arxiv:2601.01426
Yuxin Jiang
YuxinJiang
AI & ML interests
NLP
Recent Activity
updated a dataset about 14 hours ago
SWE-Lego/samples_for_llama_factory_sft published a dataset about 14 hours ago
SWE-Lego/samples_for_llama_factory_sft upvoted a paper about 20 hours ago
What Makes Interaction Trajectories Effective for Training Terminal Agents?Organizations
models 6
YuxinJiang/lion-7b
Text Generation • Updated • 2 • 10
YuxinJiang/debate-alpaca-lora_7b_002
Updated • 1
YuxinJiang/debate-alpaca-lora_7b_001
Updated
YuxinJiang/sup-promcse-roberta-base
Updated • 4 • 1
YuxinJiang/unsup-promcse-bert-base-uncased
Updated • 6 • 1
YuxinJiang/sup-promcse-roberta-large
Updated • 14 • 3
datasets 18
YuxinJiang/SWE-bench_Verified_second_half
Viewer • Updated • 250 • 8
YuxinJiang/SWE-bench_Verified_first_half
Viewer • Updated • 250 • 24
YuxinJiang/SWE-bench_Verified_Subset100
Viewer • Updated • 100 • 40
YuxinJiang/WebR-Pro-100k
Viewer • Updated • 100k • 38 • 2
YuxinJiang/WebR-Basic-100k
Viewer • Updated • 100k • 17
YuxinJiang/autoif_8k_gpt_4o_mini
Viewer • Updated • 7.79k • 17
YuxinJiang/autoif_l1_5
Viewer • Updated • 18k • 8
YuxinJiang/autoif_l1_10
Viewer • Updated • 20.3k • 8
YuxinJiang/RL_IF
Viewer • Updated • 61.5k • 8
YuxinJiang/magpie_100k_llama3
Viewer • Updated • 120k • 27