Charlie Ruan

CharlieFRuan's activity

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

upvoted a paper about 1 month ago

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published Sep 29 • 25

liked a dataset about 1 month ago

XiaomiMiMo/MiMo-V2.6-RL-oss

Viewer • Updated 16 days ago • 7.68k • 285k • 1.05k

liked a Space about 2 months ago

Running

Agents

19

Token Count Viewer

⚡

19

Explore token counts across datasets with interactive charts

updated a collection 2 months ago

ApexAgents-SkyRL-Recipe

Collection

Checkpoints and eval traces from "Training frontier knowledge work agents: A 397B open recipe with SkyRL" • 4 items • Updated Sep 1 • 4

updated 2 models 2 months ago

mercor/Qwen3.5-397B-A17B-Mercor

Image-Text-to-Text • 397B • Updated Sep 1 • 24 • 1

mercor/Qwen3.6-35B-A3B-Mercor

Image-Text-to-Text • 35B • Updated Sep 1 • 37 • 3

published a model 2 months ago

mercor/Qwen3.6-35B-A3B-Mercor

Image-Text-to-Text • 35B • Updated Sep 1 • 37 • 3

updated a dataset 2 months ago

mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces

Updated Sep 1 • 272 • 1

published a dataset 2 months ago

mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces

Updated Sep 1 • 272 • 1

updated a dataset 2 months ago

mercor/ApexAgentsRecipe-TBench2_1-EvalTraces

Updated Sep 1 • 575

published a dataset 2 months ago

mercor/ApexAgentsRecipe-TBench2_1-EvalTraces

Updated Sep 1 • 575

updated a model 3 months ago

some-climbers/qwen397b-gs174-aa

397B • Updated Aug 13 • 4

upvoted a paper 5 months ago

Playful Agentic Robot Learning

Paper • 2606.19419 • Published Jun 17 • 49

liked 2 datasets 6 months ago

open-thoughts/AgentTrove

Viewer • Updated May 7 • 1.7M • 7.21k • 206

open-thoughts/TaskTrove

Viewer • Updated Sep 18 • 1.91M • 12.3k • 29

upvoted a paper 7 months ago

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Paper • 2604.04247 • Published Apr 5 • 30

upvoted a collection 8 months ago

M2RNN

Collection

Note that the 7B models are MoE with 1.1B active parameters and 400M models are dense models • 14 items • Updated Mar 12 • 7