Xiangzhe Xu

8 papers · 2023–2025 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17)

Venues

CVPR (2) ICML (2) NeurIPS (2) EMNLP (1) ICLR (1)

Top co-authors

Xiangyu Zhang (8) Zian Su (5) Kaiyuan Zhang (4) Chengpeng Wang (3) Wuqi Zhang (2) Guangyu Shen (2) Jinyao Guo (2) Yingqi Liu (2) Siyuan Cheng (2) Shiqing Ma (2)

Research topics

Artificial Intelligence (7) Core AI (6) Machine Learning (5) Application Areas (4) Learning Types (3) Natural Language Processing (2) Resources & Methods (2) Deep Learning (1) Learning Paradigms (1) Techniques (1)

Keywords

large language model (2) data flow analysis (2) backdoor detection (2) adversarial learning (2) foundation model (1) binary analysis (1) self-supervised learning (1) false positive (1) preference learning (1) backdoor attack (1) program analysis (1) hallucination mitigation (1) chain-of-thought prompting (1) bug detection (1) trigger pattern (1) source code (1) code decompilation (1) llm agent (1) hierarchical attention (1) transfer learning (1)

Papers

Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning ICLR 2025 ProSec: Fortifying Code LLMs with Proactive Security Alignment ICML 2025 RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing ICML 2025 LLMDFA: Analyzing Dataflow in Code with Large Language Models NeurIPS 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 Sanitizing Large Language Models in Bug Detection with Data-Flow EMNLP 2024 Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases NeurIPS 2024 Detecting Backdoors in Pre-Trained Encoders CVPR 2023