Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
Paper
•
2502.12488
•
Published
Beijing Institute of AI Safety and Governance
non-profit
AI & ML interests
AI Safety, AI Ethics, AI Governance, Risk Mitigation
Recent Activity
View all activity
Beijing-AISI's activity
xianghe
authored
a
paper
8 days ago
xianghe
authored
a
paper
12 days ago
wdaisies
updated
a
dataset
15 days ago
XduSponge
updated
a
Space
16 days ago
yizeng-ai
updated
a
Space
16 days ago
yizeng-ai
updated
a
dataset
16 days ago
floyed
updated
a
dataset
17 days ago
Upload benchmarks.zip
#2 opened 18 days ago
by
xianghe
Upload benchmarks.zip
#2 opened 18 days ago
by
xianghe
liangdqd
updated
a
dataset
18 days ago
xianghe
authored
4
papers
3 months ago
Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings
Paper
•
2404.19438
•
Published
Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
Paper
•
2410.04190
•
Published
An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain
Paper
•
2303.13077
•
Published
CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization
Paper
•
2408.01952
•
Published