Longzhu He
4 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(15)
Conferences
EMNLP (2)
ACL (1)
ICML (1)
Top co-authors
Keywords
retrieval-augmented generation
(2)
large language model
(2)
chain-of-thought reasoning
(1)
model safety
(1)
safety alignment
(1)
supervised fine-tuning
(1)
jailbreak attack
(1)
jailbreak defense
(1)
adaptive decoding
(1)
distractor generation
(1)
multiple choice question
(1)
multimodal chain-of-thought
(1)
token-level refinement
(1)
adversarial learning
(1)
visual option generation
(1)
knowledge editing
(1)
Papers
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
ACL 2026
Beyond the Textual: Generating Coherent Visual Options for MCQs
EMNLP 2025
Going Deeper into Locally Differentially Private Graph Neural Networks
ICML 2025
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions
EMNLP 2024