Roman Vainshtein
8 papers · 2024–2026 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Keywords
large language model
(3)
zero-shot learning
(2)
benchmark evaluation
(1)
few-shot learning
(1)
domain adaptation
(1)
ai-generated content
(1)
model evaluation
(1)
bias detection
(1)
responsible ai
(1)
generative model
(1)
diffusion model
(1)
autoregressive model
(1)
agent security
(1)
gradient inversion
(1)
temporal coherence
(1)
multimodal model
(1)
conditional likelihood
(1)
performance degradation
(1)
fairness evaluation
(1)
manifold analysis
(1)
Papers
General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
WACV 2026
MAPS: A Multilingual Benchmark for Agent Performance and Security
EACL 2026
Training-free Detection of Text-to-video Generations via Over-coherence
WACV 2026
CAIR: Counterfactual-based Agent Influence Ranker for Agentic AI Workflows
EMNLP 2025
Gradient Inversion of Multimodal Models
ICML 2025
Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
ICLR 2025
TFDP: Token-Efficient Disparity Audits for Autoregressive LLMs via Single-Token Masked Evaluation
EMNLP 2025
MONTAGE: Monitoring Training for Attribution of Generative Diffusion Models
ECCV 2024