Xiangzheng Zhang

Venues

Frequent coauthors

Papers

1. DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
   ACL 2026 ·

   Wenzhuo Xu

   DBLP profile ↗ORCID search ↗
2. Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
   AAAI 2026 ·

   Jianfeng Si

   DBLP profile ↗ORCID search ↗
3. Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
   AAAI 2026 ·

   Chenyang Wang

   DBLP profile ↗ORCID search ↗
4. Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
   ACL 2026 ·

   Guangxiang Zhao

   DBLP profile ↗ORCID search ↗
5. TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
   ACL 2026 ·

   Zhewen Tan

   DBLP profile ↗ORCID search ↗
6. When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
   ACL 2026 ·

   Lin Sun

   DBLP profile ↗ORCID search ↗
7. Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
   EMNLP 2025 ·

   Dawei Zhu

   DBLP profile ↗ORCID search ↗
8. Expand VSR Benchmark for VLLM to Expertize in Spatial Rules
   AAAI 2025 ·

   Peijin Xie

   DBLP profile ↗ORCID search ↗
9. Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
   EMNLP 2025 ·

   Guangxiang Zhao

   DBLP profile ↗ORCID search ↗
10. Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
    ACL 2025 ·

    Liang Wen

    DBLP profile ↗ORCID search ↗
11. Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
    EMNLP 2025 ·

    Zonghao Ying

    DBLP profile ↗ORCID search ↗
12. Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
    ECAI 2025 ·

    Junfeng Ran

    DBLP profile ↗ORCID search ↗