Jonathan Brokman
5 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
federated learning
(1)
zero-shot learning
(1)
benchmark evaluation
(1)
few-shot learning
(1)
ai-generated content
(1)
neural network optimization
(1)
parameter clustering
(1)
generative model
(1)
diffusion model
(1)
training dynamics
(1)
agent security
(1)
temporal coherence
(1)
performance degradation
(1)
manifold analysis
(1)
image detection
(1)
training-free detection
(1)
large language model
(1)
multilingual agentic system
(1)
text-to-video detection
(1)
correlation mode decomposition
(1)
Papers
MAPS: A Multilingual Benchmark for Agent Performance and Security
EACL 2026
Training-free Detection of Text-to-video Generations via Over-coherence
WACV 2026
Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
ICLR 2025
Enhancing Neural Training via a Correlated Dynamics Model
ICLR 2024
MONTAGE: Monitoring Training for Attribution of Generative Diffusion Models
ECCV 2024