Shiyao Cui
15 papers · 2020–2026 · 4 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 ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (27)
🧬
Topic Evolution
🗃️
Keyword Collector
(79)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(11)
Natural Language Processing
(10)
Deep Learning
(5)
Applications
(5)
Machine Learning
(4)
Resources & Methods
(4)
Learning Types · Deep Learning
(3)
Understanding
(3)
Application Areas
(2)
Knowledge & Reasoning
(1)
Security & Privacy
(1)
Architectures
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Keywords
large language model
(3)
supervised fine-tuning
(2)
visual grounding
(2)
safety benchmark
(2)
model compression
(2)
multimodal learning
(2)
attack success rate
(2)
information extraction
(1)
relation extraction
(1)
gradient-based optimization
(1)
toxic content detection
(1)
event detection
(1)
adversarial attack
(1)
memory efficiency
(1)
safety alignment
(1)
jailbreaking attack
(1)
in-context learning
(1)
multimodal large language model
(1)
cross-modal alignment
(1)
language model
(1)
Papers
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
ACL 2026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
ACL 2026
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
ACL 2026
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning
ACL 2026
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity
AAAI 2026
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
ACL 2025
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
ACL 2025
LongSafety: Evaluating Long-Context Safety of Large Language Models
ACL 2025
An Effective Span-based Multimodal Named Entity Recognition with Consistent Cross-Modal Alignment
COLING 2024
LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion
ACL 2024
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time
ACL 2024
Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction
ACL 2023
Event Causality Extraction with Event Argument Correlations
COLING 2022
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
ACL 2021
Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
EMNLP 2020