PPaperPicks

Daniel Dajun Zeng

Chinese Academy of Sciences, Institute of Automation, Beijing, China

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

DBLP profile ↗ORCID 0000-0002-9046-222X ↗Google Scholar ↗Homepage ↗

Venues

AAAI ×3ACL ×3EMNLP ×3WWW ×3ICML ×2AAMAS ×1SIGIR ×1

Frequent coauthors

Yifei Wang
DBLP profile ↗ORCID search ↗
×3
Xingjin Wang
DBLP profile ↗ORCID search ↗
×2
Mengyu Xiang
DBLP profile ↗ORCID search ↗
×2
Yuxuan Song
DBLP profile ↗ORCID search ↗
×2
Gang Zhou
DBLP profile ↗ORCID search ↗
×1
Songran Bai
DBLP profile ↗ORCID search ↗
×1
Yu Sheng
DBLP profile ↗ORCID search ↗
×1
Haorui Li
DBLP profile ↗ORCID search ↗
×1
Minjie Yuan
DBLP profile ↗ORCID search ↗
×1
Ruike Zhang
DBLP profile ↗ORCID search ↗
×1
Youzhi Zhang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Entropy Scheduling in Reinforcement Learning for Large Language Models
    ACL 2026 ·
    Xingjin Wang
    DBLP profile ↗ORCID search ↗
  2. Reinforcement Learning-Guided Adaptive Tuning for Out-of-Distribution Harmful Text Detection
    ACL 2026 ·
    Mengyu Xiang
    DBLP profile ↗ORCID search ↗
  3. Spectral-Adaptive Adversarial Hashing for Robust Image Retrieval
    SIGIR 2026 ·
    Gang Zhou
    DBLP profile ↗ORCID search ↗
  4. A Self-Supervised Adaptive Tuning Approach for Out-of-Distribution Social Media Bot Detection
    WWW 2025 ·
    Yuxuan Song
    DBLP profile ↗ORCID search ↗
  5. Alleviating Performance Disparity in Adversarial Spatiotemporal Graph Learning Under Zero-Inflated Distribution
    AAAI 2025 ·
    Songran Bai
    DBLP profile ↗ORCID search ↗
  6. Dynamic Detection of Sarcasm Topic-Target Pairs via LLM-Based Knowledge Alignment
    WWW 2025 ·
    Mengyu Xiang
    DBLP profile ↗ORCID search ↗
  7. Knowledge-Enhanced Hierarchical Heterogeneous Graph for Personality Identification with Limited Training Data
    AAAI 2025 ·
    Yuxuan Song
    DBLP profile ↗ORCID search ↗
  8. Learning Dynamics in Continual Pre-Training for Large Language Models
    ICML 2025 ·
    Xingjin Wang
    DBLP profile ↗ORCID search ↗
  9. Learning Theorem Rationale for Improving the Mathematical Reasoning Capability of Large Language Models
    AAAI 2025 ·
    Yu Sheng
    DBLP profile ↗ORCID search ↗
  10. Offline Meta Reinforcement Learning with Weighted Policy Constraints and Proximal Context Collection
    AAMAS 2025 ·
    Haorui Li
    DBLP profile ↗ORCID search ↗
  11. POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation
    EMNLP 2025 ·
    Yifei Wang
    DBLP profile ↗ORCID search ↗
  12. Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?
    ACL 2025 ·
    Yifei Wang
    DBLP profile ↗ORCID search ↗
  13. A Heterogeneous Network fused with Context-aware Contrastive Learning for Sarcasm Topic-Target Pair Identification
    WWW 2024 ·
    Minjie Yuan
    DBLP profile ↗ORCID search ↗
  14. An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification
    EMNLP 2024 ·
    Ruike Zhang
    DBLP profile ↗ORCID search ↗
  15. DAG-Based Column Generation for Adversarial Team Games
    ICML 2024 ·
    Youzhi Zhang
    DBLP profile ↗ORCID search ↗
  16. Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
    EMNLP 2024 ·
    Yifei Wang
    DBLP profile ↗ORCID search ↗