Jiarong Liang

lllqaq's activity

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

updated a model about 12 hours ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fimMidPostV2-r2egym-32k-ckpt808

1.12M • Updated about 12 hours ago • 10

published a model about 12 hours ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fimMidPostV2-r2egym-32k-ckpt808

1.12M • Updated about 12 hours ago • 10

updated a model 1 day ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct-trajmix-gpt5miniAB-claude45AB-r2egymSFT-shuf42-32k-8gpu-oomfix

Text Generation • 841k • Updated 1 day ago • 9

published a model 1 day ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct-trajmix-gpt5miniAB-claude45AB-r2egymSFT-shuf42-32k-8gpu-oomfix

Text Generation • 841k • Updated 1 day ago • 9

updated a model 2 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_posttrain_r2egym_32768_8gpu

Text Generation • 1.12M • Updated 2 days ago • 13

published a model 2 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_posttrain_r2egym_32768_8gpu

Text Generation • 1.12M • Updated 2 days ago • 13

authored a paper 5 days ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published 15 days ago • 12

updated a model 5 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_32768_8gpu

Text Generation • 1.12M • Updated 5 days ago • 7

published a model 5 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_32768_8gpu

Text Generation • 1.12M • Updated 5 days ago • 7

upvoted a paper 6 days ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published 15 days ago • 12

submitted a paper to Daily Papers 6 days ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published 15 days ago • 12

updated a collection 6 days ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 2 items • Updated 5 days ago

updated a model 8 days ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct1-traj-gpt5mini-full-bucketAB_32768_oomfix

Text Generation • 841k • Updated 8 days ago • 12

published a model 8 days ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct1-traj-gpt5mini-full-bucketAB_32768_oomfix

Text Generation • 841k • Updated 8 days ago • 12

updated a model 8 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-r2egym_32768_8gpu

Text Generation • 1.12M • Updated 8 days ago • 15

published a model 8 days ago

lllqaq/R2EGym-32B-Agent-Coder-Instruct-r2egym_32768_8gpu

Text Generation • 1.12M • Updated 8 days ago • 15

updated a model 12 days ago

lllqaq/R2EGym-7B-Agent-Coder-Instruct-merged_bucketAB_32768_8gpu_oomfix

Text Generation • 333k • Updated 12 days ago • 7

published a model 12 days ago

lllqaq/R2EGym-7B-Agent-Coder-Instruct-merged_bucketAB_32768_8gpu_oomfix

Text Generation • 333k • Updated 12 days ago • 7

updated a model 13 days ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct-merged_bucketAB_32768_8gpu_oomfix

Text Generation • 841k • Updated 13 days ago • 9

published a model 13 days ago

lllqaq/R2EGym-14B-Agent-Coder-Instruct-merged_bucketAB_32768_8gpu_oomfix

Text Generation • 841k • Updated 13 days ago • 9