arxiv:2603.20691
Jiarong Liang
lllqaq
AI & ML interests
Large Language Models (LLMs)
Natural Language Processing (NLP)
Recent Activity
upvoted a paper 2 days ago
Watch Before You Answer: Learning from Visually Grounded Post-Training authored a paper 2 days ago
SWE-Next: Scalable Real-World Software Engineering Tasks for Agents updated a dataset 3 days ago
TIGER-Lab/packages_python_filteredOrganizations
models 42
lllqaq/Qwen3-8B-fim-v2v3pt
Text Generation • 308k • Updated • 155
lllqaq/R2EGym-7B-Agent-Coder-Instruct1-merged_bucketab_4sources_11_0319
Text Generation • 333k • Updated • 13
lllqaq/Qwen2.5-Coder-7B-Instruct-num06-accumulate_16_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated • 16
lllqaq/Qwen2.5-Coder-7B-Instruct-num05-accumulate_16_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated • 16
lllqaq/Qwen2.5-Coder-7B-fim-v2-filtered-0316
Text Generation • 333k • Updated • 14
lllqaq/Qwen2.5-Coder-7B-fim-v2-filtered-0316_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated • 25
lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu
Text Generation • 333k • Updated • 46
lllqaq/R2EGym-Qwen3-14B-merged_bucketab_4src_32768_4gpu_oomfix
Text Generation • 425k • Updated • 16
lllqaq/R2EGym-Qwen3-8B-Agent-Coder-Instruct1-merged_bucketab_4sources_11
Text Generation • 308k • Updated • 13
lllqaq/Qwen2.5-Coder-7B-fim-v1-128batchsize
Text Generation • 333k • Updated • 11
datasets 0
None public yet