PPaperPicks

Xu Sun

Peking University, School of EECS, MOE Key Lab of Computational Linguistics, China

19 papers at tracked venues · 14 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-8241-9320 ↗Homepage ↗

Venues

ACL ×5EMNLP ×3AAAI ×2ACM MM ×2CVPR ×2ICLR ×2ECCV ×1NAACL ×1NeurIPS ×1

Frequent coauthors

Yuchi Wang
DBLP profile ↗ORCID search ↗
×4
Linli Yao
DBLP profile ↗ORCID search ↗
×3
Shicheng Li
DBLP profile ↗ORCID search ↗
×2
Zhiyu Xu
DBLP profile ↗ORCID search ↗
×1
Yi Liu
DBLP profile ↗ORCID search ↗
×1
Kun Ouyang
DBLP profile ↗ORCID search ↗
×1
Lei Li
DBLP profile ↗ORCID search ↗
×1
Qingxiu Dong
DBLP profile ↗ORCID search ↗
×1
Zhiyuan Zhang
DBLP profile ↗ORCID search ↗
×1
Yuanxin Liu
DBLP profile ↗ORCID search ↗
×1
Shuhuai Ren
DBLP profile ↗ORCID search ↗
×1
Lean Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
    ACL 2026 ·
    Zhiyu Xu
    DBLP profile ↗ORCID search ↗
  2. TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
    AAAI 2026 ·
    Shicheng Li
    DBLP profile ↗ORCID search ↗
  3. ATLANTIS: Weak-to-Strong Learning via Importance Sampling
    ACL 2025 ·
    Yi Liu
    DBLP profile ↗ORCID search ↗
  4. Generative Frame Sampler for Long Video Understanding
    ACL 2025 ·
    Linli Yao
    DBLP profile ↗ORCID search ↗
  5. InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation
    AAAI 2025 ·
    Yuchi Wang
    DBLP profile ↗ORCID search ↗
  6. PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
    ACL 2025 ·
    Kun Ouyang
    DBLP profile ↗ORCID search ↗
  7. RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
    EMNLP 2025 ·
    Yuchi Wang
    DBLP profile ↗ORCID search ↗
  8. Temporal Reasoning Transfer from Text to Video
    ICLR 2025 ·
    Lei Li
    DBLP profile ↗ORCID search ↗
  9. TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
    ACM MM 2025 ·
    Linli Yao
    DBLP profile ↗ORCID search ↗
  10. VidTwin: Video VAE with Decoupled Structure and Dynamics
    CVPR 2025 ·
    Yuchi Wang
    DBLP profile ↗ORCID search ↗
  11. A Survey on In-context Learning
    EMNLP 2024 ·
    Qingxiu Dong
    DBLP profile ↗ORCID search ↗
  12. Edit As You Wish: Video Caption Editing with Multi-grained User Control
    ACM MM 2024 ·
    Linli Yao
    DBLP profile ↗ORCID search ↗
  13. Enhancing Byzantine-Resistant Aggregations with Client Embedding
    EMNLP 2024 ·
    Zhiyuan Zhang
    DBLP profile ↗ORCID search ↗
  14. LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?
    NAACL 2024 ·
    Yuchi Wang
    DBLP profile ↗ORCID search ↗
  15. TempCompass: Do Video LLMs Really Understand Videos?
    ACL 2024 ·
    Yuanxin Liu
    DBLP profile ↗ORCID search ↗
  16. TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
    CVPR 2024 ·
    Shuhuai Ren
    DBLP profile ↗ORCID search ↗
  17. Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
    ICLR 2024 ·
    Lean Wang
    DBLP profile ↗ORCID search ↗
  18. VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
    ECCV 2024 ·
    Shicheng Li
    DBLP profile ↗ORCID search ↗
  19. Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
    NeurIPS 2024 ·
    Wenkai Yang
    DBLP profile ↗ORCID search ↗