Weijie J. Su

Venues

Frequent coauthors

Papers

1. UCS: Estimating Unseen Coverage for Improved In-Context Learning
   ACL 2026 ·

   Jiayi Xin

   DBLP profile ↗ORCID search ↗
2. Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
   ICLR 2025 ·

   Ruochen Jin

   DBLP profile ↗ORCID search ↗
3. Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
   ICLR 2025 ·

   Mingzhi Wang

   DBLP profile ↗ORCID search ↗
4. Mitigating the Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
   NeurIPS 2025 ·

   Xiang Li

   DBLP profile ↗ORCID search ↗
5. On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
   NeurIPS 2025 ·

   Weiqing He

   DBLP profile ↗ORCID search ↗
6. Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
   ICML 2025 ·

   Jiancong Xiao

   DBLP profile ↗ORCID search ↗
7. Towards Rationality in Language and Multimodal Agents: A Survey
   NAACL 2025 ·

   Bowen Jiang

   DBLP profile ↗ORCID search ↗
8. A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners
   EMNLP 2024 ·

   Bowen Jiang

   DBLP profile ↗ORCID search ↗
9. Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization
   COLT 2024 ·

   Jiancong Xiao

   DBLP profile ↗ORCID search ↗
10. Eliciting Honest Information from Authors Using Sequential Review
    AAAI 2024 ·

    Yichi Zhang

    DBLP profile ↗ORCID search ↗
11. Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
    ICML 2024 ·

    Chendi Wang

    DBLP profile ↗ORCID search ↗
12. Shifted Interpolation for Differential Privacy
    ICML 2024 ·

    Jinho Bok

    DBLP profile ↗ORCID search ↗