Ming Ma
6 papers · 2017–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(5)
π
Academic Marathon
(8)
π
Cross-Pollinator
(12)
π
Interdisciplinary Bridge
Conferences
AAAI (1)
ACL (1)
ICCV (1)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
large language model
(3)
dynamic routing
(1)
abductive learning
(1)
symbolic planning
(1)
adversarial defense
(1)
implicit bia
(1)
instruction fine-tuning
(1)
safety framework
(1)
usability preservation
(1)
harmless response
(1)
state machine
(1)
neuro-symbolic learning
(1)
llm safety
(1)
defense strategy
(1)
security threat
(1)
bias manipulation
(1)
harmful output
(1)
security mechanism
(1)
secure tuning
(1)
adversarial learning
(1)
Papers
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
ACL 2026
Investigating the Security Threat Arising from βYes-Noβ Implicit Bias in Large Language Models
AAAI 2025
Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments
ICML 2025
From End-to-end to Step-by-step: Learning to Abstract via Abductive Reinforcement Learning
IJCAI 2025
MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
NIPS 2024
Surface Registration via Foliation
ICCV 2017