLM scores

#4 opened 7 days ago by

Owen777

New activity in wxli318/GenAgent_Raw_Rollouts 8 days ago

Add CoReBench_Style_Synth selection: filters, holdout, train tiers, GLM scores

#3 opened 8 days ago by

Owen777

Add CoReBench_Style_Synth rollouts: 7,608 DeepSeek trajectories with Qwen-Image-2.1-Turbo

1

#2 opened 8 days ago by

Owen777

Add CoReBench_Style_Synth: 7,608 CoReBench-style synthetic prompts after leak filtering

1

#1 opened 8 days ago by

Owen777