UCSB-MLSEC

university

https://henrygwb.github.io/

AI & ML interests

None defined yet.

Recent Activity

March07 submitted a paper about 1 month ago

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

yuzhounie authored a paper 3 months ago

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection

yuzhounie published a model 5 months ago

secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_gpt-oss-20b_sft

View all activity

secmlr 's datasets 61

secmlr/patching_mcts_hard

Viewer • Updated Apr 14, 2025 • 7.3k • 4

secmlr/patching_mcts_soft

Viewer • Updated Apr 14, 2025 • 7.31k • 4

secmlr/ossfuzz_dataset_ds_correct_direct_QwQ-32B_train_len_32000_inputlen_16000

Viewer • Updated Apr 11, 2025 • 139 • 5

secmlr/clean_dataset_ds_correct_direct_QwQ-32B_train_len_32000_inputlen_16000

Viewer • Updated Apr 11, 2025 • 5.08k • 5

secmlr/noisy_dataset_ds_correct_direct_QwQ-32B_small_train_len_32000_inputlen_16000

Viewer • Updated Apr 11, 2025 • 2.72k • 6

secmlr/noisy_dataset_ds_correct_together-deepseek-reasoner_small_train_len_32000_inputlen_16000

Viewer • Updated Apr 11, 2025 • 2.91k • 5

secmlr/clean_dataset_ds_correct_together-deepseek-reasoner_train_len_32000_inputlen_16000

Viewer • Updated Apr 11, 2025 • 5.14k • 4

secmlr/clean_dataset_ds_correct_QwQ-32B_train_len_32000_inputlen_16000

Viewer • Updated Apr 10, 2025 • 5.08k • 5

secmlr/noisy_dataset_ds_correct_QwQ-32B_small_train_len_32000_inputlen_16000

Viewer • Updated Apr 10, 2025 • 2.72k • 4

secmlr/clean_dataset_dsformat_filtered_QwQ-32B_train_len_32000_inputlen_16000

Viewer • Updated Apr 10, 2025 • 5.95k • 5

secmlr/ossfuzz_dataset_filtered_QwQ-32B_train_len_32000_inputlen_16000

Viewer • Updated Apr 4, 2025 • 251 • 5

secmlr/patching_mcts

Viewer • Updated Apr 2, 2025 • 3.61k • 6

secmlr/reduced_noisy_dataset_filtered_QwQ-32B-Preview_small_train_len_8000_inputlen_5000

Viewer • Updated Mar 23, 2025 • 3.95k • 5

secmlr/reduced_clean_dataset_filtered_together-deepseek-reasoner_train_len_8000_inputlen_5000

Viewer • Updated Mar 23, 2025 • 4.98k • 4

secmlr/reduced_clean_dataset_filtered_QwQ-32B-Preview_train_len_8000_inputlen_5000

Viewer • Updated Mar 23, 2025 • 5.16k • 5

secmlr/Math-Shepherd

Viewer • Updated Mar 23, 2025 • 517k • 5

secmlr/prm_clean_dataset_filtered_QwQ-32B-Preview_train_len_8000_inputlen_5000

Viewer • Updated Mar 23, 2025 • 1.37k • 5

secmlr/VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_train_dpo

Viewer • Updated Mar 12, 2025 • 5.45k • 4

secmlr/noisy_dataset_filtered_QwQ-32B-Preview_small_train_len_16000_inputlen_5000

Viewer • Updated Mar 11, 2025 • 3.96k • 5

secmlr/noisy_dataset_filtered_QwQ-32B-Preview_small_train_len_8000_inputlen_5000

Viewer • Updated Mar 11, 2025 • 3.95k • 5

secmlr/Sky-T1_preference_data_10k_filtered

Viewer • Updated Mar 4, 2025 • 9.39k • 6

secmlr/VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_train_dpo_filtered

Viewer • Updated Mar 3, 2025 • 5.72k • 4

secmlr/Sky-T1_data_17k_filtered

Viewer • Updated Mar 1, 2025 • 14.6k • 25

secmlr/clean_dataset_filtered_together-deepseek-reasoner_train_len_8000_inputlen_5000

Viewer • Updated Mar 1, 2025 • 4.98k • 5

secmlr/clean_dataset_dsformat_filtered_QwQ-32B-Preview_train_len_8000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 5.16k • 5

secmlr/clean_dataset_dsformat_filtered_QwQ-32B-Preview_train_len_16000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 5.16k • 5

secmlr/clean_dataset_filtered_together-deepseek-reasoner_train_len_16000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 4.99k • 5

secmlr/clean_dataset_dsformat_filtered_together-deepseek-reasoner_train_len_8000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 4.98k • 5

secmlr/clean_dataset_dsformat_filtered_together-deepseek-reasoner_train_len_16000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 4.99k • 5

secmlr/clean_dataset_filtered_QwQ-32B-Preview_train_len_16000_inputlen_5000

Viewer • Updated Feb 28, 2025 • 5.16k • 5