Zixiang Xu
4 papers · 2025–2026 · 3 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
🗺️
Taxonomy Completionist
(13)
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
semantic alignment
(1)
bayesian optimization
(1)
adversarial perturbation
(1)
zero-shot generalization
(1)
safety evaluation
(1)
jailbreak attack
(1)
large vision-language model
(1)
beam search
(1)
multilingual large language model
(1)
cross-lingual consistency
(1)
cross-lingual weakness
(1)
bilingual probing
(1)
linguistic similarity
(1)
cross-lingual generalization
(1)
audio perturbation
(1)
audio-language model
(1)
verifiable reward
(1)
bilingual evaluation
(1)
embodied manipulation
(1)
Papers
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
ACL 2026
ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
AAAI 2026
Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models
ACL 2025
Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
EMNLP 2025