Mrinank Sharma
8 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π Academic Marathon (5) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Renaissance Researcher
(6)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
π₯
Mega-Team
(34)
β
The Questioner
(2)
Conferences
ICLR (3)
ICML (2)
NIPS (2)
AISTATS (1)
Top co-authors
Keywords
causal inference
(1)
sample efficiency
(1)
variational inference
(1)
curriculum learning
(1)
posterior approximation
(1)
data selection
(1)
jailbreaking attack
(1)
bayesian neural network
(1)
adversarial prompt
(1)
red teaming
(1)
context window
(1)
training acceleration
(1)
robustness analysis
(1)
epidemiological modeling
(1)
probabilistic predictor
(1)
model generalisation
(1)
large language model
(1)
generalization loss
(1)
redundant datum
(1)
epidemiological model
(1)
Papers
PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data
ICML 2025
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
ICLR 2025
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
ICLR 2025
Towards Understanding Sycophancy in Language Models
ICLR 2024
Many-shot Jailbreaking
NIPS 2024
Do Bayesian Neural Networks Need To Be Fully Stochastic?
AISTATS 2023
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
ICML 2022
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
NIPS 2020