Xianjie Wu

Venues

Frequent coauthors

Papers

1. DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
   AAAI 2026 ·

   Ziyuan Gao

   DBLP profile ↗ORCID search ↗
2. M3TQA: Massively Multilingual Multitask Table Question Answering
   ACL 2026 ·

   Daixin Shu

   DBLP profile ↗ORCID search ↗
3. MMTableBench: A Multi-level Multimodal Benchmark for Reasoning and Layout Complexity in Table QA
   WWW 2026 · Xianjie Wu
4. Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
   ACL 2026 ·

   Zekai Lin

   DBLP profile ↗ORCID search ↗
5. Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
   ACL 2026 ·

   Chao Xue

   DBLP profile ↗ORCID search ↗
6. Table-R1: Region-based Reinforcement Learning for Table Understanding
   ACL 2026 ·

   Zhenhe Wu

   DBLP profile ↗ORCID search ↗
7. Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
   ACL 2026 ·

   Chao Xue

   DBLP profile ↗ORCID search ↗
8. McEval: Massively Multilingual Code Evaluation
   ICLR 2025 ·

   Linzheng Chai

   DBLP profile ↗ORCID search ↗
9. SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
   ICCV 2025 ·

   Xianfu Cheng

   DBLP profile ↗ORCID search ↗
10. Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
    EMNLP 2025 ·

    Xiaoyu Liu

    DBLP profile ↗ORCID search ↗
11. TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
    AAAI 2025 · Xianjie Wu