Xiangzheng Zhang

39 papers A* 5A 1Journal 30Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging. CoRR Weihong Lin, Lin Sun, Qilong Shi, Aomufei Yuan, Yuxuan Tian, Zhengyang Wang, Guangxiang Zhao, Xiangzheng Zhang, Tong Yang
2026	J	`jnl`	Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought. CoRR Jianfeng Si, Lin Sun, Weihong Lin, Xiangzheng Zhang
2026	J	`jnl`	DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection. CoRR Weilin Zhou, Zonghao Ying, Chunlei Meng, Jiahui Liu, Hengyang Zhou, Quanchen Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang
2026	A*	`conf`	Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training. AAAI Jianfeng Si, Lin Sun, Zhewen Tan, Xiangzheng Zhang
2026	J	`jnl`	FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning. CoRR Lin Sun, Linglin Zhang, Jingang Huang, Change Jia, Zhengwei Cheng, Xiangzheng Zhang
2026	A*	`conf`	Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following. AAAI Chenyang Wang, Liang Wen, Shousheng Jia, Xiangzheng Zhang, Liang Xu
2026	J	`jnl`	MT-dyna: A framework for evaluating multi-turn capabilities of LLMs. Appl. Soft Comput. Jun Gao, Junlin Cui, Anwen Yang, Yiqi Tong, Huijia Wu, Xiangzheng Zhang, Yaodong Yang, Zhaofeng He
2026	J	`jnl`	Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models. CoRR Quanchen Zou, Moyang Chen, Zonghao Ying, Wenzhuo Xu, Yisong Xiao, Deyue Zhang, Dongdong Yang, Zhao Liu, Xiangzheng Zhang
2026	J	`jnl`	Robust Privacy: Inference-Time Privacy through Certified Robustness. CoRR Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Deyue Zhang, Quanchen Zou
2026	J	`jnl`	SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization. CoRR Xinghao Wang, Changtao Miao, Dianmo Sheng, Tao Gong, Qi Chu, Nenghai Yu, Quanchen Zou, Deyue Zhang, Xiangzheng Zhang
2026	J	`jnl`	TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment. CoRR Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Duohe Ma, Xiangzheng Zhang, Tong Yang, Lin Sun
2026	J	`jnl`	Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking. CoRR Moyang Chen, Zonghao Ying, Wenzhuo Xu, Quancheng Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang
2026	J	`jnl`	VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models. CoRR Chonghan Liu, Yimin Du, Qi An, Xin He, Cunqi Zhai, Fei Tan, Weijia Lin, Xiaochun Gong, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang
2026	J	`jnl`	VIP-doc :Visual prompts guide fine-grained document understanding for reader friendly VLLM. Expert Syst. Appl. Peijin Xie, Dexin Wang, Lin Sun, Xiangzheng Zhang, Yunhe Xie, Shun Qian, Chengjie Sun, Bingquan Liu
2025	J	`jnl`	360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training. CoRR Haosheng Zou, Xiaowei Lv, Shousheng Jia, Xiangzheng Zhang
2025	—	`conf`	Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision. EMNLP (Findings) Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, Xun Wang, Lin Sun, Xiangzheng Zhang, Sujian Li
2025	J	`jnl`	Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision. CoRR Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, Xun Wang, Lin Sun, Xiangzheng Zhang, Sujian Li
2025	J	`jnl`	Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection. CoRR Weilin Zhou, Zonghao Ying, Junjie Mu, Shengwei Tian, Quanchen Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang
2025	J	`jnl`	Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training. CoRR Jianfeng Si, Lin Sun, Zhewen Tan, Xiangzheng Zhang
2025	J	`jnl`	Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design. CoRR Lin Sun, Weihong Lin, Jinzhu Wu, Yongfu Zhu, Xiaoqi Jian, Guangxiang Zhao, Change Jia, Linglin Zhang, Saier Hu, Yuhan Wu, Xiangzheng Zhang
