PPaperPicks

Xiao Liu

Microsoft Research Asia, Beijing, China

16 papers at tracked venues · 13 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-8893-366X ↗Google Scholar ↗Homepage ↗

Venues

ACL ×7ICML ×4AAAI ×1EMNLP ×1NAACL ×1NeurIPS ×1WSDM ×1

Frequent coauthors

Haebin Shin
DBLP profile ↗ORCID search ↗
×2
Yiming Huang
DBLP profile ↗ORCID search ↗
×2
Boci Peng
DBLP profile ↗ORCID search ↗
×1
Kailai Yang
DBLP profile ↗ORCID search ↗
×1
Yi-Fan Lu
DBLP profile ↗ORCID search ↗
×1
Junu Kim
DBLP profile ↗ORCID search ↗
×1
Zhong-Zhi Li
DBLP profile ↗ORCID search ↗
×1
Sungjin Park
DBLP profile ↗ORCID search ↗
×1
Yaoxiang Wang
DBLP profile ↗ORCID search ↗
×1
Ruizhe Wang
DBLP profile ↗ORCID search ↗
×1
Jie Wu
DBLP profile ↗ORCID search ↗
×1
Hao Sun
DBLP profile ↗ORCID search ↗
×1

Papers

  1. COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval
    ACL 2026 ·
    Boci Peng
    DBLP profile ↗ORCID search ↗
  2. Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
    ACL 2026 ·
    Kailai Yang
    DBLP profile ↗ORCID search ↗
  3. DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
    ACL 2026 ·
    Haebin Shin
    DBLP profile ↗ORCID search ↗
  4. EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain
    ACL 2026 ·
    Yi-Fan Lu
    DBLP profile ↗ORCID search ↗
  5. LayerNorm Induces Recency Bias in Transformer Decoders
    ACL 2026 ·
    Junu Kim
    DBLP profile ↗ORCID search ↗
  6. Too Long, Do Re-weighting for Efficient LLM Reasoning Compression
    ACL 2026 ·
    Zhong-Zhi Li
    DBLP profile ↗ORCID search ↗
  7. Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
    NAACL 2025 ·
    Sungjin Park
    DBLP profile ↗ORCID search ↗
  8. EpiCoder: Encompassing Diversity and Complexity in Code Generation
    ICML 2025 ·
    Yaoxiang Wang
    DBLP profile ↗ORCID search ↗
  9. Key-Point-Driven Data Synthesis with Its Enhancement on Mathematical Reasoning
    AAAI 2025 ·
    Yiming Huang
    DBLP profile ↗ORCID search ↗
  10. Optimizing Large Language Model Training Using FP4 Quantization
    ICML 2025 ·
    Ruizhe Wang
    DBLP profile ↗ORCID search ↗
  11. Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling
    ICML 2025 ·
    Haebin Shin
    DBLP profile ↗ORCID search ↗
  12. Teaching Your Models to Understand Code via Focal Preference Alignment
    EMNLP 2025 ·
    Jie Wu
    DBLP profile ↗ORCID search ↗
  13. Competition-Level Problems are Effective LLM Evaluators
    ACL 2024 ·
    Yiming Huang
    DBLP profile ↗ORCID search ↗
  14. LEAD: Liberal Feature-based Distillation for Dense Retrieval
    WSDM 2024 ·
    Hao Sun
    DBLP profile ↗ORCID search ↗
  15. Not All Tokens Are What You Need for Pretraining
    NeurIPS 2024 ·
    Zhenghao Lin
    DBLP profile ↗ORCID search ↗
  16. Using Left and Right Brains Together: Towards Vision and Language Planning
    ICML 2024 ·
    Jun Cen
    DBLP profile ↗ORCID search ↗