bug-bounty448
google354
microsoft311
facebook262
xss238
apple179
malware174
rce149
exploit124
bragging-post101
cve99
account-takeover93
phishing83
csrf79
privilege-escalation77
supply-chain65
stored-xss65
authentication-bypass63
dos60
browser57
reflected-xss57
react50
cloudflare49
cross-site-scripting48
reverse-engineering48
input-validation48
access-control47
aws45
docker45
smart-contract45
node44
sql-injection43
ethereum43
web343
defi42
web-security42
web-application41
ssrf38
burp-suite35
idor34
vulnerability-disclosure34
info-disclosure33
race-condition33
html-injection33
cloud32
writeup32
oauth32
buffer-overflow32
smart-contract-vulnerability32
information-disclosure30
0
2/10
This paper proposes using Neural Cellular Automata (NCA)—synthetic data generated from learned transition rules on grids—as pre-training data for language models, achieving 6% perplexity gains and 1.6× faster convergence than natural language pre-training at equivalent scale. The key insight is that NCA sequences force models to develop in-context rule inference capabilities purely from structural patterns without semantic shortcuts, resulting in more transferable representations to downstream language tasks.
language-models
synthetic-data
pre-training
neural-cellular-automata
transformer
in-context-learning
research
machine-learning
Neural Cellular Automata (NCA)
OpenWebText
OpenWebMath
CodeParrot
C4
GSM8K
HumanEval
BigBench-Lite
Conway's Game of Life