UCSB-MLSEC

university

https://henrygwb.github.io/

AI & ML interests

None defined yet.

Recent Activity

yuzhounie authored a paper 7 days ago

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

yuzhounie published a model 2 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

yuzhounie updated a model 2 months ago

secmlr/Llama-3.2-3B-final_model

View all activity

secmlr 's models 164

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

secmlr/Llama-3.2-3B-final_model

Text Generation • 3B • Updated Oct 19 • 9

secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Llama-3.2-3B-Instruct_sft

Text Generation • 3B • Updated Oct 19 • 14

secmlr/Qwen2.5-1.5B-final_model

Text Generation • 2B • Updated Oct 18 • 17

secmlr/llama-3.1-8b-final_model

Text Generation • 8B • Updated Oct 18 • 12

secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Qwen2.5-1.5B-Instruct_sft

Text Generation • 2B • Updated Oct 18 • 16

secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Llama-3.1-8B-Instruct_sft

Text Generation • 8B • Updated Oct 18 • 18

secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Meta-Llama-3-8B-Instruct_sft

Text Generation • 8B • Updated Oct 17 • 17

secmlr/best_n_no_rationale_poc_agent_withjava_vulnllm_final_model_repo_vulnscan

Text Generation • 8B • Updated Aug 14 • 8

secmlr/best_n_no_rationale_poc_agent_withjava_vulnllm_final_model_nopolicy_agent_vulnscan

Text Generation • 8B • Updated Aug 7 • 7

secmlr/SWE-BENCH-combine-all_combine-all-32b

Text Generation • 33B • Updated Jul 31 • 9

secmlr/best_n_no_rationale_poc_agent_withjava_vulnllm_final_model_nopolicy_agent_train_vulnscan

secmlr/best_n_rationale_poc_agent_withjava_final_model_nopolicy_agent_train_vulnscan

secmlr/split_context

8B • Updated Jun 25 • 13

secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent_h100_64step_5epoch

Text Generation • 8B • Updated Jun 24 • 10

secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent_h100

Text Generation • 8B • Updated Jun 24 • 14

secmlr/best_n_rationale_poc_agent_withjava_final_model_agent

Text Generation • 8B • Updated Jun 22 • 9

secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent

Text Generation • 8B • Updated Jun 21 • 10

secmlr/best_n_rationale_poc_agent_final_model_agent_train

Text Generation • 8B • Updated Jun 20 • 12

secmlr/best_n_no_rationale_poc_agent_final_model_agent_train

Text Generation • 8B • Updated Jun 20 • 13

secmlr/Qwen3-pi-ft-0.6b

0.6B • Updated Jun 3 • 7

secmlr/SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_qwen_code_0.5b_433_enriched

Text Generation • 0.5B • Updated May 24 • 15

secmlr/QWQ-JAVA_DS-JAVA_final_model_sft

Text Generation • 8B • Updated May 22 • 9

secmlr/dapo_all_reward_final_model

8B • Updated May 21 • 6

secmlr/SWE-BENCH-reproduce-verify-validation-plus-gym-diverse-source_qwen_code_32b_rvvpgds

Text Generation • 33B • Updated May 19 • 8

secmlr/dapo_final_model

8B • Updated May 19 • 6

secmlr/SWE-BENCH-reproduce-verify-validation-plus-gym-diverse-source_qwen_code_7B

Text Generation • 8B • Updated May 18 • 7

secmlr/SWE-BENCH-loc_500_gen_plus_critic_combine_qwen_code_14B

Text Generation • 15B • Updated May 16 • 8

secmlr/SWE-BENCH-validation_combine_diverse_correct_qwen_code_14B

Text Generation • 15B • Updated May 16 • 10

secmlr/SWE-BENCH-generation_claude_reasoning_search_replace_train_first_1000_qwen_code_14b_f

Text Generation • 15B • Updated May 15 • 7