Yong Liu

Venues

Frequent coauthors

Papers

1. Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge
   AAAI 2026 ·

   Pengwei Tang

   DBLP profile ↗ORCID search ↗
2. ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
   ICLR 2025 ·

   Pengwei Tang

   DBLP profile ↗ORCID search ↗
3. AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization
   AAAI 2025 ·

   Xiao Zhang

   DBLP profile ↗ORCID search ↗
4. Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
   NeurIPS 2025 ·

   Qijiong Liu

   DBLP profile ↗ORCID search ↗
5. Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
   NeurIPS 2025 ·

   Chen Qian

   DBLP profile ↗ORCID search ↗
6. Do not Abstain! Identify and Solve the Uncertainty
   ACL 2025 ·

   Jingyu Liu

   DBLP profile ↗ORCID search ↗
7. REEF: Representation Encoding Fingerprints for Large Language Models
   ICLR 2025 ·

   Jie Zhang

   DBLP profile ↗ORCID search ↗
8. Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
   ICML 2025 ·

   Zeyu Gan

   DBLP profile ↗ORCID search ↗
9. Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
   ACL 2025 ·

   Wei Yao

   DBLP profile ↗ORCID search ↗
10. SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin
    EMNLP 2025 ·

    Hao Yi

    DBLP profile ↗ORCID search ↗
11. SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
    NeurIPS 2025 ·

    Ruyue Liu

    DBLP profile ↗ORCID search ↗
12. Stability and Sharper Risk Bounds with Convergence Rate Õ(1/n2)
    NeurIPS 2025 ·

    Bowei Zhu

    DBLP profile ↗ORCID search ↗
13. Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
    ICLR 2025 ·

    Wenkai Yang

    DBLP profile ↗ORCID search ↗
14. The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
    ACL 2025 ·

    Chen Qian

    DBLP profile ↗ORCID search ↗
15. Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization
    ICLR 2025 ·

    Zixuan Gong

    DBLP profile ↗ORCID search ↗
16. Towards Improved Risk Bounds for Transductive Learning
    IJCAI 2025 ·

    Bowei Zhu

    DBLP profile ↗ORCID search ↗
17. Towards Reward Fairness in RLHF: From a Resource Allocation Perspective
    ACL 2025 ·

    Sheng Ouyang

    DBLP profile ↗ORCID search ↗
18. Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
    ICLR 2025 ·

    Zeyu Gan

    DBLP profile ↗ORCID search ↗
19. Understanding Model Ensemble in Transferable Adversarial Attack
    ICML 2025 ·

    Wei Yao

    DBLP profile ↗ORCID search ↗
20. ASWT-SGNN: Adaptive Spectral Wavelet Transform-Based Self-Supervised Graph Neural Network
    AAAI 2024 ·

    Ruyue Liu

    DBLP profile ↗ORCID search ↗
21. Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses
    ICML 2024 ·

    Shaojie Li

    DBLP profile ↗ORCID search ↗
22. Concentration Inequalities for General Functions of Heavy-Tailed Random Variables
    ICML 2024 ·

    Shaojie Li

    DBLP profile ↗ORCID search ↗
23. Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
    NeurIPS 2024 ·

    Xinhao Yao

    DBLP profile ↗ORCID search ↗
24. FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
    AAAI 2024 ·

    Jian Li

    DBLP profile ↗ORCID search ↗
25. High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm
    AAAI 2024 ·

    Jian Li

    DBLP profile ↗ORCID search ↗
26. IdmGAE: Importance-Inspired Dynamic Masking for Graph Autoencoders
    SIGIR 2024 ·

    Ge Chen

    DBLP profile ↗ORCID search ↗
27. Neural Retrievers are Biased Towards LLM-Generated Content
    SIGKDD 2024 ·

    Sunhao Dai

    DBLP profile ↗ORCID search ↗
28. Perfect Alignment May be Poisonous to Graph Contrastive Learning
    ICML 2024 ·

    Jingyu Liu

    DBLP profile ↗ORCID search ↗
29. Reimagining Graph Classification from a Prototype View with Optimal Transport: Algorithm and Theorem
    SIGKDD 2024 ·

    Chen Qian

    DBLP profile ↗ORCID search ↗
30. Towards Sharper Risk Bounds for Minimax Problems
    IJCAI 2024 ·

    Bowei Zhu

    DBLP profile ↗ORCID search ↗
31. Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
    NeurIPS 2024 ·

    Ruifeng Ren

    DBLP profile ↗ORCID search ↗
32. WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets
    AAAI 2024 ·

    Zhirui Yang

    DBLP profile ↗ORCID search ↗