bug-bounty507
xss280
rce130
bragging-post118
account-takeover106
open-source94
google90
csrf85
authentication-bypass83
exploit75
stored-xss74
facebook74
privilege-escalation70
access-control65
web-security65
microsoft63
reflected-xss63
ai-agents63
cve54
input-validation51
writeup49
sql-injection48
smart-contract48
defi48
cross-site-scripting47
ssrf47
privacy46
tool46
information-disclosure45
ethereum44
api-security41
malware39
web-application39
llm37
automation36
burp-suite36
opinion35
vulnerability-disclosure34
web334
phishing34
smart-contract-vulnerability33
html-injection33
responsible-disclosure33
machine-learning32
infrastructure31
apple31
code-generation31
waf-bypass31
idor30
oauth30
0
2/10
LoGeR is a novel deep learning architecture from DeepMind and UC Berkeley for 3D geometric reconstruction from extremely long videos (up to 19,000 frames) using a hybrid memory module that combines Sliding Window Attention for local precision with Test-Time Training for global consistency, achieving state-of-the-art results on KITTI, 7-Scenes, and long-sequence benchmarks while maintaining sub-quadratic complexity.
3d-reconstruction
computer-vision
deep-learning
video-processing
attention-mechanism
long-context-modeling
geometric-alignment
slam
machine-learning
neural-networks
LoGeR
Google DeepMind
UC Berkeley
Junyi Zhang
Charles Herrmann
Junhwa Hur
Chen Sun
Ming-Hsuan Yang
Forrester Cole
Trevor Darrell
Deqing Sun
KITTI
VBR
7-Scenes
ScanNet
TUM-Dynamics