PPaperPicks

Jian Liang

Chinese Academy of Sciences, Institute of Automation, Center for Research on Intelligent Perception and Computing, State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Beijing, China

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

DBLP profile ↗ORCID 0000-0003-3890-1894 ↗Google Scholar ↗Homepage ↗

Venues

ICML ×4AAAI ×3CVPR ×3ICLR ×3ACL ×2NeurIPS ×2ACM MM ×1ECCV ×1ICCV ×1

Frequent coauthors

Zhengbo Wang
DBLP profile ↗ORCID search ↗
×3
Lijun Sheng
DBLP profile ↗ORCID search ↗
×3
Yongcan Yu
DBLP profile ↗ORCID search ↗
×2
Kuangpu Guo
DBLP profile ↗ORCID search ↗
×2
Yanbo Wang
DBLP profile ↗ORCID search ↗
×2
Dapeng Hu
DBLP profile ↗ORCID search ↗
×2
Dong Yan
DBLP profile ↗ORCID search ↗
×1
Yiyang Fang
DBLP profile ↗ORCID search ↗
×1
Jian Jia
DBLP profile ↗ORCID search ↗
×1
Shuo Lu
DBLP profile ↗ORCID search ↗
×1
Jiyang Guan
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
    ACL 2026 ·
    Yongcan Yu
    DBLP profile ↗ORCID search ↗
  2. What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time
    ACL 2026 ·
    Dong Yan
    DBLP profile ↗ORCID search ↗
  3. Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
    ICML 2025 ·
    Yiyang Fang
    DBLP profile ↗ORCID search ↗
  4. Cooperative Pseudo Labeling for Unsupervised Federated Classification
    ICCV 2025 ·
    Kuangpu Guo
    DBLP profile ↗ORCID search ↗
  5. Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
    CVPR 2025 ·
    Yanbo Wang
    DBLP profile ↗ORCID search ↗
  6. Exploring Vacant Classes in Label-Skewed Federated Learning
    AAAI 2025 ·
    Kuangpu Guo
    DBLP profile ↗ORCID search ↗
  7. LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application
    AAAI 2025 ·
    Jian Jia
    DBLP profile ↗ORCID search ↗
  8. LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
    ICLR 2025 ·
    Zhengbo Wang
    DBLP profile ↗ORCID search ↗
  9. Protecting Model Adaptation from Trojans in the Unlabeled Data
    AAAI 2025 ·
    Lijun Sheng
    DBLP profile ↗ORCID search ↗
  10. R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
    CVPR 2025 ·
    Lijun Sheng
    DBLP profile ↗ORCID search ↗
  11. The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
    NeurIPS 2025 ·
    Lijun Sheng
    DBLP profile ↗ORCID search ↗
  12. Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation
    ACM MM 2025 ·
    Shuo Lu
    DBLP profile ↗ORCID search ↗
  13. A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
    ICLR 2024 ·
    Zhengbo Wang
    DBLP profile ↗ORCID search ↗
  14. Backdoor Defense via Test-Time Detecting and Repairing
    CVPR 2024 ·
    Jiyang Guan
    DBLP profile ↗ORCID search ↗
  15. Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
    ICML 2024 ·
    Zhengbo Wang
    DBLP profile ↗ORCID search ↗
  16. Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation
    ICML 2024 ·
    Dapeng Hu
    DBLP profile ↗ORCID search ↗
  17. Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
    ICML 2024 · Jian Liang
  18. STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
    ECCV 2024 ·
    Yongcan Yu
    DBLP profile ↗ORCID search ↗
  19. Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
    ICLR 2024 ·
    Yanbo Wang
    DBLP profile ↗ORCID search ↗
  20. Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
    NeurIPS 2024 ·
    Dapeng Hu
    DBLP profile ↗ORCID search ↗