Junxiao Yang

5 papers · 2024–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)

Venues

ACL (4) AAAI (1)

Top co-authors

Minlie Huang (5) Hongning Wang (5) Zhexin Zhang (5) Shiyao Cui (4) Han Qiu (2) Yingkang Wang (2) Fei Mi (2) Jinzhe Tu (1) Lifeng Shang (1) Jiaqi Weng (1)

Research topics

Artificial Intelligence (5) Core AI (5) Natural Language Processing (3) Resources & Methods (2) Deep Learning (1) Learning Types (1) Understanding (1)

Keywords

safety alignment (2) jailbreaking attack (2) attack success rate (2) supervised fine-tuning (1) jailbreak attack (1) goal prioritization (1) reasoning process (1) data distillation (1) large reasoning model (1) llm security (1) multilingual safety (1) language-agnostic representation (1) large language model (1) safety enhancement (1) semantic cognition (1) safety defense (1) emoji-triggered toxicity (1) gradient-based optimization (1) semantic bottleneck (1) instruction following (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 When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026 Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025 Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization ACL 2024