bug-bounty458
google364
microsoft314
facebook272
xss250
apple179
malware176
rce165
exploit141
cve111
account-takeover104
bragging-post101
phishing84
privilege-escalation81
csrf81
supply-chain68
stored-xss65
authentication-bypass63
dos63
browser62
reflected-xss57
react54
cloudflare51
reverse-engineering49
cross-site-scripting48
input-validation48
aws48
docker47
node47
access-control47
smart-contract45
web343
ethereum43
sql-injection43
web-security42
ssrf42
defi42
web-application41
oauth37
writeup37
race-condition36
burp-suite35
vulnerability-disclosure34
info-disclosure34
idor34
html-injection33
cloud33
auth-bypass33
lfi32
smart-contract-vulnerability32
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