Profiles2024-2026
Xinghua Zhang
Alibaba Group
8Papers
0Last author
13Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- Adaptive Social Learning via Mode Policy Optimization for Language AgentsAuthor 4 of 9ICLR 2026 · 15 citations
- ExpSeek: Self-Triggered Experience Seeking for Web AgentsAuthor 2 of 8ACL Findings 2026
- MemPO: Self-Memory Policy Optimization for Long-Horizon AgentsAuthor 2 of 10ACL Findings 2026
- IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference OptimizationAuthor 1 of 5ACL 2025 · 29 citations
- DEMO: Reframing Dialogue Interaction with Fine-grained Element ModelingAuthor 2 of 8ACL Findings 2025 · 1 citation
- EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language ModelsAuthor 2 of 6EMNLP 2025 · 1 citation
- On the Role of Attention Heads in Large Language Model SafetyAuthor 3 of 9ICLR 2025
- How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden StatesAuthor 3 of 6EMNLP Findings 2024 · 14 citations
