PPaperPicks

Yan Gao

Xiaohongshu Inc., Beijing, China

21 papers at tracked venues · 15 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0009-0004-5960-1684 ↗Google Scholar ↗Homepage ↗

Venues

ACL ×6EMNLP ×5NeurIPS ×4SIGIR ×2AAAI ×1NAACL ×1SIGKDD ×1WWW ×1

Frequent coauthors

Dongjie Yang
DBLP profile ↗ORCID search ↗
×3
Chen Zhang
DBLP profile ↗ORCID search ↗
×2
Chao Zhang
DBLP profile ↗ORCID search ↗
×2
Wei Wu
DBLP profile ↗ORCID search ↗
×1
Xiaowei Yuan
DBLP profile ↗ORCID search ↗
×1
Xuyang Zhi
DBLP profile ↗ORCID search ↗
×1
Yongqi Leng
DBLP profile ↗ORCID search ↗
×1
Zihan Niu
DBLP profile ↗ORCID search ↗
×1
Jia Chen
DBLP profile ↗ORCID search ↗
×1
Rongyang Zhang
DBLP profile ↗ORCID search ↗
×1
Fei Zhao
DBLP profile ↗ORCID search ↗
×1
Yuqing Huang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
    ACL 2026 ·
    Wei Wu
    DBLP profile ↗ORCID search ↗
  2. R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
    ACL 2026 ·
    Xiaowei Yuan
    DBLP profile ↗ORCID search ↗
  3. SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
    ACL 2026 ·
    Xuyang Zhi
    DBLP profile ↗ORCID search ↗
  4. DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision
    EMNLP 2025 ·
    Yongqi Leng
    DBLP profile ↗ORCID search ↗
  5. MoDification: Mixture of Depths Made Easy
    NAACL 2025 ·
    Chen Zhang
    DBLP profile ↗ORCID search ↗
  6. NoteLLM-2: Multimodal Large Representation Models for Recommendation
    SIGKDD 2025 ·
    Chao Zhang
    DBLP profile ↗ORCID search ↗
  7. PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval
    SIGIR 2025 ·
    Zihan Niu
    DBLP profile ↗ORCID search ↗
  8. Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions
    SIGIR 2025 ·
    Jia Chen
    DBLP profile ↗ORCID search ↗
  9. RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
    NeurIPS 2025 ·
    Rongyang Zhang
    DBLP profile ↗ORCID search ↗
  10. RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
    EMNLP 2025 ·
    Fei Zhao
    DBLP profile ↗ORCID search ↗
  11. SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
    EMNLP 2025 ·
    Yuqing Huang
    DBLP profile ↗ORCID search ↗
  12. Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair
    EMNLP 2025 ·
    Bojian Xiong
    DBLP profile ↗ORCID search ↗
  13. Towards the Law of Capacity Gap in Distilling Language Models
    ACL 2025 ·
    Chen Zhang
    DBLP profile ↗ORCID search ↗
  14. Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
    NeurIPS 2025 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗
  15. AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries
    AAAI 2024 ·
    Runqi Wang
    DBLP profile ↗ORCID search ↗
  16. DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?
    EMNLP 2024 ·
    Zhouhong Gu
    DBLP profile ↗ORCID search ↗
  17. Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
    ACL 2024 · Yan Gao
  18. NoteLLM: A Retrievable Large Language Model for Note Recommendation
    WWW 2024 ·
    Chao Zhang
    DBLP profile ↗ORCID search ↗
  19. PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
    ACL 2024 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗
  20. VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
    NeurIPS 2024 ·
    Shiwei Wu
    DBLP profile ↗ORCID search ↗
  21. Vript: A Video Is Worth Thousands of Words
    NeurIPS 2024 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