Proactive Security Alignment

non-profit

AI & ML interests

None defined yet.

Recent Activity

ziansu authored a paper 19 days ago

Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary

ziansu authored a paper 19 days ago

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

ziansu authored a paper 19 days ago

LLMDFA: Analyzing Dataflow in Code with Large Language Models

View all activity

prosecalign 's models 35

prosecalign/phi3m0128-wds-0.3-kendall-onof-ofif-corr-max-2-simpo-max1500-default

prosecalign/phi3m0128-wds-0.1-kendall-onof-ofif-corr-max-2-simpo-max1500-default

prosecalign/phi3m0128-wds-0.5-kendall-onof-ofif-corr-max-2-simpo-max1500-default

prosecalign/phi3m0128-kendall-on-neg_if-corr-max-2-simpo-max1500-decay-sft0.2-beta1.5-gamma0.5-lr5e-6

prosecalign/phi3m0128-kendall-onof-neg_if-corr-max-2-simpo-max1500-decay-sft0.2-beta1.5-gamma0.5-lr5e-6