Xiachong Feng

Venues

Frequent coauthors

Papers

1. Adaptive Backtracking for Privacy Protection in Large Language Models
   ACL 2026 ·

   Zhihao Yao

   DBLP profile ↗ORCID search ↗
2. Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
   AAAI 2026 ·

   Qiming Li

   DBLP profile ↗ORCID search ↗
3. Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management
   ACL 2026 ·

   Weitao Ma

   DBLP profile ↗ORCID search ↗
4. ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models
   ACL 2026 ·

   Chonghan Qin

   DBLP profile ↗ORCID search ↗
5. LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning
   AAAI 2026 ·

   Yangfan Ye

   DBLP profile ↗ORCID search ↗
6. OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models
   ACL 2026 ·

   Qiguang Chen

   DBLP profile ↗ORCID search ↗
7. SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
   ACL 2026 · Xiachong Feng
8. Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play
   ACL 2026 · Xiachong Feng
9. Two-Stage Parameter Alignment for Multi-LoRA Merging in Large Language Models
   ACL 2026 ·

   Zijian Li

   DBLP profile ↗ORCID search ↗
10. Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
    ACL 2026 ·

    Qiming Li

    DBLP profile ↗ORCID search ↗
11. x1: Learning to Think Adaptively Across Languages and Cultures
    ACL 2026 ·

    Yangfan Ye

    DBLP profile ↗ORCID search ↗
12. Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning
    ACL 2025 ·

    Lei Huang

    DBLP profile ↗ORCID search ↗
13. CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning
    ACL 2025 ·

    Yangfan Ye

    DBLP profile ↗ORCID search ↗
14. Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective
    AAAI 2025 ·

    Xinmiao Yu

    DBLP profile ↗ORCID search ↗
15. From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems
    EMNLP 2025 ·

    Zekun Zhou

    DBLP profile ↗ORCID search ↗
16. Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
    ACL 2025 ·

    Lei Huang

    DBLP profile ↗ORCID search ↗
17. MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios
    ACL 2025 ·

    Jinyang Huang

    DBLP profile ↗ORCID search ↗
18. One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit
    ACL 2025 ·

    Weitao Ma

    DBLP profile ↗ORCID search ↗
19. Reasoning Does Not Necessarily Improve Role-Playing Ability
    ACL 2025 · Xiachong Feng
20. GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization
    EMNLP 2024 ·

    Yangfan Ye

    DBLP profile ↗ORCID search ↗
21. Learning Fine-Grained Grounded Citations for Attributed Large Language Models
    ACL 2024 ·

    Lei Huang

    DBLP profile ↗ORCID search ↗
22. Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding
    EMNLP 2024 ·

    Liang Zhao

    DBLP profile ↗ORCID search ↗
23. Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models
    ACL 2024 ·

    Lei Li

    DBLP profile ↗ORCID search ↗