Hao Di
3 papers · 2024–2025 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
composite optimization
(1)
variance reduction
(1)
iteration complexity
(1)
proximal algorithm
(1)
zeroth-order optimization
(1)
jailbreaking attack
(1)
doubly stochastic matrix
(1)
adversarial prompting
(1)
large language model
(1)
harmful output
(1)
perplexity defense
(1)
accelerated
(1)
communication network topology
(1)
snapshot
(1)
stochastic gradient tracking
(1)
coordinate-wise variance
(1)
stochastic zeroth-order oracle
(1)
Papers
ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
ICLR 2025
Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods
ICML 2024
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
ICML 2024