arxiv:2602.13294
Jiarong Liang
lllqaq
AI & ML interests
Large Language Models (LLMs)
Natural Language Processing (NLP)
Recent Activity
published
a model 1 minute ago
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num03_posttrain_r2egym_32768_8gpu updated
a model 2 days ago
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num02_posttrain_r2egym_32768_8gpu published
a model 2 days ago
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num02_posttrain_r2egym_32768_8gpu Organizations
models 31
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num03_posttrain_r2egym_32768_8gpu
Updated
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num02_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated
• 23
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num01_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated
• 18
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_11_epochs468
Updated
lllqaq/R2EGym-7B-Agent-Coder-Instruct1-merged_bucketab_4sources_sweep
Updated
lllqaq/R2EGym-32B-Agent-Coder-Instruct_merged_bucketab_4sources_20260228_101548_32768_8gpu
Text Generation • 1.12M • Updated
• 14
lllqaq/R2EGym-7B-Agent-Coder-Instruct-merged_bucketab_4sources_20260228_101548_32768_3gpu_oomfix
Text Generation • 333k • Updated
• 38
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-traj_reward1_loose_4sources_shuf42_ckpt2400
841k • Updated
• 11
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_20260228_101548_32768_4gpu_oomfix
Text Generation • 841k • Updated
• 14
lllqaq/R2EGym-14B-Agent-Coder-Instruct-traj_bucketAB_multi_3sources_bucketAB_sft_shuf42
Text Generation • 841k • Updated
• 12