PPaperPicks

Haiyang Yu

Alibaba Group, China

16 papers at tracked venues · 12 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×7EMNLP ×3ICLR ×2AAAI ×1ICML ×1NAACL ×1NeurIPS ×1

Frequent coauthors

Minzheng Wang
DBLP profile ↗ORCID search ↗
×2
Zhuoqun Li
DBLP profile ↗ORCID search ↗
×2
Zhenhong Zhou
DBLP profile ↗ORCID search ↗
×2
Xinyu Lu
DBLP profile ↗ORCID search ↗
×2
Guibin Zhang
DBLP profile ↗ORCID search ↗
×1
Wenyuan Zhang
DBLP profile ↗ORCID search ↗
×1
Ruoran Li
DBLP profile ↗ORCID search ↗
×1
Tao Zou
DBLP profile ↗ORCID search ↗
×1
Xinghua Zhang
DBLP profile ↗ORCID search ↗
×1
Le Yu
DBLP profile ↗ORCID search ↗
×1
Feifan Song
DBLP profile ↗ORCID search ↗
×1
Qiaoyu Tang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. EvoRoute: Experience-Driven Self-Routing LLM Agent Systems
    ACL 2026 ·
    Guibin Zhang
    DBLP profile ↗ORCID search ↗
  2. ExpSeek: Self-Triggered Experience Seeking for Web Agents
    ACL 2026 ·
    Wenyuan Zhang
    DBLP profile ↗ORCID search ↗
  3. MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
    ACL 2026 ·
    Ruoran Li
    DBLP profile ↗ORCID search ↗
  4. DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
    ACL 2025 ·
    Minzheng Wang
    DBLP profile ↗ORCID search ↗
  5. DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
    ACL 2025 ·
    Zhuoqun Li
    DBLP profile ↗ORCID search ↗
  6. EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
    EMNLP 2025 ·
    Tao Zou
    DBLP profile ↗ORCID search ↗
  7. IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
    ACL 2025 ·
    Xinghua Zhang
    DBLP profile ↗ORCID search ↗
  8. On the Role of Attention Heads in Large Language Model Safety
    ICLR 2025 ·
    Zhenhong Zhou
    DBLP profile ↗ORCID search ↗
  9. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
    ICLR 2025 ·
    Zhuoqun Li
    DBLP profile ↗ORCID search ↗
  10. Transferable Post-training via Inverse Value Learning
    NAACL 2025 ·
    Xinyu Lu
    DBLP profile ↗ORCID search ↗
  11. How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
    EMNLP 2024 ·
    Zhenhong Zhou
    DBLP profile ↗ORCID search ↗
  12. Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
    ICML 2024 ·
    Le Yu
    DBLP profile ↗ORCID search ↗
  13. Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
    EMNLP 2024 ·
    Minzheng Wang
    DBLP profile ↗ORCID search ↗
  14. Preference Ranking Optimization for Human Alignment
    AAAI 2024 ·
    Feifan Song
    DBLP profile ↗ORCID search ↗
  15. Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
    NeurIPS 2024 ·
    Qiaoyu Tang
    DBLP profile ↗ORCID search ↗
  16. SoFA: Shielded On-the-fly Alignment via Priority Rule Following
    ACL 2024 ·
    Xinyu Lu
    DBLP profile ↗ORCID search ↗