Roman Vainshtein
8 papers · 2024–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
WACV (2)
EACL (1)
ECCV (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
large language model
(3)
zero-shot learning
(1)
benchmark evaluation
(1)
domain adaptation
(1)
ai-generated content
(1)
model evaluation
(1)
bias detection
(1)
responsible ai
(1)
autoregressive model
(1)
agent security
(1)
temporal coherence
(1)
conditional likelihood
(1)
performance degradation
(1)
fairness evaluation
(1)
model auditing
(1)
counterfactual analysis
(1)
training-free detection
(1)
multi-agent system
(1)
disparity audit
(1)
generated image detection
(1)
Papers
MAPS: A Multilingual Benchmark for Agent Performance and Security
EACL 2026
General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
WACV 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
Gradient Inversion of Multimodal Models
ICML 2025
CAIR: Counterfactual-based Agent Influence Ranker for Agentic AI Workflows
EMNLP 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