Keivan Rezaei
8 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (27) π£ Hot Topic Early Bird π Cross-Pollinator (13) π Renaissance Researcher (5) π Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(5)
π
Grand Slam
π
Triple Crown
β‘
Prolific Year
(5)
Conferences
ICML (3)
ICLR (2)
AAAI (1)
ACL (1)
NIPS (1)
Top co-authors
Keywords
retrieval augmented generation
(1)
feature alignment
(1)
certified robustness
(1)
online learning
(1)
data poisoning
(1)
fact verification
(1)
feature embedding
(1)
out-of-distribution generalization
(1)
majority vote
(1)
cumulative regret
(1)
regret bound
(1)
sublinear regret
(1)
ensemble method
(1)
cross-modal alignment
(1)
incentive compatibility
(1)
welfare maximization
(1)
auction mechanism
(1)
vision-language model
(1)
concept bottleneck
(1)
tabular datum
(1)
Papers
RePanda: Pandas-powered Tabular Verification and Reasoning
ACL 2025
Regret Analysis of Repeated Delegated Choice
AAAI 2024
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024
PRIME: Prioritizing Interpretability in Failure Mode Extraction
ICLR 2024
On Mechanistic Knowledge Localization in Text-to-Image Generative Models
ICML 2024
Ad Auctions for LLMs via Retrieval Augmented Generation
NIPS 2024
Run-off Election: Improved Provable Defense against Data Poisoning Attacks
ICML 2023
Text-To-Concept (and Back) via Cross-Model Alignment
ICML 2023