2025	A*	`conf`	Expand VSR Benchmark for VLLM to Expertize in Spatial Rules. AAAI Peijin Xie, Lin Sun, Bingquan Liu, Dexin Wang, Xiangzheng Zhang, Chengjie Sun, Jiajia Zhang
2025	A*	`conf`	Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements. EMNLP Guangxiang Zhao, Saier Hu, Xiaoqi Jian, Jinzhu Wu, Yuhan Wu, Lin Sun, Xiangzheng Zhang
2025	J	`jnl`	Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following. CoRR Chenyang Wang, Liang Wen, Shousheng Jia, Xiangzheng Zhang, Liang Xu
2025	—	`conf`	Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond. ACL (6) Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Lifu Tang, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang
2025	J	`jnl`	Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond. CoRR Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Lifu Tang, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang
2025	J	`jnl`	Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks? CoRR Junjie Mu, Zonghao Ying, Zhekui Fan, Zonglei Jing, Yaoyuan Zhang, Zhengmin Yu, Wenxin Zhang, Quanchen Zou, Xiangzheng Zhang
2025	—	`conf`	Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models. EMNLP (Findings) Zonghao Ying, Deyue Zhang, Zonglei Jing, Yisong Xiao, Quanchen Zou, Aishan Liu, Siyuan Liang, Xiangzheng Zhang, Xianglong Liu, Dacheng Tao
2025	J	`jnl`	Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models. CoRR Zonghao Ying, Deyue Zhang, Zonglei Jing, Yisong Xiao, Quanchen Zou, Aishan Liu, Siyuan Liang, Xiangzheng Zhang, Xianglong Liu, Dacheng Tao
2025	A	`conf`	Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling. ECAI Junfeng Ran, Guangxiang Zhao, Yuhan Wu, Dawei Zhu, Longyun Wu, Yikai Zhao, Tong Yang, Lin Sun, Xiangzheng Zhang, Sujian Li
2025	J	`jnl`	Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling. CoRR Junfeng Ran, Guangxiang Zhao, Yuhan Wu, Dawei Zhu, Longyun Wu, Yikai Zhao, Tong Yang, Lin Sun, Xiangzheng Zhang, Sujian Li
2025	J	`jnl`	Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling. CoRR Deyue Zhang, Dongdong Yang, Junjie Mu, Quanchen Zou, Zonghao Ying, Wenzhuo Xu, Zhao Liu, Xuan Wang, Xiangzheng Zhang
2025	J	`jnl`	Stress Testing Generalization: How Minor Modifications Undermine Large Language Model Performance. CoRR Guangxiang Zhao, Saier Hu, Xiaoqi Jian, Jinzhu Wu, Yuhan Wu, Change Jia, Lin Sun, Xiangzheng Zhang
2025	J	`jnl`	TextlessRAG: End-to-End Visual Document RAG by Speech Without Text. CoRR Peijin Xie, Shun Qian, Bingquan Liu, Dexin Wang, Lin Sun, Xiangzheng Zhang
2025	J	`jnl`	TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation. CoRR Lin Sun, Guangxiang Zhao, Xiaoqi Jian, Yuhan Wu, Weihong Lin, Yongfu Zhu, Change Jia, Linglin Zhang, Jinzhu Wu, Junfeng Ran, Saier Hu, Zihan Jiang, Junting Zhou, Wenrui Liu, Bin Cui, Tong Yang, Xiangzheng Zhang
2025	J	`jnl`	Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM. CoRR Yongfu Zhu, Lin Sun, Guangxiang Zhao, Weihong Lin, Xiangzheng Zhang
2025	J	`jnl`	Utilizing Jailbreak Probability to Attack and Safeguard Multimodal LLMs. CoRR Wenzhuo Xu, Zhipeng Wei, Xiongtao Sun, Deyue Zhang, Dongdong Yang, Quanchen Zou, Xiangzheng Zhang
2024	J	`jnl`	Expand VSR Benchmark for VLLM to Expertize in Spatial Rules. CoRR Peijin Xie, Lin Sun, Bingquan Liu, Dexin Wang, Xiangzheng Zhang, Chengjie Sun, Jiajia Zhang
2024	J	`jnl`	TransGCN: a semi-supervised graph convolution network-based framework to infer protein translocations in spatio-temporal proteomics. Briefings Bioinform. Bing Wang, Xiangzheng Zhang, Xudong Han, Bingjie Hao, Yan Li, Xuejiang Guo
2023	A*	`conf`	CCMB: A Large-scale Chinese Cross-modal Benchmark. ACM Multimedia Chunyu Xie, Heng Cai, Jincheng Li, Fanjing Kong, Xiaoyu Wu, Jianfei Song, Henrique Morimitsu, Lin Yao, Dexin Wang, Xiangzheng Zhang, Dawei Leng, Baochang Zhang, Xiangyang Ji, Yafeng Deng