divelab/LIFT-SFT-12K
Viewer • Updated • 12k • 99
AI & ML interests
None defined yet.
Papers
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
Learnability-Informed Fine-Tuning of Diffusion Language Models
divelab/OrbEvo
Updated • 3.7k
divelab/opdlm_eval_data
Viewer • Updated • 8.52k • 204
divelab/opdlm_train_data
Viewer • Updated • 61.8k • 194
divelab/ShockCast
Updated • 1.37k
divelab/Hybrid_train_new_code
Viewer • Updated • 21.6k • 13
divelab/mix_60k_4096_v1
Viewer • Updated • 119k • 13
divelab/combined_gsm8k_math_dataset_dapo_math_17k_Qwen3-4B_ntokens2048_sft
Viewer • Updated • 186k • 31
divelab/blocksworld
Viewer • Updated • 10.5k • 47
divelab/countdown
Viewer • Updated • 1.64M • 141
divelab/math
Viewer • Updated • 12.5k • 40
divelab/gsm8k
Viewer • Updated • 8.79k • 35
divelab/aqua
Viewer • Updated • 5.25k • 49
divelab/PubChemQCR
Updated • 2.19k • 1
divelab/Sys2Bench
Viewer • Updated • 108k • 165