arxiv:2508.03346
Zeju Li
zeju-0727
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 21 hours ago
ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition
updated
a dataset
2 months ago
zeju-0727/SFT_cot_compression
published
a dataset
2 months ago
zeju-0727/SFT_cot_compression
Organizations
models
9
zeju-0727/grpo-10k-3-reward-h100-1
8B
•
Updated
zeju-0727/grpo-10k-4-reward-h100-1
8B
•
Updated
zeju-0727/Dyve_plus_RL_copy
Updated
zeju-0727/Dyve_plus_RL
Updated
zeju-0727/rtl_eval
Updated
zeju-0727/dyver_qwen
Updated
zeju-0727/o1
Updated
zeju-0727/dyver_code_zeju
Updated
zeju-0727/openr_deepseek_our
Updated
datasets
30
zeju-0727/SFT_cot_compression
Viewer
•
Updated
•
74k
•
21
zeju-0727/DeepCirCuitX_Dataset
Updated
•
7
zeju-0727/111
Updated
•
1
zeju-0727/filter_130k_code
Updated
•
1
zeju-0727/openai_math_90k
Viewer
•
Updated
•
93.7k
•
12
zeju-0727/merge_lora_model
Updated
•
3
zeju-0727/grpo_train_code
Updated
•
12
zeju-0727/huhuhu_data
Updated
•
3
zeju-0727/train_code
Updated
•
5
zeju-0727/toc_comp_dataset
Preview
•
Updated
•
3